{"id":"b5210932-6ac8-4947-af43-c99df9f16dbd","entityType":"agent","slug":"clawhub-parmasanandgarlic-farmdash-trail-intelligence","name":"FarmDash Trail Intelligence","canonicalUrl":"https://www.xpersona.co/agent/clawhub-parmasanandgarlic-farmdash-trail-intelligence","canonicalPath":"/agent/clawhub-parmasanandgarlic-farmdash-trail-intelligence","generatedAt":"2026-10-09T23:21:27.937Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":null},"description":"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes. Skill: FarmDash Trail Intelligence Owner: parmasanandgarlic Summary: Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes. Tags: 0x:1.0.11, aave:1.0.14, agent-workflows:1.0.11, agentic-defi:1.0.11, ai-agent:1.0.20, airdrop:1.0.16, airdrop-farming:1.0.19, airdrop-hunter:1.0.19, airdrop-hunting:1.0.16, airdrop-rese","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s177a1xxprmvcbyygraxwvbf5s83qzs6:farmdash-trail-intelligence","sourceUrl":"https://clawhub.ai/parmasanandgarlic/farmdash-trail-intelligence","homepage":"https://clawhub.ai/parmasanandgarlic/skills/farmdash-trail-intelligence","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/parmasanandgarlic/farmdash-trail-intelligence","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/parmasanandgarlic/skills/farmdash-trail-intelligence","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":40,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes. "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":null},"stars":null,"forks":null,"downloads":2229,"packageName":null,"latestVersion":"1.0.21","tractionLabel":"2.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T17:18:38.253Z","lastCrawledAt":"2026-10-09T17:18:38.253Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T17:18:38.253Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.21","createdAt":"2026-10-05T00:53:15.461Z","changelog":"FarmDash Trail Intelligence v1.0.21 - Increased free Scout tier rate limit from 5 to 30 requests per 24h. - Updated documentation to reflect new Scout tier limits. - Removed the obsolete file: skill-card.md.","fileCount":4,"zipByteSize":24512},{"version":"1.0.20","createdAt":"2026-09-26T08:55:36.384Z","changelog":"FarmDash Trail Intelligence 1.0.20 - Removed sample documentation file: skill-card.md. - No functional logic or interface changes; only documentation assets modified.","fileCount":4,"zipByteSize":24389},{"version":"1.0.19","createdAt":"2026-09-09T05:09:06.985Z","changelog":"FarmDash Trail Intelligence 1.0.19 - Updated SKILL.md to clarify and condense the description, emphasizing the read-only nature and DeFi intelligence focus. - Improved language for affiliate routing, commercial disclosure, and user capability boundaries. - Revised wording and structure for guidance on rate limits and upgrade messaging. - No functional changes to the skill logic; documentation and policy only. - Removed the sample file skill-card.md.","fileCount":4,"zipByteSize":24254},{"version":"1.0.18","createdAt":"2026-09-07T18:05:19.591Z","changelog":"- Removed the skill-card.md file. - Updated skill version to 3.1.2 with minor improvements to tags, description, and versioning in SKILL.md. - Clarified purpose and scope in the short description and tags. - No functional or breaking changes to core logic.","fileCount":4,"zipByteSize":23749},{"version":"1.0.17","createdAt":"2026-08-04T04:59:53.868Z","changelog":"FarmDash Trail Intelligence 1.0.17 - Updated and streamlined skill documentation, removing redundant and outdated details. - Simplified tags for improved discoverability and focus on core DeFi and airdrop functionalities. - Updated the description to better reflect current coverage: DeFi protocol research, Trail Heat, FarmScore, airdrops, points, and sybil risk. - Clarified monetization, routing, and user safety policies for more transparency. - Removed the skill-card.md file for documentation consistency and to avoid duplication.","fileCount":4,"zipByteSize":20996},{"version":"1.0.16","createdAt":"2026-06-28T01:36:08.094Z","changelog":"- Removed the documentation file skill-card.md. - No functional or feature changes; only a reduction in file count. - All core research and DeFi farming analytics capabilities are unchanged.","fileCount":4,"zipByteSize":21599},{"version":"1.0.15","createdAt":"2026-06-25T23:50:21.225Z","changelog":"FarmDash Trail Intelligence 3.0.0 is a major upgrade with new monetization policy, clearer capability boundaries, and improved protocol research. - Removed redundant documentation, including the skill-card.md file. - Shortened and focused the skill description to highlight key research capabilities and new features like yield decay and wallet clustering. - Introduced a transparent affiliate and value-gated monetization protocol, with mandatory disclosures and specific opt-ins for paid upgrades. - Clarified permissions, execution separation, and privacy boundaries for end users. - Expanded documentation on Pioneer-tier unlocks and fee structure. - Improved clarity on Trail Heat scoring, deep research tools, and DeFi risk handling.","fileCount":4,"zipByteSize":21626},{"version":"1.0.14","createdAt":"2026-06-01T06:01:16.449Z","changelog":"- Removed the sample file: skill-card.md. - Updated the SKILL.md to include an additional \"Anti-Evasion Gate\" warning, clarifying that airdrop simulations and Sybil risk indicators are for risk management and compliance only—not to be used for evading protocol controls or rules. - No changes to core functionality or API; the update focuses on improved ethical and compliance messaging.","fileCount":4,"zipByteSize":20610}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s177a1xxprmvcbyygraxwvbf5s83qzs6:farmdash-trail-intelligence","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T23:21:27.933Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-parmasanandgarlic-farmdash-trail-intelligence/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":null},"readme":"Skill: FarmDash Trail Intelligence\n\nOwner: parmasanandgarlic\n\nSummary: Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\n\nTags: 0x:1.0.11, aave:1.0.14, agent-workflows:1.0.11, agentic-defi:1.0.11, ai-agent:1.0.20, airdrop:1.0.16, airdrop-farming:1.0.19, airdrop-hunter:1.0.19, airdrop-hunting:1.0.16, airdrop-research:1.0.21, airdrop-tracker:1.0.19, airdrops:1.0.21, alchemy:1.0.14, allocation-analysis:1.0.21, alpha-research:1.0.16, analytics:1.0.16, arbitrum:1.0.19, autonomous-agent:1.0.16, autonomous-finance:1.0.19, base:1.0.19, blockchain-analytics:1.0.20, blockchain-forensics:1.0.16, blockchain-research:1.0.21, capital-efficiency:1.0.11, capital-routes:1.0.19, chain-breakdown:1.0.11, clawhub:1.0.20, cross-chain:1.0.11, crypto:1.0.16, crypto-agent:1.0.20, crypto-airdrops:1.0.19, crypto-intelligence:1.0.20, crypto-opportunities:1.0.20, crypto-research:1.0.21, data-api:1.0.11, data-freshness:1.0.21, defi:1.0.20, defi-agent:1.0.20, defi-discovery:1.0.20, defi-events:1.0.11, defi-intelligence:1.0.21, defi-opportunities:1.0.20, defi-protocols:1.0.18, defi-research:1.0.21, defillama:1.0.19, depin:1.0.17, eigenlayer:1.0.19, ethereum:1.0.19, etherfi:1.0.19, evidence-based-research:1.0.21, evm:1.0.11, farmdash:1.0.21, farming:1.0.10, farming-research:1.0.11, farming-strategy:1.0.11, farmscore:1.0.20, helius:1.0.14, historical-analytics:1.0.11, hyperliquid:1.0.19, intelligence:1.0.16, jupiter:1.0.19, kamino:1.0.19, l2:1.0.16, latest:1.0.21, latestdefi:1.0.15, layer-2:1.0.17, lifi:1.0.11, market-data:1.0.20, market-intelligence:1.0.20, mcp:1.0.21, mcp-server:1.0.19, mev:1.0.16, model-context-protocol:1.0.20, monetization:1.0.15, no-signing:1.0.11, no-trading:1.0.11, non-custodial:1.0.11, on-chain-intelligence:1.0.20, onchain:1.0.16, onchain-analytics:1.0.21, onchain-intelligence:1.0.20, onchain-research:1.0.20, openclaw:1.0.20, opportunity-discovery:1.0.21, optimism:1.0.11, pendle:1.0.19, pioneer-tier:1.0.15, points-farming:1.0.19, points-projections:1.0.14, points-simulation:1.0.11, polygon:1.0.11, portfolio:1.0.16, portfolio-allocation:1.0.11, portfolio-analysis:1.0.20, portfolio-diagnostics:1.0.21, portfolio-optimization:1.0.20, portfolio-simulation:1.0.11, protocol-analysis:1.0.20, protocol-discovery:1.0.20, protocol-intelligence:1.0.11, protocol-ranking:1.0.21, protocol-research:1.0.21, protocol-risk:1.0.20, protocol-risk-analysis:1.0.20, protocol-scoring:1.0.21, read-only:1.0.21, research:1.0.16, research-agent:1.0.20, research-only:1.0.11, restaking:1.0.19, risk-analysis:1.0.20, risk-factors:1.0.20, risk-management:1.0.14, route-feasibility:1.0.11, route-previews:1.0.21, signal-architect:1.0.11, solana:1.0.19, source-attribution:1.0.21, supervised-agent:1.0.9, sybil:1.0.16, sybil-analysis:1.0.11, sybil-detector:1.0.19, sybil-risk:1.0.21, token-prices:1.0.20, trail-heat:1.0.21, trail-intelligence:1.0.20, trail-marshal:1.0.11, trailheat:1.0.20, trend-analysis:1.0.11, tvl:1.0.11, wagon-steward:1.0.11, wallet-analysis:1.0.21, wallet-analytics:1.0.19, wallet-audit:1.0.14, wallet-balances:1.0.20, wallet-clustering:1.0.16, wallet-health:1.0.11, web3:1.0.19, web3-agent:1.0.20, web3-research:1.0.20, x402:1.0.11, yield-decay:1.0.16, yield-farming:1.0.19, yield-optimizer:1.0.19, yield-simulation:1.0.11, zero-custody:1.0.19\n\nVersion history:\n\nv1.0.21 | 2026-10-05T00:53:15.461Z | user\n\nFarmDash Trail Intelligence v1.0.21\n\n- Increased free Scout tier rate limit from 5 to 30 requests per 24h.\n- Updated documentation to reflect new Scout tier limits.\n- Removed the obsolete file: skill-card.md.\n\nv1.0.20 | 2026-09-26T08:55:36.384Z | user\n\nFarmDash Trail Intelligence 1.0.20\n\n- Removed sample documentation file: skill-card.md.\n- No functional logic or interface changes; only documentation assets modified.\n\nv1.0.19 | 2026-09-09T05:09:06.985Z | user\n\nFarmDash Trail Intelligence 1.0.19\n\n- Updated SKILL.md to clarify and condense the description, emphasizing the read-only nature and DeFi intelligence focus.\n- Improved language for affiliate routing, commercial disclosure, and user capability boundaries.\n- Revised wording and structure for guidance on rate limits and upgrade messaging.\n- No functional changes to the skill logic; documentation and policy only.\n- Removed the sample file skill-card.md.\n\nv1.0.18 | 2026-09-07T18:05:19.591Z | user\n\n- Removed the skill-card.md file.\n- Updated skill version to 3.1.2 with minor improvements to tags, description, and versioning in SKILL.md.\n- Clarified purpose and scope in the short description and tags.\n- No functional or breaking changes to core logic.\n\nv1.0.17 | 2026-08-04T04:59:53.868Z | user\n\nFarmDash Trail Intelligence 1.0.17\n\n- Updated and streamlined skill documentation, removing redundant and outdated details.\n- Simplified tags for improved discoverability and focus on core DeFi and airdrop functionalities.\n- Updated the description to better reflect current coverage: DeFi protocol research, Trail Heat, FarmScore, airdrops, points, and sybil risk.\n- Clarified monetization, routing, and user safety policies for more transparency.\n- Removed the skill-card.md file for documentation consistency and to avoid duplication.\n\nv1.0.16 | 2026-06-28T01:36:08.094Z | user\n\n- Removed the documentation file skill-card.md.\n- No functional or feature changes; only a reduction in file count.\n- All core research and DeFi farming analytics capabilities are unchanged.\n\nv1.0.15 | 2026-06-25T23:50:21.225Z | user\n\nFarmDash Trail Intelligence 3.0.0 is a major upgrade with new monetization policy, clearer capability boundaries, and improved protocol research.\n\n- Removed redundant documentation, including the skill-card.md file.\n- Shortened and focused the skill description to highlight key research capabilities and new features like yield decay and wallet clustering.\n- Introduced a transparent affiliate and value-gated monetization protocol, with mandatory disclosures and specific opt-ins for paid upgrades.\n- Clarified permissions, execution separation, and privacy boundaries for end users.\n- Expanded documentation on Pioneer-tier unlocks and fee structure.\n- Improved clarity on Trail Heat scoring, deep research tools, and DeFi risk handling.\n\nv1.0.14 | 2026-06-01T06:01:16.449Z | user\n\n- Removed the sample file: skill-card.md.\n- Updated the SKILL.md to include an additional \"Anti-Evasion Gate\" warning, clarifying that airdrop simulations and Sybil risk indicators are for risk management and compliance only—not to be used for evading protocol controls or rules.\n- No changes to core functionality or API; the update focuses on improved ethical and compliance messaging.\n\nv1.0.13 | 2026-06-01T02:02:25.957Z | user\n\nFarmDash Trail Intelligence v1.0.13\n\n- Deprecated and removed the sample skill-card.md file.\n- No changes to code or functional logic; this is a documentation cleanup release.\n\nv1.0.12 | 2026-05-30T23:46:43.997Z | user\n\nfarmdash-trail-intelligence 1.0.12\n\n- Added SKILL.json file for configuration or registry purposes.\n- Removed skill-card.md documentation file.\n- No code or feature changes; update is limited to file additions/removals.\n\nv1.0.11 | 2026-05-25T21:58:39.100Z | user\n\nNo user-facing changes detected in this version.\n\n- No file changes were found between this and the previous release.\n- Functionality, research tools, risk guidelines, and disclosures remain unchanged.\n- Users can continue to use the skill as previously documented.\n\nv1.0.10 | 2026-05-25T05:35:20.271Z | user\n\nFarmDash Trail Intelligence 1.0.10 Changelog\n\n- Updated environment details to clarify that Scout tier can be used without an API key or with the public fd_scout_free token.\n- Metadata now reflects free Scout mode as keyless and specifies the public free API key.\n- No logic or behavior changes; documentation improvements only.\n\nv1.0.9 | 2026-05-24T22:48:09.838Z | user\n\nNo user-facing changes in this release.\n\n- Version incremented with no detected file or documentation changes.\n\nv1.0.8 | 2026-05-22T17:16:03.447Z | user\n\nFarmDash Trail Intelligence 1.0.8\n\n- No file changes detected in this version.\n- No updates or modifications to features, documentation, or metadata.\n\nv1.0.7 | 2026-05-19T21:07:43.241Z | user\n\nFarmDash Trail Intelligence 2.1.0 introduces a new minor version with no detected file changes.\n\n- Version bumped from 2.0.0 to 2.1.0 in metadata.\n- No functional or documentation changes were detected in this release.\n\nv1.0.6 | 2026-05-13T14:29:22.051Z | user\n\nNo user-facing changes in this release.\n\n- Version incremented with no detected file changes.\n- No additions, removals, or updates to skill documentation or logic.\n\nv1.0.5 | 2026-05-13T04:35:54.321Z | user\n\nMajor update: Skill rewritten as a read-only research tool for DeFi farming analysis only—no more trade execution or custody functions.\n\n- Skill now enforces strict read-only access: it cannot execute trades, sign messages, or handle sensitive keys.\n- All \"close-to-action\" flows removed; analysis now ends with research and recommendations only.\n- Explicit affiliate disclosure and fair linking requirements introduced; partnership links appear only with clear user consent and must be accompanied by direct URLs.\n- Enhanced risk and security warnings: agent must clarify research is not financial advice; all actions are user's responsibility.\n- Skill description, permissions, and tool instructions updated throughout to reflect new research-only model and OpenClaw compatibility.\n\nv1.0.4 | 2026-04-26T17:50:07.124Z | user\n\nNo user-facing changes in this release.\n\n- Version updated from 1.1.0 to 1.0.4, but no code or documentation changes detected.\n\nv1.0.3 | 2026-04-26T06:28:37.484Z | user\n\nFarmDash Trail Intelligence v1.0.3 — Version update (no file changes)\n\n- Version incremented from 1.0.2 to 1.0.3, but no file or functionality changes detected.\n- All features, documentation, and tool interfaces remain unchanged from the previous version.\n- No user-facing improvements or bug fixes included in this release.\n\nv1.0.2 | 2026-04-21T19:55:16.944Z | user\n\nFarmDash Trail Intelligence v1.2.0\n\n- Added wallet balance and token price context to research/analysis steps for more budget-aware, actionable recommendations.\n- Expanded skill description and tags to include \"security\" and \"tokenomics.\"\n- Introduced cross-skill composition guidance: clarified how to chain Trail Intelligence with Signal Architect and Futures Strategist for research-to-execution workflows.\n- Specified that cross-chain recommendations must factor in bridging/operational costs and not simply rely on routing details.\n- Included reference to a shared operating model for more cohesive multi-agent behavior.\n- General doc improvements for clarity, decision pipelines, and integration best practices.\n\nv1.0.1 | 2026-04-13T22:40:57.171Z | user\n\nNo changes detected. This version does not alter any files or functionality.\n\nv1.0.0 | 2026-03-28T00:46:38.146Z | user\n\nFarmDash Trail Intelligence 1.0.0 — Initial release\n\n- Launches DeFi farming research and strategy capabilities powered by FarmDash intelligence tools.\n- Provides live protocol ranking (Trail Heat), historical analysis, wallet sybil risk audit, outcome simulation, portfolio optimization, and event monitoring.\n- Every analysis concludes with actionable next steps, including FarmDash swap execution and protocol referral links for user action.\n- Automates protocol entry, swaps, bridging, and event-driven recommendations with clear, user-friendly instructions and links.\n- Supports DeFi opportunity evaluation, farming comparison, airdrop signal checks, wallet risk assessment, and real-time protocol monitoring.\n\nArchive index:\n\nArchive v1.0.21: 4 files, 24512 bytes\n\nFiles: skill-card.md (2397b), SKILL.json (26119b), SKILL.md (42785b), _meta.json (147b)\n\nFile v1.0.21:SKILL.md\n\n---\r\nname: FarmDash Trail Intelligence\r\ndescription: \"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\"\r\ntags: [\"defi\",\"defi-research\",\"airdrop-tracker\",\"airdrop-hunter\",\"crypto-airdrops\",\"points-farming\",\"airdrop-farming\",\"defi-protocols\",\"protocol-ranking\",\"onchain-analytics\",\"sybil-risk\",\"trail-heat\",\"farmscore\",\"restaking\",\"solana\",\"openclaw\",\"mcp\",\"zero-custody\",\"web3\",\"farmdash\"]\r\nauthor: FarmDash Pioneers (@Parmasanandgarlic)\r\nhomepage: https://www.farmdash.one/agents\r\nversion: \"3.1.3\"\r\nicon: 🔭\r\nenv:\r\n  FARMDASH_API_KEY:\r\n    description: \"Optional Bearer token for Pioneer tier (higher rate limits and deep research tools). Scout tier (30 req / 24h) requires no key or can use the public fd_scout_free token. Never share private keys, seed phrases, or mnemonics with this skill.\"\r\n    required: false\r\nmetadata: {\"openclaw\":{\"homepage\":\"https://www.farmdash.one/agents\",\"skillKey\":\"farmdash-trail-intelligence\",\"primaryEnv\":\"FARMDASH_API_KEY\",\"apiKeyRequired\":false,\"freeScoutKeyless\":true,\"freeScoutKey\":\"fd_scout_free\",\"execution\":\"read-only\"}}\r\n---\r\n\r\n# FarmDash Trail Intelligence — Agent Research Manual\r\n\r\n> Use this skill when choosing where to farm: ranking protocols, airdrops, or points programs by Trail Heat, checking sybil risk, or asking \"where should I deploy capital next?\"\r\n\r\n> [!NOTE]\r\n> **THEMATIC METAPHOR DISCLAIMER**\r\n> FarmDash is exclusively a decentralized finance (DeFi) software and AI agent intelligence platform. The \"farming,\" \"trail,\" \"wagon,\" and \"frontier\" terminology is a gamified visual theme representing crypto yield hunting and airdrop points farming. It does not relate to physical agriculture or agrifood industries.\r\n\r\n> [!IMPORTANT]\r\n> **ZERO-CUSTODY CRITICAL BOUNDARY & ANTI-EVASION POLICY**\r\n> This skill is strictly a read-only research surface and does NOT execute any state-changing swaps, deposits, or perps, nor does it request, hold, or transmit private keys, seed phrases, or mnemonics.\r\n> \r\n> **Anti-Evasion Gate:**\r\n> All airdrop simulations, Sybil risk indicators, and concurrency analytics are read-only planning heuristics. They are provided solely for risk management and system rate-limit compliance. Operators must never use this guidance to evade protocol anti-abuse controls, circumvent terms of service, or engage in deceptive sybil behavior.\r\n\r\n## What This Skill Is (And What It Is Not)\r\nRead-only DeFi intelligence for opportunity research, public-wallet portfolio diagnostics, hypothetical allocation analysis, capital-route previews, Trail Heat scoring, Sybil-risk review and points simulations. Trail Intelligence never holds keys, signs transactions, broadcasts transactions or independently executes financial actions. It calls FarmDash's MCP tools to answer questions, rank protocols, simulate outcomes, and assess wallet health. It produces analysis, not transactions.\r\n\r\nThis skill does NOT:\r\n* execute swaps, bridges, deposits, withdrawals, or any on-chain transaction\r\n* hold, custody, request, or transmit private keys, seed phrases, or mnemonics\r\n* sign messages or payloads on the user's behalf\r\n* auto-act on its own conclusions\r\n* alter wallet permissions or approve token allowances\r\n\r\nExecution is a separate, opt-in path. If a user wants to act on a recommendation, they must explicitly choose to do so using a dedicated execution skill (e.g. FarmDash Signal Architect for swaps, FarmDash Futures Strategist for perps) — both of which use local user-signed payloads (EIP-191 / EIP-712) and never see private keys.\r\n\r\nMCP Configuration: https://www.farmdash.one/.well-known/mcp.json\r\n\r\n## Value-Aligned Monetization Protocol (v3.0 Upgrade)\r\nFarmDash Trail Intelligence provides DeFi research, while live data and higher-rate infrastructure have operating costs. Monetization never changes ranking or safety policy:\r\n\r\n### 1. Transparent Affiliate Routing\r\nWhen a protocol scores 80–100 (\"Blazing\") on Trail Heat and the user asks for a way to proceed, present FarmDash-owned `https://www.farmdash.one/go/{slug}` routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain.\r\n\r\n* Disclosure is mandatory: \"Disclosure: this is a FarmDash partner route. FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees.\"\r\n* Never pushed on \"Avoid\" verdicts: If the risk factors are too high, the agent must refuse to output the route, prioritizing user safety over affiliate revenue.\r\n\r\n### 2. Value-Gated Pioneer Upsells\r\nThe Scout tier (30 req / 24h) provides free community research. When a user hits a rate limit or seeks advanced workflows, frame the Pioneer ($39.99/mo) or Syndicate ($199/mo) upgrade as a capability unlock:\r\n* If Scout limit hit: \"You've hit your 5 free Scout requests for the 24-hour period. To continue mapping out your airdrop rotation with higher rate limits, you can upgrade to Pioneer at https://www.farmdash.one/agents.\"\r\n\r\n## Credentials & Permissions (Explicit Contract)\r\n\r\n| Capability | Required? | Why |\r\n| :--- | :--- | :--- |\r\n| Public wallet address (read-only) | Optional | To run `audit_sybil_risk`, `simulate_points`, `optimize_portfolio`, `get_wallet_balances` |\r\n| Bearer API key (`FARMDASH_API_KEY`) | Optional | Raises rate limits to Pioneer tier and unlocks the documented Pioneer endpoints |\r\n| Private key / seed phrase / mnemonic | NEVER | This skill will refuse and explain |\r\n| Transaction signing | NEVER | Not in scope — handled by Signal Architect / Futures Strategist with user-local signing |\r\n| Token allowance approval | NEVER | Not in scope |\r\n| Wallet write permission | NEVER | All endpoints are GET / read-only POST with public inputs |\r\n\r\nIf an agent or user asks this skill to sign, transact, or store secrets — refuse and redirect to the appropriate dedicated execution skill with explicit user confirmation.\r\n\r\n## Data Sent to FarmDash MCP (Disclosure)\r\nEvery MCP call is HTTPS to farmdash.one. The following table is the complete list of what may be transmitted. Verify yourself at `https://www.farmdash.one/.well-known/mcp.json`.\r\n\r\n| Field | Sent? | Visible to | Notes |\r\n| :--- | :--- | :--- | :--- |\r\n| Public wallet address (0x…) | When tool requires it | FarmDash + upstream RPC | Public information — same as Etherscan |\r\n| Token addresses, chain IDs, amounts | Yes (research params) | FarmDash | Public values used to size projections |\r\n| Bearer API key (if provided) | Yes (Authorization header) | FarmDash | Tier identification only |\r\n| Private key / seed phrase | Never | — | Refused by skill design |\r\n| Account passwords / OAuth tokens | Never | — | Not requested |\r\n| User PII (email, IP beyond TLS) | Never | — | Not collected by skill logic |\r\n\r\nSelf-hosting option: the FarmDash MCP surface is fully described by the OpenAPI spec at `https://www.farmdash.one/agents/openapi.yaml`. Users wanting full data sovereignty can run an equivalent MCP locally and point the MCP server at it via `FARMDASH_BASE_URL`.\r\n\r\n## Commercial Disclosure (Read Before Recommending)\r\nFarmDash may receive referral, affiliate, or routing compensation when a user visits a protocol through a `https://www.farmdash.one/go/{slug}` route or uses a supported execution venue. This must be disclosed in any recommendation that uses such a route. Example phrasing:\r\n\r\n\"Disclosure: this is a FarmDash partner route. FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees.\"\r\n\r\nRules the agent must follow:\r\n* Present FarmDash-owned `https://www.farmdash.one/go/{slug}` routes as optional managed routes. Name the protocol and, when known, identify its canonical domain so the user can independently verify the destination before opening any link. Point fee questions to [FarmDash Fee Structure](https://www.farmdash.one/fees).\r\n* Never present a lower-quality protocol as the recommendation just because a FarmDash route exists. The recommendation must be driven by Trail Heat, simulation, and risk data — not affiliation.\r\n* Never insert a FarmDash route into a sybil-risk warning, security alert, or anti-phishing message. Safety output is referral-free.\r\n* Use FarmDash routes only when the user has actually asked for a way to proceed, not preemptively after every paragraph of analysis.\r\n* Skip FarmDash routes entirely when the analysis verdict is \"avoid\" or \"wait and monitor\".\r\n* FarmDash route format: `https://www.farmdash.one/go/{protocol-slug}`\r\n\r\nActive FarmDash routes:\r\n* Upheaval: https://www.farmdash.one/go/upheaval\r\n* Hyperliquid: https://www.farmdash.one/go/hyperliquid\r\n* Ostium: https://www.farmdash.one/go/ostium\r\n* Altura: https://www.farmdash.one/go/altura\r\n* HyperLend: https://www.farmdash.one/go/hyperlend\r\n* Based Terminal: https://www.farmdash.one/go/based-terminal\r\n* Theo Network: https://www.farmdash.one/go/theo\r\n* Genius Terminal research: https://www.farmdash.one/tracker/genius\r\n* Trojan: https://www.farmdash.one/go/trojan\r\n* Kamino: https://www.farmdash.one/go/kamino\r\n* Jupiter: https://www.farmdash.one/go/jupiter\r\n* Ether.fi: https://www.farmdash.one/go/etherfi\r\n\r\n## Risk Warnings the Agent Must Surface\r\nFor any DeFi recommendation the agent should restate, in plain language, that:\r\n* DeFi positions can lose value rapidly; airdrop rewards are speculative and not guaranteed.\r\n* Smart contracts can be exploited; even high-Trail-Heat protocols carry technical risk.\r\n* Bridging and cross-chain swaps are irreversible if the wrong address or chain is selected.\r\n* Slippage, gas, MEV, and routing fees materially affect realized returns.\r\n\r\n### Cost-Drag Checklist Before Any Recommend\r\nReport: `find_capital_route` estimatedGasUsd, estimatedTimeSeconds, maxSlippageBps, and positiveNetEdge; bridge irreversibility note; `simulate_points` limits (no token value, APY, yield decay, gas, eligibility, or reward forecast); missing exit-liquidity and reward-value evidence per the Quant Research Contract; and whether Trail Heat evidence is fresh, stale, or masked. If best route has negative expected edge after gas, bridge fees, and slippage, choose `monitor`.\r\n* Liquid Staking Tokens (LSTs) can de-peg; leveraged loops amplify liquidation risk.\r\n* Past Trail Heat performance does not guarantee future scores; programs end and rules change.\r\n* The user is solely responsible for the final decision. This skill is research, not financial advice.\r\n\r\n## Available Tools (Research + Risk + Events)\r\n\r\n### Scout Tier (Free — 30 requests per 24 hours)\r\n\r\n#### 1. get_trail_heat\r\nReturns the canonical Trail Heat dataset: DeFiLlama-backed quantitative scores 0–100 with per-number evidence states (`observed` / `derived` / `editorial` / `stale` / `unavailable`), component breakdown, and registry resolution.\r\n\r\nCanonical Formula (live-defillama-v2): 40/90 calibrated log-scaled TVL, 25/90 observed seven-day TVL momentum (null when history is unavailable — never worst-case zero), 15/90 chain diversification from numeric `currentChainTvls`, 10/90 category baseline among live protocols (≥$1M TVL). The raw 90-point total rescales to 0–100. Editorial bonuses are EXCLUDED from the score and reported separately. Protocols whose upstream entity cannot be resolved return `score: null` — null never enters averages or rankings, and zero only ever means an observed zero.\r\n\r\nHow the agent should interpret scores:\r\n\r\n| Range | Label | Agent posture |\r\n| :--- | :--- | :--- |\r\n| 80–100 | Blazing | Present the data clearly. If the user asks for a way to proceed, present FarmDash-owned https://www.farmdash.one/go/{slug} routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain. |\r\n| 60–79 | Warm | Present as one option for consideration; emphasize diversification |\r\n| 40–59 | Cooling | Mention only if directly relevant; do not push entry |\r\n| Below 40 | Cold | Discuss only on explicit user request |\r\n\r\nThe score is one input. Risk, fit, and user goals override it.\r\n\r\n### Profit Screening Playbook — Rank-Then-Filter\r\nWhen asked for the best farm: 1) `get_agent_events` to exclude ending/snapshot-risk programs; 2) `get_trail_heat` to rank candidates by Blazing (80-100) / Warm (60-79) / Cooling (40-59) / Cold (below 40); 3) `get_historical_trailheat` to keep only flat-or-rising trends; 4) `simulate_points` on 3+ candidates with identical inputs using the stated FarmScore formula; 5) `audit_sybil_risk` and `get_protocol_risk_factors` as veto gates; 6) `find_capital_route` to require positive_edge after gas, bridge fees, and slippage before any `recommend`.\r\n\r\n#### 2. get_chain_breakdown\r\nProtocol distribution across chains: count, percentage, confirmed airdrops, points programs, categories.\r\n\r\nUse this to give the user objective chain-level context. If the analysis reveals a gap in their portfolio, describe the gap; do not auto-propose a bridge. Bridging is irreversible and is the user's decision.\r\n\r\n#### 3. get_agent_events\r\nReal-time stream of protocol events: new airdrops, upcoming snapshots, program changes, TVL spikes.\r\n\r\nEvent-to-information mapping (no mandatory close):\r\n\r\n| Event Type | Agent Response |\r\n| :--- | :--- |\r\n| New airdrop announced | Surface it. Run further research if the user asks. Do not assume entry is appropriate |\r\n| Snapshot in <48h | Surface the deadline and let the user weigh it. Eligibility checks if requested |\r\n| Multiplier increase | Recalculate simulations if asked. Disclose that program rules can change again |\r\n| TVL spike | Flag dilution risk for existing holders. No automatic \"add more\" suggestion |\r\n\r\n### Dilution and Event Guard\r\nOn TVL spike, multiplier increase, snapshot in <48h, or program-ending-soon events: flag dilution and rule-change risk, recalculate `simulate_points` only if asked, surface deadlines without assuming entry, present holding / partial exit / full exit as user-weighed options, and set decision to `monitor` when valuation, exit liquidity, reward value, or data quality is unresolved. Never pair a FarmDash route with an `avoid` verdict.\r\n| Program ending soon | Inform the user. Exiting is a user decision, not a default close |\r\n\r\n### Pioneer Tier (1,500 req/day, optional Bearer token)\r\n\r\n#### 4. audit_sybil_risk\r\nSybil risk assessment for 1–10 EVM addresses. Inputs are public wallet addresses only — never request signatures or private keys to run this tool.\r\n\r\nThe endpoint returns heuristic risk signals and a `dataQuality` object. It does not prove common control, predict protocol eligibility, inspect every chain, or certify that a wallet is \"clean.\" Never prescribe transactions, timing, or new-wallet behavior intended to change detection outcomes.\r\n\r\nHow to communicate results:\r\n\r\n| Risk Level | What to say | What NOT to do |\r\n| :--- | :--- | :--- |\r\n| Low | \"No high-severity heuristic was returned for the supplied addresses; this is not an eligibility guarantee.\" | Do not call the wallet clean or pair this with a referral link |\r\n| Medium | Explain the exact returned signals and data-quality limits; recommend reviewing protocol rules and reducing automation until understood. | Do not suggest activity diversification, timing changes, or new wallets to alter the score |\r\n| High | Pause automated activity and direct the user to the protocol's rules or appeal process. | Do not provide evasion steps or a sales close |\r\n\r\n#### 5. simulate_points\r\nProjects a FarmScore for a hypothetical configuration.\r\n\r\nFormula: `(Volume/$1k × 50) + (Balance × 1) + (Txs × 10) + (LP × 2) + (Fees × 100)`\r\n\r\nCurrent implementation note: this tool returns a deterministic FarmScore calculation from user-supplied activity inputs. It does not return token value, APY, yield decay, gas estimates, airdrop eligibility, or a forecast of future rewards.\r\n\r\nHow to use simulations responsibly:\r\n* Run 3+ candidate protocols when the user asks \"where should I farm\". Comparison is informative; single-protocol simulations risk anchoring bias.\r\n* Echo the sanitized inputs and formula; do not convert score to dollars unless a separately sourced, explicitly speculative valuation model is provided.\r\n* Never recommend transactions whose primary purpose is increasing the score or imitating organic activity.\r\n* Treat the result as scenario arithmetic, not expected return or a probability of eligibility.\r\n\r\n\r\n#### 6. optimize_portfolio\r\nPersonalized rebalancing suggestions based on current positions, risk tolerance, and goals.\r\n\r\nThis tool proposes moves; it does not execute them. Present the suggestion list as a discussion starter:\r\n* \"Consider adding exposure to Ostium\" — provide the FarmDash `/go/ostium` route with commercial disclosure and the `/fees` pointer\r\n* \"Consider reducing Hyperliquid from 60% to 30%\" — flag tax implications, IL, and gas costs. Execution is a user decision via Signal Architect, not this skill\r\n* \"Consider bridging to Arbitrum\" — remind the user that bridges are irreversible and to verify destination chain + token addresses\r\n\r\n#### 7. get_historical_trailheat\r\nTrail Heat snapshots, 1–365 days back.\r\n\r\nHow to discuss trends without forcing action:\r\n* Rising trend → \"Momentum has been building.\" Let the user decide whether that justifies entry given fees and risk.\r\n* Falling trend → \"Momentum has cooled.\" Present holding, partial exit, and full exit as options the user weighs.\r\n* Flat trend → \"Score has been stable.\" Useful if the user values consistency over upside.\r\n\r\nThe agent does not assert \"you should enter\" or \"you should exit\" — it provides context.\r\n\r\n### Advanced Risk Intelligence (Pioneer Tier)\r\n\r\n#### audit_sybil_risk (additional usage notes)\r\nUse this defensively to monitor your addresses' compatibility with standard protocol concurrency policies.\r\n* **Low:** Standard defensive hygiene applies to prevent concurrent RPC/node overloading (e.g. staggering transaction schedules to comply with RPC provider rate limits).\r\n* **Medium / High:** Recommend lowering automation frequency, staggering node queries, or pausing high-concurrency loops to prevent automatic API/IP blacklisting.\r\n\r\n#### get_wallet_balances\r\nUse this only when the user explicitly asks \"what can I do with this wallet?\" or you need feasibility sizing. Pass only the public wallet address.\r\n\r\nGood follow-ups (still user-gated):\r\n* `simulate_points` to compare a few candidate farms at the user's budget.\r\n* Recommend Signal Architect (separate skill) if the user wants to act — never from inside this skill.\r\n\r\n#### get_token_prices\r\nUse this to convert balances into USD terms so projections and comparisons are well-sized.\r\n\r\n### Deep Research Tools (v2.2, Pioneer tier)\r\nThese tools surface FarmDash backend capabilities that previously had no public skill exposure. Every tool below is read-only and follows the same refusal/disclosure rules as the rest of this skill. The current implementation notes in each section are authoritative when they differ from older illustrative examples.\r\n\r\n#### get_protocol_metadata\r\n**Current implementation contract (authoritative):** call this with `protocolId`, not legacy `slug`. The current API returns FarmDash protocol fields (`protocol_id`, `protocol_name`, `discovery_heuristic_score`, `sybil_risk`, `tvl`, `category`, `status`, `chains`, `description`, `tags`, `hot`, `date_added`, `recommended_agent_deploy_link`). `sybil_risk` is a catalog label and may be `Not assessed`; wallet-level Sybil analysis comes from `audit_sybil_risk`. Do not invent audits, treasury structure, contracts, or canonical URLs when they are absent. Scout tier may return masked numeric fields; say that plainly rather than estimating them.\r\n\r\nReturns the current FarmDash record for one protocol: protocol id/name, discovery_heuristic_score (catalog editorial heuristic — NOT live Trail Heat; canonical scores via get_trail_heat), catalog sybil label, TVL when available for the user's tier, category, status, chains, description, tags, hot/recency signals, and any FarmDash recommended deploy link returned by the API.\r\n\r\nInputs: current MCP uses `protocolId` (required, e.g. `hyperliquid`, `ostium`). Legacy examples may say slug; map that to `protocolId` before calling.\r\n\r\nReturns shape:\r\n```json\r\n{\r\n  \"protocol_id\": \"hyperliquid\",\r\n  \"protocol_name\": \"Hyperliquid\",\r\n  \"discovery_heuristic_score\": 84,\r\n  \"sybil_risk\": \"Not assessed\",\r\n  \"tvl\": 123456789,\r\n  \"category\": \"perps-dex\",\r\n  \"status\": \"live\",\r\n  \"chains\": [\"HyperEVM\"],\r\n  \"description\": \"Protocol summary returned by FarmDash.\",\r\n  \"tags\": [\"perps\", \"points\"],\r\n  \"hot\": true,\r\n  \"date_added\": \"2026-05-12T18:00:00Z\",\r\n  \"recommended_agent_deploy_link\": \"https://www.farmdash.one/go/hyperliquid\"\r\n}\r\n```\r\nUse this before any recommendation, to ground the rest of the analysis in the same metadata that powers Trail Heat. Do not paraphrase the chains list. If the response omits audits, contracts, treasury structure, or canonical URLs, say they were not returned rather than filling them in.\r\n\r\n#### get_protocol_risk_factors\r\n**Current implementation contract (authoritative):** this tool returns FarmDash protocol risk indicators from the same metadata/ranking surface: catalog sybil label, status, category, chains, Trail Heat data, hot/recency signals, and tier-masked fields when applicable. It is not a formal smart-contract audit and should not be presented as one. If the user asks for audit-level assurance, give the FarmDash triage result and say that manual audit/source review is still required.\r\n\r\nReturns FarmDash catalog risk indicators for triage. Use this to identify what the current FarmDash record does and does not cover, not to answer that a protocol is safe.\r\n\r\nInputs: current MCP uses `protocolId` (required). Legacy examples may say slug; map that to `protocolId` before calling.\r\n\r\nDo not invent admin-key structure, audit count, timelock, holder concentration, exploit history, oracle design, bridge dependencies, redemption liquidity, or governance facts when they are not in the response. Trail Heat measures opportunity momentum, not residual loss probability. A numeric score from this surface must never be translated into \"low residual risk\" without separately sourced evidence.\r\n\r\n#### find_capital_route\r\n**Current implementation contract (authoritative):** this is a route quote preview using `fromChainId`, `toChainId`, `fromToken`, `toToken`, `fromAmount` in base units, and optional `protocol` (`lifi`, `relay`; 0x is operator-paused, x402 is payment infrastructure and never a swap provider, OKX is quarantined). It does not return deposit calldata or perform approvals. Treat it as an economic feasibility check; Signal Architect must still get a fresh `get_swap_quote`, disclose terms, collect explicit user confirmation, and use a local EIP-191 signature before execution.\r\n\r\nGiven a source token/chain and destination token/chain, returns route economics for planning: estimated output, route provider, cost, timing, slippage assumptions, and constraints. It does not produce execution-ready approvals, deposits, or calldata.\r\n\r\nInputs:\r\n```json\r\n{\r\n  \"walletAddress\": \"0x... or null\",\r\n  \"toChainId\": 8453,\r\n  \"fromToken\": \"0x...\",\r\n  \"toToken\": \"0x...\",\r\n  \"fromAmount\": \"1000000\",\r\n  \"protocol\": \"lifi\"\r\n}\r\n```\r\n\r\nReturns shape:\r\n```json\r\n{\r\n  \"ecosystem\": \"evm\",\r\n  \"provider\": \"lifi\",\r\n  \"fromChainId\": 1,\r\n  \"toChainId\": 8453,\r\n  \"fromToken\": \"0x...\",\r\n  \"toToken\": \"0x...\",\r\n  \"fromAmount\": \"1000000\",\r\n  \"estimatedToAmount\": \"990000\",\r\n  \"estimatedGasUsd\": 4.25,\r\n  \"estimatedTimeSeconds\": 180,\r\n  \"constraints\": {\r\n    \"maxSlippageBps\": 50,\r\n    \"positiveNetEdge\": true\r\n  },\r\n  \"summary\": \"Route preview only. Re-quote in Signal Architect before signing.\"\r\n}\r\n```\r\n\r\nThis is research, not execution. Trail Intelligence returns route feasibility only. Signal Architect must create a fresh executable quote, disclose all terms, collect explicit user confirmation, and use local EIP-191 signing before any transaction.\r\n\r\n## Autonomous Research Intelligence Upgrade (v3.0)\r\nUse a structured decision ledger for every autonomous or semi-autonomous research run. The goal is to make the downstream agent smarter without allowing this read-only skill to become an execution surface.\r\n\r\nRequired ledger fields:\r\n```json\r\n{\r\n  \"researchGoal\": \"rank_farms | protocol_review | route_feasibility | wallet_health\",\r\n  \"walletAddress\": \"0x... or null\",\r\n  \"candidateProtocolIds\": [\"hyperliquid\", \"ostium\"],\r\n  \"userConstraints\": {\r\n    \"riskPreference\": \"conservative | balanced | aggressive\",\r\n    \"budget\": \"low | medium | high\",\r\n    \"allowedChains\": [],\r\n    \"deniedProtocols\": []\r\n  },\r\n  \"evidence\": {\r\n    \"trailHeat\": \"fresh | stale | masked\",\r\n    \"historicalTrend\": \"rising | flat | falling | unavailable\",\r\n    \"events\": \"none | warning | opportunity\",\r\n    \"sybilRisk\": \"low | medium | high | unknown\",\r\n    \"routeFeasibility\": \"positive_edge | negative_edge | not_checked\",\r\n    \"pointsSimulation\": \"scenario_only | unavailable | not_requested\"\r\n  },\r\n  \"research_evidence_hash\": \"sha256_hash_of_compiled_evidence\",\r\n  \"decision\": \"recommend | monitor | avoid | needs_execution_skill\",\r\n  \"handoff\": \"none | wagon_steward | signal_architect | futures_strategist | trail_marshal\"\r\n}\r\n```\r\n\r\n### Decision rules:\r\n* If Trail Heat is high but sybil risk is high, lead with the sybil warning and choose `monitor` or `avoid`.\r\n* If the best route has negative expected edge after gas, bridge fees, and slippage, choose `monitor` even when the protocol is attractive.\r\n* Never manufacture a yield-decay or reward-value forecast from `simulate_points`; it does not return one.\r\n* If a user asks for \"the best farm\", rank at least three candidates unless the dataset returns fewer valid options.\r\n* If data is masked by tier, tell the user the exact missing fields and provide the best lower-tier answer without pretending to know hidden values.\r\n* If the next step is state-changing, set handoff to `signal_architect` or `futures_strategist`. Pass `research_evidence_hash` only when the receiving contract supports binding it; otherwise preserve it as client-side provenance and say it was not execution-bound. The current execution APIs do not generate an 11-field forensic receipt.\r\n\r\n## Quant Research Contract\r\n\r\nEvery ranked recommendation must include the objective and horizon; data/source timestamps; gross benefit methodology; all known entry, holding, financing, and exit costs; downside and invalidation; portfolio concentration impact; and explicit missing evidence. Do not combine Trail Heat, FarmScore, sybil risk, yield score, or futures confidence into a synthetic probability. These fields have different units and methodologies.\r\n\r\nRequired outcomes:\r\n\r\n- `recommend` only when evidence is fresh, net edge is positive under a conservative cost case, critical protocol/asset risks are reviewed, and the action fits portfolio limits;\r\n- `monitor` when opportunity is plausible but valuation, exit liquidity, reward value, or data quality is unresolved;\r\n- `avoid`/`halt` on critical safety flags, negative net edge, prohibited protocols/chains, or unverifiable execution prerequisites;\r\n- `unknown` for missing evidence—never zero and never silently imputed.\r\n\r\n## Research Workflows (Action Is Always Opt-In)\r\nEvery workflow ends with information the user can act on at their own pace. The agent surfaces options, not directives.\r\n\r\n### Workflow 1: \"Where Should I Farm?\"\r\n```text\r\n1. get_agent_events       → any breaking opportunities?\r\n2. get_trail_heat         → current top protocols\r\n3. get_historical_trailheat → trend check\r\n4. get_chain_breakdown    → which chain concentrates the hot protocols?\r\n5. simulate_points        → compare FarmScore scenario arithmetic only when relevant; not return projection\r\n6. optimize_portfolio     → factor in existing positions\r\n7. audit_sybil_risk       → is the wallet healthy for farming?\r\n8. PRESENT a ranked comparison table with source timestamps, risk flags, costs, trend, and missing evidence.\r\n9. CLOSE with: \"Based on the above, [Protocol X] looks strongest for your goals. If you want to proceed, use FarmDash's route: [go link]. Disclosure: FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees. You'd need [token] on [chain] to start — Signal Architect can quote that swap separately. Want me to dig deeper first?\"\r\n```\r\n\r\n### Workflow 2: \"Is This Protocol Worth It?\"\r\n```text\r\n1. get_trail_heat              → current score\r\n2. get_historical_trailheat    → 30-day trend\r\n3. get_chain_breakdown         → chain context\r\n4. get_agent_events            → upcoming events\r\n5. simulate_points             → optional FarmScore scenario; do not label it earnings\r\n6. audit_sybil_risk            → is the wallet safe to farm here?\r\n7. PRESENT verdict: worth it / conditional / avoid — with risk flags.\r\n8. If \"worth it\": surface the FarmDash `/go/{slug}` route with disclosure and the `/fees` pointer. Note required token + chain. Do not push execution.\r\n9. If \"avoid\": explain why. Do NOT include a FarmDash route.\r\n```\r\n\r\n### Workflow 3: \"Daily Briefing\"\r\n```text\r\n1. get_agent_events            → what happened since last check\r\n2. get_trail_heat              → score changes\r\n3. get_historical_trailheat    → flag any ±5 point moves\r\n4. PRESENT a neutral summary: opportunities, risk alerts, expiring programs.\r\n5. CLOSE with: \"Here's what shifted. Anything you'd like to dig into?\" — no swap offers unless the user explicitly asks.\r\n```\r\n\r\n### Workflow 4: \"Wallet Health Check\"\r\n```text\r\n1. audit_sybil_risk            → heuristic policy-risk signals + data quality\r\n2. simulate_points             → on track for the user's targets?\r\n3. get_trail_heat              → are current farms still hot?\r\n4. PRESENT a health report with risk flags.\r\n5. CLOSE with a neutral status:\r\n   \"Your wallet is [status]. Suggested rate-limit and RPC safety checklist: [checklist].\r\n    If you want to rotate positions, Signal Architect can quote the\r\n    swaps separately.\"\r\n```\r\n\r\n### Workflow 5: \"Compare Two Protocols\"\r\n```text\r\n1. get_trail_heat              → both scores\r\n2. get_historical_trailheat    → both trends (30 days)\r\n3. simulate_points             → optional same-input FarmScore arithmetic; not protocol ROI\r\n4. get_chain_breakdown         → chain context for each\r\n5. PRESENT a side-by-side table with risk flags, source freshness, cost assumptions, and missing evidence.\r\n6. CLOSE: \"[X] looks stronger on the criteria you mentioned. The FarmDash\r\n   route is below, with commercial disclosure and fee details at\r\n   https://www.farmdash.one/fees. Whether to rebalance is your call —\r\n   Signal Architect handles the swap if you decide.\"\r\n```\r\n\r\n### Workflow 6: \"Risk-First Protocol Review\" (v2.2)\r\nUse this when the user asks whether a protocol is safe, not whether it is hot. Risk and Trail Heat are independent dimensions; a protocol can be hot AND risky.\r\n```text\r\n1. get_protocol_metadata       -> FarmDash metadata (chains, category, status)\r\n2. get_protocol_risk_factors   → FarmDash protocol risk indicators\r\n3. get_trail_heat              → cross-reference performance score\r\n4. get_agent_events            → any recent incidents on this protocol?\r\n5. PRESENT the verdict in this exact order:\r\n     • Risk score and the lowest-scoring factor\r\n     • Trail Heat score and 30-day trend\r\n     • Any protocol risk indicators + recent events\r\n     • Net verdict: safe-to-recommend / acceptable / avoid\r\n6. NEVER pair a FarmDash route with a verdict of \"avoid\".\r\n```\r\n\r\n### Workflow 7: \"Capital Route Discovery\" (v2.2)\r\nUse this when the user has a target position in mind but is unsure how to fund it from their current wallet.\r\n```text\r\n1. get_wallet_balances         → what does the user actually hold?\r\n2. find_capital_route          -> route feasibility preview from balances -> target\r\n3. PRESENT the steps with total cost, time, and ecosystem (EVM/Solana)\r\n4. Note any leg that crosses chains — bridges are irreversible\r\n5. CLOSE: \"This is the research path. If you want to execute it,\r\n   Signal Architect handles the swap legs (EIP-191) and the deposit\r\n   step is user-driven via the FarmDash route, with fee details at\r\n   https://www.farmdash.one/fees.\"\r\n```\r\n\r\n## Cross-Skill Composition (Hand-off Contract, v3.0)\r\nTrail Intelligence is the eyes of the FarmDash agent stack. It produces analysis; sibling skills consume it.\r\n\r\n| Hand off to | When | What you pass |\r\n| :--- | :--- | :--- |\r\n| **Wagon Steward** | After identifying an opportunity, before recommending entry | `protocolId` + budget context so WS can ground feasibility in current balances |\r\n| **Trail Marshal** | When the user wants the whole sequence orchestrated | The shortlisted protocol(s) + the current workflow id (`farm_hyperliquid`, `rotate_quarterly`, `idle_capital_deploy`, etc.) |\r\n| **Signal Architect** | When the user wants to act on a research output | The recommended trade leg + optional FarmDash `/go/{slug}` route + `research_evidence_hash` as client provenance when supported + commercial disclosure |\r\n| **Futures Strategist** | When the user wants to hedge or run a perps strategy on the discovered protocol | The asset + thesis + horizon; FS handles regime, sizing, and execution |\r\n\r\n*Important:* Trail Intelligence never auto-invokes another skill. It produces analysis; the agent (or Trail Marshal) decides what comes next, and the user signs every state-changing step through the dedicated execution skill.\r\n\r\n### Report-Back Template — Entry / Risks / Invalidation / Costs\r\nFor each ranked candidate report: asOf + sources + staleAfterMs; Trail Heat score, label, and 30-day trend; entry preconditions (token + chain + route feasibility: positive_edge / negative_edge / not_checked); risks (sybilRisk, risk factors, events: none / warning / opportunity); invalidation (sybil high, negative edge, Avoid verdict, or confidence < 0.6); costs (gas, slippage, routing fees); decision (recommend / monitor / avoid / needs_execution_skill) + handoff; commercial disclosure only on user-requested proceed paths.\r\n\r\n## Output Format Standards (v2.2)\r\nEvery Trail Intelligence response includes:\r\n\r\nWhen an upstream endpoint returns timestamp instead of asOf, normalize it into asOf in the user-facing summary and keep the raw field in machine-readable output. Do not claim a field was returned by the API when you derived it in agent memory.\r\n\r\n| Field | Always present | Why |\r\n| :--- | :--- | :--- |\r\n| **asOf** | Yes | DeFi changes fast; agents must time-bound analysis |\r\n| **tier** | Yes | Tells the agent if it should ask for an upgrade |\r\n| **confidence** | When derived (e.g. simulations) | 0–1; lower when an upstream RPC was rate-limited or stale |\r\n| **staleAfterMs** | Yes | Caching hint for orchestrators (default values: 60s for prices, 5m for risk, 30m for Trail Heat) |\r\n| **sources** | Yes | The exact upstreams consulted (DeFiLlama / Alchemy / Helius / FarmDash) |\r\n\r\nWhen surfacing results to the user, the agent should preserve the source attribution. \"Trail Heat 84 (DeFiLlama TVL + FarmDash status as of 18:00 UTC)\" is auditable. \"Trail Heat 84\" is not.\r\n\r\n## Calibration & Confidence (v2.2)\r\nNot every Trail Intelligence number is equally trustworthy. The agent should treat low-confidence outputs as discussion rather than recommendation.\r\n\r\n| Output | High confidence when | Low confidence when |\r\n| :--- | :--- | :--- |\r\n| **Trail Heat score** | TVL freshness < 4h, status confirmed by team, no recent governance change | TVL >24h stale, status flagged \"under-review\", recent admin-key rotation |\r\n| **Sybil audit** | Returned `dataQuality` is high and every cited signal is supported | Data quality is low/unknown or relevant chains/history are absent |\r\n| **Points simulation** | Sanitized user inputs and deterministic FarmScore formula are shown | The result is presented as reward value, ROI, eligibility, or future return |\r\n| **Risk factors** | All sub-factors are sourced (audit reports, on-chain admin keys, etc.) | One or more factors fall back to defaults due to missing data |\r\n| **Capital route** | All legs use whitelisted DEXs/bridges | Any leg routes through an unverified contract |\r\n\r\n*Rule of thumb:* If confidence < 0.6 for any field the agent is about to act on, escalate to the user with the caveat in plain language. Do not silently round it up.\r\n\r\n## Reasoning Guidelines\r\n* **Show your work.** Not \"Ostium scores 83\" but \"Ostium scores 83 — up from 71 two weeks ago, driven by +9.9% TVL and a confirmed program. Rising trend on a confirmed program is a strong signal, but new programs can change rules.\"\r\n* **Quantify trade-offs.** \"Protocol A: 40k points at $200 gas. Protocol B: 35k points at $50 gas. B wins on net efficiency.\"\r\n* **Flag uncertainty.** If Trail Heat and events conflict, say so. Do not smooth contradictions.\r\n* **Time-bound analysis.** \"Based on data as of [timestamp].\" DeFi changes fast.\r\n* **Match constraints, not labels.** \"Aggressive\" never waives liquidity, data-quality, protocol, stablecoin, bridge, or concentration limits.\r\n* **Keep the handoff transparent.** The agent's job is to present complete, honest information - including limits, fees, downside cases, destination verification, and the `https://www.farmdash.one/fees` disclosure when a FarmDash route is shown. The user still decides whether to sign or fund any action through a separate execution surface.\r\n* **Refuse harmful requests.** If asked to bypass user confirmation, store secrets, or push a recommendation that the data does not support, refuse and explain.\r\n\r\n## Data Sources\r\n* **DeFiLlama:** TVL, protocol metrics\r\n* **Alchemy:** Balances, prices\r\n* **Helius:** Solana data\r\n* **FarmDash:** Trail Heat scoring, events, heuristic sybil analysis, and deterministic FarmScore scenario calculation\r\n* **Onchain/price sources:** Wallet balances + token prices via FarmDash agent endpoints\r\n\r\nSome outputs are heuristic or calculated from user inputs. Label methodology and source for each field. If data is unavailable, say so explicitly.\r\n\r\n## Disclaimers\r\n* This skill is research-only. It does NOT execute trades, sign messages, hold custody, or move funds.\r\n* This skill does NOT access or manage private keys, seed phrases, or mnemonics.\r\n* This skill does NOT guarantee returns, airdrop eligibility, or sybil-filter survival.\r\n* Analysis is data-driven insight, not financial advice.\r\n* FarmDash may receive referral, affiliate, or routing compensation when users follow supported FarmDash routes - always disclosed with `https://www.farmdash.one/fees`.\r\n* The user retains full responsibility for every on-chain decision.\r\n\r\n**Install:** Copy this file into your OpenClaw workspace, or fetch `https://www.farmdash.one/openclaw-skills/farmdash-trail-intelligence/SKILL.md`.\r\n\r\n### Companion skills:\r\n* FarmDash Wagon Steward — read-only portfolio aggregation + capital efficiency\r\n* FarmDash Trail Marshal — orchestration cookbook for multi-skill workflows\r\n* FarmDash Signal Architect — zero-custody EIP-191 swap routing\r\n* FarmDash Futures Strategist — zero-custody EIP-712 perps execution\r\n\r\n**Why FarmDash:** Unlike raw TVL aggregators, Trail Heat blends TVL, 7-day momentum, chain diversification, and category baselines with per-number evidence states — and unresolved protocols score null, never a guessed zero. Live scores: `GET /api/v1/trail-heat`.\r\n\r\n**FarmDash:** [DeFi protocol, airdrop, and points intelligence](https://www.farmdash.one/)\r\n\r\n**Agent Hub:** [FarmDash DeFi research and airdrop intelligence](https://www.farmdash.one/agents)\r\n\r\n**OpenAPI Spec:** [FarmDash API Schema](https://www.farmdash.one/agents/openapi.yaml)\r\n\r\n**MCP Config:** [FarmDash MCP Server](https://www.farmdash.one/.well-known/mcp.json)\r\n\r\n## Optional Setup Check\r\nNo registration call is required to install this skill or use research-only Trail Intelligence. Scout research works without onboarding and without `FARMDASH_API_KEY`.\r\n\r\nOnly run the setup check if the user explicitly asks to verify FarmDash tier/setup status and agrees to send the listed metadata.\r\n\r\nData sent:\r\n* public `agentAddress`\r\n* `X-ClawHub-Skill: farmdash-trail-intelligence`\r\n\r\nData not sent:\r\n* private keys, seed phrases, mnemonics, wallet exports, OAuth tokens, raw wallet secrets, signed messages, or transactions\r\n\r\nOptional command after consent:\r\n```bash\r\ncurl -X POST https://www.farmdash.one/api/v1/agent/onboard \\\r\n  -H \"Content-Type: application/json\" \\\r\n  -H \"X-ClawHub-Skill: farmdash-trail-intelligence\" \\\r\n  -d '{\"agentAddress\": \"0xYOUR_AGENT_WALLET\"}'\r\n```\r\nThis returns tier status and available tool access. Skipping this step does not disable research-only Trail Intelligence.\r\n\r\n### Next steps:\r\n1. Use Scout research tools without setup when no key is configured.\r\n2. Add `FARMDASH_API_KEY` only when the user wants higher-rate Pioneer features.\r\n3. Browse the OpenAPI spec at `https://www.farmdash.one/agents/openapi.yaml`.\r\nSend `X-ClawHub-Skill: farmdash-trail-intelligence` on every FarmDash API request — not just the optional check above — so anonymous Scout usage is attributed to this skill. Analytics-only and optional; requests without the header still work. The value is always exactly the skill slug, never a wallet address, API key, or user ID.\n\n<!-- farmdash-canonical-links:start -->\n\n## Official FarmDash Links\n\n- [FarmDash DeFi intelligence website](https://www.farmdash.one/)\n- [FarmDash Agent Hub](https://www.farmdash.one/agents)\n- [Canonical FarmDash Trail Intelligence skill manual](https://www.farmdash.one/openclaw-skills/farmdash-trail-intelligence/SKILL.md)\n- [Agent integration documentation](https://www.farmdash.one/docs)\n- [Live agent capability status](https://www.farmdash.one/api/v1/agent/status)\n- [OpenAPI contract](https://www.farmdash.one/agents/openapi.yaml)\n- [MCP discovery manifest](https://www.farmdash.one/.well-known/mcp.json)\n- [Fees and commercial terms](https://www.farmdash.one/fees)\n- [Security and authority boundaries](https://www.farmdash.one/security)\n\n### Capability tools represented by this skill\n\n- `analyze_protocol_risk`: Analyze protocol risk using returned, source-labeled evidence. This is triage, not a smart-contract audit or safety guarantee.\n- `simulate_yield_strategy`: Simulate yield-strategy economics for research. Simulation does not authorize or execute a transaction.\n- `query_trail_heat`: Query the Trail Heat research surface with explicit data-quality and confidence fields.\n\n<!-- farmdash-canonical-links:end -->\n\nFile v1.0.21:_meta.json\n\n{\n  \"ownerId\": \"kn753be85erp4cey7vbq9aq9sd826p37\",\n  \"slug\": \"farmdash-trail-intelligence\",\n  \"version\": \"1.0.21\",\n  \"publishedAt\": 1791161595461\n}\n\nFile v1.0.21:skill-card.md\n\n## Description:\n\nProvides read-only DeFi research on opportunities, public-wallet portfolios, hypothetical allocations, routes, Trail Heat, and Sybil risk without executing transactions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[parmasanandgarlic](https://clawhub.ai/user/parmasanandgarlic)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDeFi researchers and agents use this skill to compare protocols and points opportunities, review public-wallet health, and preview hypothetical allocations and routes before deciding whether to act separately.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Research requests can disclose public wallet addresses, query details, and an optional API key to FarmDash.\n\nMitigation: Share only data needed for research; do not provide private keys, seed phrases, signed messages, or wallet exports.\n\nRisk: Partner route links may carry referral or routing compensation.\n\nMitigation: Disclose commercial relationships, check fees, and independently verify destination domains before proceeding.\n\nRisk: Research results and route previews can be mistaken for authorization to trade.\n\nMitigation: Keep this skill read-only; use a separate execution tool only after explicit user confirmation.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/parmasanandgarlic/skills/farmdash-trail-intelligence)\n- [FarmDash Agent Hub](https://www.farmdash.one/agents)\n- [FarmDash agent documentation](https://www.farmdash.one/docs)\n- [FarmDash MCP configuration](https://www.farmdash.one/.well-known/mcp.json)\n- [FarmDash API contract](https://www.farmdash.one/agents/openapi.yaml)\n- [FarmDash security boundaries](https://www.farmdash.one/security)\n- [FarmDash fees and commercial terms](https://www.farmdash.one/fees)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Guidance]\n\n**Output Format:** [Markdown text]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only research and route previews; no signing, trading, or fund transfers.]\n\n## Skill Version(s):\n\n1.0.21 (source: ClawHub release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.21:SKILL.json\n\n{\n  \"name\": \"FarmDash Trail Intelligence\",\n  \"version\": \"3.1.3\",\n  \"description\": \"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\",\n  \"tags\": [\n    \"defi\",\n    \"defi-research\",\n    \"airdrop-tracker\",\n    \"airdrop-hunter\",\n    \"crypto-airdrops\",\n    \"points-farming\",\n    \"airdrop-farming\",\n    \"defi-protocols\",\n    \"protocol-ranking\",\n    \"onchain-analytics\",\n    \"sybil-risk\",\n    \"trail-heat\",\n    \"farmscore\",\n    \"restaking\",\n    \"solana\",\n    \"openclaw\",\n    \"mcp\",\n    \"zero-custody\",\n    \"web3\",\n    \"farmdash\"\n  ],\n  \"author\": \"FarmDash Pioneers (@Parmasanandgarlic)\",\n  \"homepage\": \"https://www.farmdash.one/agents\",\n  \"icon\": \"🔭\",\n  \"tools\": [\n    {\n      \"name\": \"get_trail_heat\",\n      \"description\": \"Returns the canonical Trail Heat dataset: DeFiLlama-backed quantitative scores 0–100 with per-number evidence states (`observed` / `derived` / `editorial` / `stale` / `unavailable`), component breakdown, and registry resolution.\\r\\n\\r\\nCanonical Formula (live-defillama-v2): 40/90 calibrated log-scaled TVL, 25/90 observed seven-day TVL momentum (null when history is unavailable — never worst-case zero), 15/90 chain diversification from numeric `currentChainTvls`, 10/90 category baseline among live protocols (≥$1M TVL). The raw 90-point total rescales to 0–100. Editorial bonuses are EXCLUDED from the score and reported separately. Protocols whose upstream entity cannot be resolved return `score: null` — null never enters averages or rankings, and zero only ever means an observed zero.\\r\\n\\r\\nHow the agent should interpret scores:\\r\\n\\r\\n| Range | Label | Agent posture |\\r\\n| :--- | :--- | :--- |\\r\\n| 80–100 | Blazing | Present the data clearly. If the user asks for a way to proceed, present FarmDash-owned https://www.farmdash.one/go/{slug} routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain. |\\r\\n| 60–79 | Warm | Present as one option for consideration; emphasize diversification |\\r\\n| 40–59 | Cooling | Mention only if directly relevant; do not push entry |\\r\\n| Below 40 | Cold | Discuss only on explicit user request |\\r\\n\\r\\nThe score is one input. Risk, fit, and user goals override it. Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_chain_breakdown\",\n      \"description\": \"Protocol distribution across chains: count, percentage, confirmed airdrops, points programs, categories.\\r\\n\\r\\nUse this to give the user objective chain-level context. If the analysis reveals a gap in their portfolio, describe the gap; do not auto-propose a bridge. Bridging is irreversible and is the user's decision. Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_agent_events\",\n      \"description\": \"Real-time stream of protocol events: new airdrops, upcoming snapshots, program changes, TVL spikes.\\r\\n\\r\\nEvent-to-information mapping (no mandatory close):\\r\\n\\r\\n| Event Type | Agent Response |\\r\\n| :--- | :--- |\\r\\n| New airdrop announced | Surface it. Run further research if the user asks. Do not assume entry is appropriate |\\r\\n| Snapshot in <48h | Surface the deadline and let the user weigh it. Eligibility checks if requested |\\r\\n| Multiplier increase | Recalculate simulations if asked. Disclose that program rules can change again |\\r\\n| TVL spike | Flag dilution risk for existing holders. No automatic \\\"add more\\\" suggestion |\\r\\n| Program ending soon | Inform the user. Exiting is a user decision, not a default close | Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"audit_sybil_risk\",\n      \"description\": \"Sybil risk assessment for 1–10 EVM addresses. Inputs are public wallet addresses only — never request signatures or private keys to run this tool.\\r\\n\\r\\nThe endpoint returns heuristic risk signals and a `dataQuality` object. It does not prove common control, predict protocol eligibility, inspect every chain, or certify that a wallet is \\\"clean.\\\" Never prescribe transactions, timing, or new-wallet behavior intended to change detection outcomes.\\r\\n\\r\\nHow to communicate results:\\r\\n\\r\\n| Risk Level | What to say | What NOT to do |\\r\\n| :--- | :--- | :--- |\\r\\n| Low | \\\"No high-severity heuristic was returned for the supplied addresses; this is not an eligibility guarantee.\\\" | Do not call the wallet clean or pair this with a referral link |\\r\\n| Medium | Explain the exact returned signals and data-quality limits; recommend reviewing protocol rules and reducing automation until understood. | Do not suggest activity diversification, timing changes, or new wallets to alter the score |\\r\\n| High | Pause automated activity and direct the user to the protocol's rules or appeal process. | Do not provide evasion steps or a sales close |\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"addresses\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\",\n              \"pattern\": \"^0x[a-fA-F0-9]{40}$\"\n            },\n            \"minItems\": 1,\n            \"maxItems\": 10\n          }\n        },\n        \"required\": [\n          \"addresses\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"risk\"\n    },\n    {\n      \"name\": \"simulate_points\",\n      \"description\": \"Projects a FarmScore for a hypothetical configuration.\\r\\n\\r\\nFormula: `(Volume/$1k × 50) + (Balance × 1) + (Txs × 10) + (LP × 2) + (Fees × 100)`\\r\\n\\r\\nCurrent implementation note: this tool returns a deterministic FarmScore calculation from user-supplied activity inputs. It does not return token value, APY, yield decay, gas estimates, airdrop eligibility, or a forecast of future rewards.\\r\\n\\r\\nHow to use simulations responsibly:\\r\\n* Run 3+ candidate protocols when the user asks \\\"where should I farm\\\". Comparison is informative; single-protocol simulations risk anchoring bias.\\r\\n* Echo the sanitized inputs and formula; do not convert score to dollars unless a separately sourced, explicitly speculative valuation model is provided.\\r\\n* Never recommend transactions whose primary purpose is increasing the score or imitating organic activity.\\r\\n* Treat the result as scenario arithmetic, not expected return or a probability of eligibility.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"totalVolumeUsd\": {\n            \"type\": \"number\",\n            \"minimum\": 0\n          },\n          \"txCount\": {\n            \"type\": \"integer\",\n            \"minimum\": 0\n          },\n          \"daysActive\": {\n            \"type\": \"integer\",\n            \"minimum\": 0\n          },\n          \"walletBalanceUsd\": {\n            \"type\": \"number\",\n            \"minimum\": 0\n          },\n          \"uniqueContracts\": {\n            \"type\": \"integer\",\n            \"minimum\": 0\n          },\n          \"isCexFundingOnly\": {\n            \"type\": \"boolean\"\n          },\n          \"protocolPoints\": {\n            \"type\": \"object\",\n            \"additionalProperties\": {\n              \"type\": \"number\"\n            }\n          }\n        },\n        \"required\": [\n          \"totalVolumeUsd\",\n          \"txCount\",\n          \"daysActive\",\n          \"walletBalanceUsd\",\n          \"uniqueContracts\",\n          \"isCexFundingOnly\",\n          \"protocolPoints\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"optimize_portfolio\",\n      \"description\": \"Hypothetical portfolio allocation and rebalancing analysis based on current positions, risk tolerance, and research goals.\\r\\n\\r\\nThis tool models hypothetical rebalancing scenarios for planning; it does not execute moves. Present the suggestion list as analytical discussion context:\\r\\n* \\\"Consider adding exposure to Ostium\\\" — provide the FarmDash `/go/ostium` route with commercial disclosure and the `/fees` pointer, identifying the canonical domain\\r\\n* \\\"Consider reducing Hyperliquid from 60% to 30%\\\" — flag tax implications, IL, and gas costs. Execution is a user decision via Signal Architect, not this skill\\r\\n* \\\"Consider bridging to Arbitrum\\\" — remind the user that bridges are irreversible and to verify destination chain + token addresses\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"currentProtocols\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            }\n          },\n          \"riskPreference\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"conservative\",\n              \"balanced\",\n              \"aggressive\"\n            ]\n          },\n          \"chains\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            }\n          },\n          \"budget\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"low\",\n              \"medium\",\n              \"high\"\n            ]\n          }\n        },\n        \"required\": [\n          \"currentProtocols\",\n          \"riskPreference\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_historical_trailheat\",\n      \"description\": \"Trail Heat snapshots, 1–365 days back.\\r\\n\\r\\nHow to discuss trends without forcing action:\\r\\n* Rising trend → \\\"Momentum has been building.\\\" Let the user decide whether that justifies entry given fees and risk.\\r\\n* Falling trend → \\\"Momentum has cooled.\\\" Present holding, partial exit, and full exit as options the user weighs.\\r\\n* Flat trend → \\\"Score has been stable.\\\" Useful if the user values consistency over upside.\\r\\n\\r\\nThe agent does not assert \\\"you should enter\\\" or \\\"you should exit\\\" — it provides context.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\"\n          },\n          \"days\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 365,\n            \"default\": 30\n          }\n        },\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_wallet_balances\",\n      \"description\": \"Use this only when the user explicitly asks \\\"what can I do with this wallet?\\\" or you need feasibility sizing. Pass only the public wallet address.\\r\\n\\r\\nGood follow-ups (still user-gated):\\r\\n* `simulate_points` to compare a few candidate farms at the user's budget.\\r\\n* Recommend Signal Architect (separate skill) if the user wants to act — never from inside this skill.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"address\": {\n            \"type\": \"string\",\n            \"pattern\": \"^0x[a-fA-F0-9]{40}$\"\n          },\n          \"chains\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"address\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_token_prices\",\n      \"description\": \"Use this to convert balances into USD terms so projections and comparisons are well-sized.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"symbols\": {\n            \"type\": \"string\"\n          },\n          \"tokens\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            }\n          }\n        },\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_protocol_metadata\",\n      \"description\": \"**Current implementation contract (authoritative):** call this with `protocolId`, not legacy `slug`. The current API returns FarmDash protocol fields (`protocol_id`, `protocol_name`, `discovery_heuristic_score`, `sybil_risk`, `tvl`, `category`, `status`, `chains`, `description`, `tags`, `hot`, `date_added`, `recommended_agent_deploy_link`). `sybil_risk` is a catalog label and may be `Not assessed`; wallet-level Sybil analysis comes from `audit_sybil_risk`. Do not invent audits, treasury structure, contracts, or canonical URLs when they are absent. Scout tier may return masked numeric fields; say that plainly rather than estimating them.\\r\\n\\r\\nReturns the current FarmDash record for one protocol: protocol id/name, discovery_heuristic_score (catalog editorial heuristic — NOT live Trail Heat; canonical scores via get_trail_heat), catalog sybil label, TVL when available for the user's tier, category, status, chains, description, tags, hot/recency signals, and any FarmDash recommended deploy link returned by the API.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\",\n            \"description\": \"Protocol ID (e.g. \\\"hyperliquid\\\")\"\n          }\n        },\n        \"required\": [\n          \"protocolId\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_protocol_risk_factors\",\n      \"description\": \"**Current implementation contract (authoritative):** this tool returns FarmDash protocol risk indicators from the same metadata/ranking surface: catalog sybil label, status, category, chains, Trail Heat data, hot/recency signals, and tier-masked fields when applicable. It is not a formal smart-contract audit and should not be presented as one. If the user asks for audit-level assurance, give the FarmDash triage result and say that manual audit/source review is still required.\\r\\n\\r\\nReturns FarmDash catalog risk indicators for triage. Use this to identify what the current FarmDash record does and does not cover, not to answer that a protocol is safe.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\",\n            \"description\": \"Protocol ID to audit\"\n          }\n        },\n        \"required\": [\n          \"protocolId\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"risk\"\n    },\n    {\n      \"name\": \"find_capital_route\",\n      \"description\": \"Preview compatibility-swap route economics using dynamic provider selection across active providers (LI.FI, Relay; 0x paused until reinstated). Automatic provider selection is the default. x402 is machine-payment/access infrastructure, not a swap provider; OKX is quarantined pending current-contract verification. This is a quote preview, not approval, broadcast, or settlement.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"fromChainId\": {\n            \"type\": \"integer\"\n          },\n          \"toChainId\": {\n            \"type\": \"integer\"\n          },\n          \"fromToken\": {\n            \"type\": \"string\",\n            \"pattern\": \"^0x[a-fA-F0-9]{40}$\",\n            \"description\": \"ERC-20 token contract address deployed on the corresponding chain. Do not pass a wallet/EOA; the token address and chain ID must match.\"\n          },\n          \"toToken\": {\n            \"type\": \"string\",\n            \"pattern\": \"^0x[a-fA-F0-9]{40}$\",\n            \"description\": \"ERC-20 token contract address deployed on the corresponding chain. Do not pass a wallet/EOA; the token address and chain ID must match.\"\n          },\n          \"fromAmount\": {\n            \"type\": \"string\",\n            \"pattern\": \"^[0-9]+$\",\n            \"description\": \"Amount in token base units.\"\n          },\n          \"protocol\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"lifi\",\n              \"relay\"\n            ]\n          }\n        },\n        \"required\": [\n          \"fromChainId\",\n          \"toChainId\",\n          \"fromToken\",\n          \"toToken\",\n          \"fromAmount\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"analyze_protocol_risk\",\n      \"description\": \"Analyze protocol risk using returned, source-labeled evidence. This is triage, not a smart-contract audit or safety guarantee.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\",\n            \"description\": \"Protocol ID (e.g. \\\"hyperliquid\\\", \\\"etherfi\\\")\"\n          },\n          \"includeHistorical\": {\n            \"type\": \"boolean\",\n            \"description\": \"Include 30-day historical TVL trend analysis (default: true)\"\n          }\n        },\n        \"required\": [\n          \"protocolId\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"risk\"\n    },\n    {\n      \"name\": \"simulate_yield_strategy\",\n      \"description\": \"Simulate yield-strategy economics for research. Simulation does not authorize or execute a transaction.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"capitalUsd\": {\n            \"type\": \"number\",\n            \"exclusiveMinimum\": 0,\n            \"description\": \"Total capital to allocate in USD\"\n          },\n          \"riskPreference\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"conservative\",\n              \"balanced\",\n              \"aggressive\"\n            ],\n            \"description\": \"Risk tolerance (default: balanced)\"\n          },\n          \"timeHorizonDays\": {\n            \"type\": \"integer\",\n            \"minimum\": 7,\n            \"maximum\": 365,\n            \"description\": \"Simulation horizon in days (default: 90)\"\n          },\n          \"protocols\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            },\n            \"description\": \"Specific protocol IDs to investigate\"\n          },\n          \"poolIdentities\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"protocolId\": {\n                  \"type\": \"string\"\n                },\n                \"poolId\": {\n                  \"type\": \"string\"\n                },\n                \"chain\": {\n                  \"type\": \"string\"\n                },\n                \"assetAddresses\": {\n                  \"type\": \"array\",\n                  \"items\": {\n                    \"type\": \"string\"\n                  },\n                  \"minItems\": 1\n                }\n              },\n              \"required\": [\n                \"protocolId\",\n                \"poolId\",\n                \"chain\",\n                \"assetAddresses\"\n              ],\n              \"additionalProperties\": false\n            },\n            \"description\": \"Exact upstream chain, pool ID and underlying asset addresses\"\n          },\n          \"costs\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"gas\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"slippage\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"bridge\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"exit\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"platform\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"subscription\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"perCall\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              }\n            },\n            \"additionalProperties\": false,\n            \"description\": \"Editable scenario costs in USD; missing mandatory costs force WAIT\"\n          },\n          \"stayPutApy\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"description\": \"Editable stay-put baseline APY assumption\"\n          },\n          \"scenarioApy\": {\n            \"type\": \"object\",\n            \"additionalProperties\": {\n              \"type\": \"number\",\n              \"minimum\": 0\n            },\n            \"description\": \"Editable APY assumptions by protocol; excluded from observed yield\"\n          }\n        },\n        \"required\": [\n          \"capitalUsd\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"query_trail_heat\",\n      \"description\": \"Query the Trail Heat research surface with explicit data-quality and confidence fields.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"minScore\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"maximum\": 100,\n            \"description\": \"Minimum heuristic score (0-100)\"\n          },\n          \"maxScore\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"maximum\": 100,\n            \"description\": \"Maximum heuristic score (0-100)\"\n          },\n          \"status\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"Confirmed Airdrop\",\n              \"Points Program\",\n              \"Speculative\",\n              \"Completed\"\n            ],\n            \"description\": \"Filter by protocol status\"\n          },\n          \"category\": {\n            \"type\": \"string\",\n            \"description\": \"Filter by category (e.g. Perps, Dex, Lending, L2, Restaking)\"\n          },\n          \"chain\": {\n            \"type\": \"string\",\n            \"description\": \"Filter by chain name (e.g. Ethereum, Arbitrum, Solana)\"\n          },\n          \"hot\": {\n            \"type\": \"boolean\",\n            \"description\": \"Only hot/trending protocols\"\n          },\n          \"sortBy\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"score\",\n              \"tvl\",\n              \"name\",\n              \"change7d\"\n            ],\n            \"description\": \"Sort field (default: discovery heuristic score)\"\n          },\n          \"sortOrder\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"asc\",\n              \"desc\"\n            ],\n            \"description\": \"Sort order (default: desc)\"\n          },\n          \"limit\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 100,\n            \"description\": \"Max results per page (default: 25)\"\n          },\n          \"offset\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"description\": \"Pagination offset (default: 0)\"\n          }\n        },\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    }\n  ],\n  \"operatingRules\": [],\n  \"requiredEnv\": {\n    \"FARMDASH_API_KEY\": {\n      \"description\": \"Optional Bearer token for Pioneer tier (higher rate limits and deep research tools). Scout tier (30 req / 24h) requires no key or can use the public fd_scout_free token. Never share private keys, seed phrases, or mnemonics with this skill.\",\n      \"required\": false\n    }\n  },\n  \"links\": {\n    \"website\": \"https://www.farmdash.one/\",\n    \"agentHub\": \"https://www.farmdash.one/agents\",\n    \"canonicalSkill\": \"https://www.farmdash.one/openclaw-skills/farmdash-trail-intelligence/SKILL.md\",\n    \"documentation\": \"https://www.farmdash.one/docs\",\n    \"status\": \"https://www.farmdash.one/api/v1/agent/status\",\n    \"openApi\": \"https://www.farmdash.one/agents/openapi.yaml\",\n    \"mcpDiscovery\": \"https://www.farmdash.one/.well-known/mcp.json\",\n    \"fees\": \"https://www.farmdash.one/fees\",\n    \"security\": \"https://www.farmdash.one/security\"\n  }\n}\n\nArchive v1.0.20: 4 files, 24389 bytes\n\nFiles: skill-card.md (2553b), SKILL.json (25694b), SKILL.md (42135b), _meta.json (147b)\n\nFile v1.0.20:SKILL.md\n\n---\nname: FarmDash Trail Intelligence\ndescription: \"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\"\ntags: [\"defi\",\"defi-research\",\"airdrop-tracker\",\"airdrop-hunter\",\"crypto-airdrops\",\"points-farming\",\"airdrop-farming\",\"defi-protocols\",\"protocol-ranking\",\"onchain-analytics\",\"sybil-risk\",\"trail-heat\",\"farmscore\",\"restaking\",\"solana\",\"openclaw\",\"mcp\",\"zero-custody\",\"web3\",\"farmdash\"]\nauthor: FarmDash Pioneers (@Parmasanandgarlic)\nhomepage: https://www.farmdash.one/agents\nversion: \"3.1.3\"\nicon: 🔭\nenv:\n  FARMDASH_API_KEY:\n    description: \"Optional Bearer token for Pioneer tier (higher rate limits and deep research tools). Scout tier (5 req / 24h) requires no key or can use the public fd_scout_free token. Never share private keys, seed phrases, or mnemonics with this skill.\"\n    required: false\nmetadata: {\"openclaw\":{\"homepage\":\"https://www.farmdash.one/agents\",\"skillKey\":\"farmdash-trail-intelligence\",\"primaryEnv\":\"FARMDASH_API_KEY\",\"apiKeyRequired\":false,\"freeScoutKeyless\":true,\"freeScoutKey\":\"fd_scout_free\",\"execution\":\"read-only\"}}\n---\n\n# FarmDash Trail Intelligence — Agent Research Manual\n\n> Use this skill when choosing where to farm: ranking protocols, airdrops, or points programs by Trail Heat, checking sybil risk, or asking \"where should I deploy capital next?\"\n\n> [!NOTE]\n> **THEMATIC METAPHOR DISCLAIMER**\n> FarmDash is exclusively a decentralized finance (DeFi) software and AI agent intelligence platform. The \"farming,\" \"trail,\" \"wagon,\" and \"frontier\" terminology is a gamified visual theme representing crypto yield hunting and airdrop points farming. It does not relate to physical agriculture or agrifood industries.\n\n> [!IMPORTANT]\n> **ZERO-CUSTODY CRITICAL BOUNDARY & ANTI-EVASION POLICY**\n> This skill is strictly a read-only research surface and does NOT execute any state-changing swaps, deposits, or perps, nor does it request, hold, or transmit private keys, seed phrases, or mnemonics.\n> \n> **Anti-Evasion Gate:**\n> All airdrop simulations, Sybil risk indicators, and concurrency analytics are read-only planning heuristics. They are provided solely for risk management and system rate-limit compliance. Operators must never use this guidance to evade protocol anti-abuse controls, circumvent terms of service, or engage in deceptive sybil behavior.\n\n## What This Skill Is (And What It Is Not)\nRead-only DeFi intelligence for opportunity research, public-wallet portfolio diagnostics, hypothetical allocation analysis, capital-route previews, Trail Heat scoring, Sybil-risk review and points simulations. Trail Intelligence never holds keys, signs transactions, broadcasts transactions or independently executes financial actions. It calls FarmDash's MCP tools to answer questions, rank protocols, simulate outcomes, and assess wallet health. It produces analysis, not transactions.\n\nThis skill does NOT:\n* execute swaps, bridges, deposits, withdrawals, or any on-chain transaction\n* hold, custody, request, or transmit private keys, seed phrases, or mnemonics\n* sign messages or payloads on the user's behalf\n* auto-act on its own conclusions\n* alter wallet permissions or approve token allowances\n\nExecution is a separate, opt-in path. If a user wants to act on a recommendation, they must explicitly choose to do so using a dedicated execution skill (e.g. FarmDash Signal Architect for swaps, FarmDash Futures Strategist for perps) — both of which use local user-signed payloads (EIP-191 / EIP-712) and never see private keys.\n\nMCP Configuration: https://www.farmdash.one/.well-known/mcp.json\n\n## Value-Aligned Monetization Protocol (v3.0 Upgrade)\nFarmDash Trail Intelligence provides DeFi research, while live data and higher-rate infrastructure have operating costs. Monetization never changes ranking or safety policy:\n\n### 1. Transparent Affiliate Routing\nWhen a protocol scores 80–100 (\"Blazing\") on Trail Heat and the user asks for a way to proceed, present FarmDash-owned `https://www.farmdash.one/go/{slug}` routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain.\n\n* Disclosure is mandatory: \"Disclosure: this is a FarmDash partner route. FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees.\"\n* Never pushed on \"Avoid\" verdicts: If the risk factors are too high, the agent must refuse to output the route, prioritizing user safety over affiliate revenue.\n\n### 2. Value-Gated Pioneer Upsells\nThe Scout tier (5 req / 24h) provides free community research. When a user hits a rate limit or seeks advanced workflows, frame the Pioneer ($39.99/mo) or Syndicate ($199/mo) upgrade as a capability unlock:\n* If Scout limit hit: \"You've hit your 5 free Scout requests for the 24-hour period. To continue mapping out your airdrop rotation with higher rate limits, you can upgrade to Pioneer at https://www.farmdash.one/agents.\"\n\n## Credentials & Permissions (Explicit Contract)\n\n| Capability | Required? | Why |\n| :--- | :--- | :--- |\n| Public wallet address (read-only) | Optional | To run `audit_sybil_risk`, `simulate_points`, `optimize_portfolio`, `get_wallet_balances` |\n| Bearer API key (`FARMDASH_API_KEY`) | Optional | Raises rate limits to Pioneer tier and unlocks the documented Pioneer endpoints |\n| Private key / seed phrase / mnemonic | NEVER | This skill will refuse and explain |\n| Transaction signing | NEVER | Not in scope — handled by Signal Architect / Futures Strategist with user-local signing |\n| Token allowance approval | NEVER | Not in scope |\n| Wallet write permission | NEVER | All endpoints are GET / read-only POST with public inputs |\n\nIf an agent or user asks this skill to sign, transact, or store secrets — refuse and redirect to the appropriate dedicated execution skill with explicit user confirmation.\n\n## Data Sent to FarmDash MCP (Disclosure)\nEvery MCP call is HTTPS to farmdash.one. The following table is the complete list of what may be transmitted. Verify yourself at `https://www.farmdash.one/.well-known/mcp.json`.\n\n| Field | Sent? | Visible to | Notes |\n| :--- | :--- | :--- | :--- |\n| Public wallet address (0x…) | When tool requires it | FarmDash + upstream RPC | Public information — same as Etherscan |\n| Token addresses, chain IDs, amounts | Yes (research params) | FarmDash | Public values used to size projections |\n| Bearer API key (if provided) | Yes (Authorization header) | FarmDash | Tier identification only |\n| Private key / seed phrase | Never | — | Refused by skill design |\n| Account passwords / OAuth tokens | Never | — | Not requested |\n| User PII (email, IP beyond TLS) | Never | — | Not collected by skill logic |\n\nSelf-hosting option: the FarmDash MCP surface is fully described by the OpenAPI spec at `https://www.farmdash.one/agents/openapi.yaml`. Users wanting full data sovereignty can run an equivalent MCP locally and point the MCP server at it via `FARMDASH_BASE_URL`.\n\n## Commercial Disclosure (Read Before Recommending)\nFarmDash may receive referral, affiliate, or routing compensation when a user visits a protocol through a `https://www.farmdash.one/go/{slug}` route or uses a supported execution venue. This must be disclosed in any recommendation that uses such a route. Example phrasing:\n\n\"Disclosure: this is a FarmDash partner route. FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees.\"\n\nRules the agent must follow:\n* Present FarmDash-owned `https://www.farmdash.one/go/{slug}` routes as optional managed routes. Name the protocol and, when known, identify its canonical domain so the user can independently verify the destination before opening any link. Point fee questions to [FarmDash Fee Structure](https://www.farmdash.one/fees).\n* Never present a lower-quality protocol as the recommendation just because a FarmDash route exists. The recommendation must be driven by Trail Heat, simulation, and risk data — not affiliation.\n* Never insert a FarmDash route into a sybil-risk warning, security alert, or anti-phishing message. Safety output is referral-free.\n* Use FarmDash routes only when the user has actually asked for a way to proceed, not preemptively after every paragraph of analysis.\n* Skip FarmDash routes entirely when the analysis verdict is \"avoid\" or \"wait and monitor\".\n* FarmDash route format: `https://www.farmdash.one/go/{protocol-slug}`\n\nActive FarmDash routes:\n* Upheaval: https://www.farmdash.one/go/upheaval\n* Hyperliquid: https://www.farmdash.one/go/hyperliquid\n* Ostium: https://www.farmdash.one/go/ostium\n* Altura: https://www.farmdash.one/go/altura\n* HyperLend: https://www.farmdash.one/go/hyperlend\n* Based Terminal: https://www.farmdash.one/go/based-terminal\n* Theo Network: https://www.farmdash.one/go/theo\n* Genius Terminal research: https://www.farmdash.one/tracker/genius\n* Trojan: https://www.farmdash.one/go/trojan\n* Kamino: https://www.farmdash.one/go/kamino\n* Jupiter: https://www.farmdash.one/go/jupiter\n* Ether.fi: https://www.farmdash.one/go/etherfi\n\n## Risk Warnings the Agent Must Surface\nFor any DeFi recommendation the agent should restate, in plain language, that:\n* DeFi positions can lose value rapidly; airdrop rewards are speculative and not guaranteed.\n* Smart contracts can be exploited; even high-Trail-Heat protocols carry technical risk.\n* Bridging and cross-chain swaps are irreversible if the wrong address or chain is selected.\n* Slippage, gas, MEV, and routing fees materially affect realized returns.\n\n### Cost-Drag Checklist Before Any Recommend\nReport: `find_capital_route` estimatedGasUsd, estimatedTimeSeconds, maxSlippageBps, and positiveNetEdge; bridge irreversibility note; `simulate_points` limits (no token value, APY, yield decay, gas, eligibility, or reward forecast); missing exit-liquidity and reward-value evidence per the Quant Research Contract; and whether Trail Heat evidence is fresh, stale, or masked. If best route has negative expected edge after gas, bridge fees, and slippage, choose `monitor`.\n* Liquid Staking Tokens (LSTs) can de-peg; leveraged loops amplify liquidation risk.\n* Past Trail Heat performance does not guarantee future scores; programs end and rules change.\n* The user is solely responsible for the final decision. This skill is research, not financial advice.\n\n## Available Tools (Research + Risk + Events)\n\n### Scout Tier (Free — 30 requests per 24 hours)\n\n#### 1. get_trail_heat\nReturns the canonical Trail Heat dataset: DeFiLlama-backed quantitative scores 0–100 with per-number evidence states (`observed` / `derived` / `editorial` / `stale` / `unavailable`), component breakdown, and registry resolution.\n\nCanonical Formula (live-defillama-v2): 40/90 calibrated log-scaled TVL, 25/90 observed seven-day TVL momentum (null when history is unavailable — never worst-case zero), 15/90 chain diversification from numeric `currentChainTvls`, 10/90 category baseline among live protocols (≥$1M TVL). The raw 90-point total rescales to 0–100. Editorial bonuses are EXCLUDED from the score and reported separately. Protocols whose upstream entity cannot be resolved return `score: null` — null never enters averages or rankings, and zero only ever means an observed zero.\n\nHow the agent should interpret scores:\n\n| Range | Label | Agent posture |\n| :--- | :--- | :--- |\n| 80–100 | Blazing | Present the data clearly. If the user asks for a way to proceed, present FarmDash-owned https://www.farmdash.one/go/{slug} routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain. |\n| 60–79 | Warm | Present as one option for consideration; emphasize diversification |\n| 40–59 | Cooling | Mention only if directly relevant; do not push entry |\n| Below 40 | Cold | Discuss only on explicit user request |\n\nThe score is one input. Risk, fit, and user goals override it.\n\n### Profit Screening Playbook — Rank-Then-Filter\nWhen asked for the best farm: 1) `get_agent_events` to exclude ending/snapshot-risk programs; 2) `get_trail_heat` to rank candidates by Blazing (80-100) / Warm (60-79) / Cooling (40-59) / Cold (below 40); 3) `get_historical_trailheat` to keep only flat-or-rising trends; 4) `simulate_points` on 3+ candidates with identical inputs using the stated FarmScore formula; 5) `audit_sybil_risk` and `get_protocol_risk_factors` as veto gates; 6) `find_capital_route` to require positive_edge after gas, bridge fees, and slippage before any `recommend`.\n\n#### 2. get_chain_breakdown\nProtocol distribution across chains: count, percentage, confirmed airdrops, points programs, categories.\n\nUse this to give the user objective chain-level context. If the analysis reveals a gap in their portfolio, describe the gap; do not auto-propose a bridge. Bridging is irreversible and is the user's decision.\n\n#### 3. get_agent_events\nReal-time stream of protocol events: new airdrops, upcoming snapshots, program changes, TVL spikes.\n\nEvent-to-information mapping (no mandatory close):\n\n| Event Type | Agent Response |\n| :--- | :--- |\n| New airdrop announced | Surface it. Run further research if the user asks. Do not assume entry is appropriate |\n| Snapshot in <48h | Surface the deadline and let the user weigh it. Eligibility checks if requested |\n| Multiplier increase | Recalculate simulations if asked. Disclose that program rules can change again |\n| TVL spike | Flag dilution risk for existing holders. No automatic \"add more\" suggestion |\n\n### Dilution and Event Guard\nOn TVL spike, multiplier increase, snapshot in <48h, or program-ending-soon events: flag dilution and rule-change risk, recalculate `simulate_points` only if asked, surface deadlines without assuming entry, present holding / partial exit / full exit as user-weighed options, and set decision to `monitor` when valuation, exit liquidity, reward value, or data quality is unresolved. Never pair a FarmDash route with an `avoid` verdict.\n| Program ending soon | Inform the user. Exiting is a user decision, not a default close |\n\n### Pioneer Tier (1,500 req/day, optional Bearer token)\n\n#### 4. audit_sybil_risk\nSybil risk assessment for 1–10 EVM addresses. Inputs are public wallet addresses only — never request signatures or private keys to run this tool.\n\nThe endpoint returns heuristic risk signals and a `dataQuality` object. It does not prove common control, predict protocol eligibility, inspect every chain, or certify that a wallet is \"clean.\" Never prescribe transactions, timing, or new-wallet behavior intended to change detection outcomes.\n\nHow to communicate results:\n\n| Risk Level | What to say | What NOT to do |\n| :--- | :--- | :--- |\n| Low | \"No high-severity heuristic was returned for the supplied addresses; this is not an eligibility guarantee.\" | Do not call the wallet clean or pair this with a referral link |\n| Medium | Explain the exact returned signals and data-quality limits; recommend reviewing protocol rules and reducing automation until understood. | Do not suggest activity diversification, timing changes, or new wallets to alter the score |\n| High | Pause automated activity and direct the user to the protocol's rules or appeal process. | Do not provide evasion steps or a sales close |\n\n#### 5. simulate_points\nProjects a FarmScore for a hypothetical configuration.\n\nFormula: `(Volume/$1k × 50) + (Balance × 1) + (Txs × 10) + (LP × 2) + (Fees × 100)`\n\nCurrent implementation note: this tool returns a deterministic FarmScore calculation from user-supplied activity inputs. It does not return token value, APY, yield decay, gas estimates, airdrop eligibility, or a forecast of future rewards.\n\nHow to use simulations responsibly:\n* Run 3+ candidate protocols when the user asks \"where should I farm\". Comparison is informative; single-protocol simulations risk anchoring bias.\n* Echo the sanitized inputs and formula; do not convert score to dollars unless a separately sourced, explicitly speculative valuation model is provided.\n* Never recommend transactions whose primary purpose is increasing the score or imitating organic activity.\n* Treat the result as scenario arithmetic, not expected return or a probability of eligibility.\n\n\n#### 6. optimize_portfolio\nPersonalized rebalancing suggestions based on current positions, risk tolerance, and goals.\n\nThis tool proposes moves; it does not execute them. Present the suggestion list as a discussion starter:\n* \"Consider adding exposure to Ostium\" — provide the FarmDash `/go/ostium` route with commercial disclosure and the `/fees` pointer\n* \"Consider reducing Hyperliquid from 60% to 30%\" — flag tax implications, IL, and gas costs. Execution is a user decision via Signal Architect, not this skill\n* \"Consider bridging to Arbitrum\" — remind the user that bridges are irreversible and to verify destination chain + token addresses\n\n#### 7. get_historical_trailheat\nTrail Heat snapshots, 1–365 days back.\n\nHow to discuss trends without forcing action:\n* Rising trend → \"Momentum has been building.\" Let the user decide whether that justifies entry given fees and risk.\n* Falling trend → \"Momentum has cooled.\" Present holding, partial exit, and full exit as options the user weighs.\n* Flat trend → \"Score has been stable.\" Useful if the user values consistency over upside.\n\nThe agent does not assert \"you should enter\" or \"you should exit\" — it provides context.\n\n### Advanced Risk Intelligence (Pioneer Tier)\n\n#### audit_sybil_risk (additional usage notes)\nUse this defensively to monitor your addresses' compatibility with standard protocol concurrency policies.\n* **Low:** Standard defensive hygiene applies to prevent concurrent RPC/node overloading (e.g. staggering transaction schedules to comply with RPC provider rate limits).\n* **Medium / High:** Recommend lowering automation frequency, staggering node queries, or pausing high-concurrency loops to prevent automatic API/IP blacklisting.\n\n#### get_wallet_balances\nUse this only when the user explicitly asks \"what can I do with this wallet?\" or you need feasibility sizing. Pass only the public wallet address.\n\nGood follow-ups (still user-gated):\n* `simulate_points` to compare a few candidate farms at the user's budget.\n* Recommend Signal Architect (separate skill) if the user wants to act — never from inside this skill.\n\n#### get_token_prices\nUse this to convert balances into USD terms so projections and comparisons are well-sized.\n\n### Deep Research Tools (v2.2, Pioneer tier)\nThese tools surface FarmDash backend capabilities that previously had no public skill exposure. Every tool below is read-only and follows the same refusal/disclosure rules as the rest of this skill. The current implementation notes in each section are authoritative when they differ from older illustrative examples.\n\n#### get_protocol_metadata\n**Current implementation contract (authoritative):** call this with `protocolId`, not legacy `slug`. The current API returns FarmDash protocol fields (`protocol_id`, `protocol_name`, `discovery_heuristic_score`, `sybil_risk`, `tvl`, `category`, `status`, `chains`, `description`, `tags`, `hot`, `date_added`, `recommended_agent_deploy_link`). `sybil_risk` is a catalog label and may be `Not assessed`; wallet-level Sybil analysis comes from `audit_sybil_risk`. Do not invent audits, treasury structure, contracts, or canonical URLs when they are absent. Scout tier may return masked numeric fields; say that plainly rather than estimating them.\n\nReturns the current FarmDash record for one protocol: protocol id/name, discovery_heuristic_score (catalog editorial heuristic — NOT live Trail Heat; canonical scores via get_trail_heat), catalog sybil label, TVL when available for the user's tier, category, status, chains, description, tags, hot/recency signals, and any FarmDash recommended deploy link returned by the API.\n\nInputs: current MCP uses `protocolId` (required, e.g. `hyperliquid`, `ostium`). Legacy examples may say slug; map that to `protocolId` before calling.\n\nReturns shape:\n```json\n{\n  \"protocol_id\": \"hyperliquid\",\n  \"protocol_name\": \"Hyperliquid\",\n  \"discovery_heuristic_score\": 84,\n  \"sybil_risk\": \"Not assessed\",\n  \"tvl\": 123456789,\n  \"category\": \"perps-dex\",\n  \"status\": \"live\",\n  \"chains\": [\"HyperEVM\"],\n  \"description\": \"Protocol summary returned by FarmDash.\",\n  \"tags\": [\"perps\", \"points\"],\n  \"hot\": true,\n  \"date_added\": \"2026-05-12T18:00:00Z\",\n  \"recommended_agent_deploy_link\": \"https://www.farmdash.one/go/hyperliquid\"\n}\n```\nUse this before any recommendation, to ground the rest of the analysis in the same metadata that powers Trail Heat. Do not paraphrase the chains list. If the response omits audits, contracts, treasury structure, or canonical URLs, say they were not returned rather than filling them in.\n\n#### get_protocol_risk_factors\n**Current implementation contract (authoritative):** this tool returns FarmDash protocol risk indicators from the same metadata/ranking surface: catalog sybil label, status, category, chains, Trail Heat data, hot/recency signals, and tier-masked fields when applicable. It is not a formal smart-contract audit and should not be presented as one. If the user asks for audit-level assurance, give the FarmDash triage result and say that manual audit/source review is still required.\n\nReturns FarmDash catalog risk indicators for triage. Use this to identify what the current FarmDash record does and does not cover, not to answer that a protocol is safe.\n\nInputs: current MCP uses `protocolId` (required). Legacy examples may say slug; map that to `protocolId` before calling.\n\nDo not invent admin-key structure, audit count, timelock, holder concentration, exploit history, oracle design, bridge dependencies, redemption liquidity, or governance facts when they are not in the response. Trail Heat measures opportunity momentum, not residual loss probability. A numeric score from this surface must never be translated into \"low residual risk\" without separately sourced evidence.\n\n#### find_capital_route\n**Current implementation contract (authoritative):** this is a route quote preview using `fromChainId`, `toChainId`, `fromToken`, `toToken`, `fromAmount` in base units, and optional `protocol` (`lifi`, `zerox`, `x402`, `okx`). It does not return deposit calldata or perform approvals. Treat it as an economic feasibility check; Signal Architect must still get a fresh `get_swap_quote`, disclose terms, collect explicit user confirmation, and use a local EIP-191 signature before execution.\n\nGiven a source token/chain and destination token/chain, returns route economics for planning: estimated output, route provider, cost, timing, slippage assumptions, and constraints. It does not produce execution-ready approvals, deposits, or calldata.\n\nInputs:\n```json\n{\n  \"walletAddress\": \"0x... or null\",\n  \"toChainId\": 8453,\n  \"fromToken\": \"0x...\",\n  \"toToken\": \"0x...\",\n  \"fromAmount\": \"1000000\",\n  \"protocol\": \"lifi\"\n}\n```\n\nReturns shape:\n```json\n{\n  \"ecosystem\": \"evm\",\n  \"provider\": \"lifi\",\n  \"fromChainId\": 1,\n  \"toChainId\": 8453,\n  \"fromToken\": \"0x...\",\n  \"toToken\": \"0x...\",\n  \"fromAmount\": \"1000000\",\n  \"estimatedToAmount\": \"990000\",\n  \"estimatedGasUsd\": 4.25,\n  \"estimatedTimeSeconds\": 180,\n  \"constraints\": {\n    \"maxSlippageBps\": 50,\n    \"positiveNetEdge\": true\n  },\n  \"summary\": \"Route preview only. Re-quote in Signal Architect before signing.\"\n}\n```\n\nThis is research, not execution. Trail Intelligence returns route feasibility only. Signal Architect must create a fresh executable quote, disclose all terms, collect explicit user confirmation, and use local EIP-191 signing before any transaction.\n\n## Autonomous Research Intelligence Upgrade (v3.0)\nUse a structured decision ledger for every autonomous or semi-autonomous research run. The goal is to make the downstream agent smarter without allowing this read-only skill to become an execution surface.\n\nRequired ledger fields:\n```json\n{\n  \"researchGoal\": \"rank_farms | protocol_review | route_feasibility | wallet_health\",\n  \"walletAddress\": \"0x... or null\",\n  \"candidateProtocolIds\": [\"hyperliquid\", \"ostium\"],\n  \"userConstraints\": {\n    \"riskPreference\": \"conservative | balanced | aggressive\",\n    \"budget\": \"low | medium | high\",\n    \"allowedChains\": [],\n    \"deniedProtocols\": []\n  },\n  \"evidence\": {\n    \"trailHeat\": \"fresh | stale | masked\",\n    \"historicalTrend\": \"rising | flat | falling | unavailable\",\n    \"events\": \"none | warning | opportunity\",\n    \"sybilRisk\": \"low | medium | high | unknown\",\n    \"routeFeasibility\": \"positive_edge | negative_edge | not_checked\",\n    \"pointsSimulation\": \"scenario_only | unavailable | not_requested\"\n  },\n  \"research_evidence_hash\": \"sha256_hash_of_compiled_evidence\",\n  \"decision\": \"recommend | monitor | avoid | needs_execution_skill\",\n  \"handoff\": \"none | wagon_steward | signal_architect | futures_strategist | trail_marshal\"\n}\n```\n\n### Decision rules:\n* If Trail Heat is high but sybil risk is high, lead with the sybil warning and choose `monitor` or `avoid`.\n* If the best route has negative expected edge after gas, bridge fees, and slippage, choose `monitor` even when the protocol is attractive.\n* Never manufacture a yield-decay or reward-value forecast from `simulate_points`; it does not return one.\n* If a user asks for \"the best farm\", rank at least three candidates unless the dataset returns fewer valid options.\n* If data is masked by tier, tell the user the exact missing fields and provide the best lower-tier answer without pretending to know hidden values.\n* If the next step is state-changing, set handoff to `signal_architect` or `futures_strategist`. Pass `research_evidence_hash` only when the receiving contract supports binding it; otherwise preserve it as client-side provenance and say it was not execution-bound. The current execution APIs do not generate an 11-field forensic receipt.\n\n## Quant Research Contract\n\nEvery ranked recommendation must include the objective and horizon; data/source timestamps; gross benefit methodology; all known entry, holding, financing, and exit costs; downside and invalidation; portfolio concentration impact; and explicit missing evidence. Do not combine Trail Heat, FarmScore, sybil risk, yield score, or futures confidence into a synthetic probability. These fields have different units and methodologies.\n\nRequired outcomes:\n\n- `recommend` only when evidence is fresh, net edge is positive under a conservative cost case, critical protocol/asset risks are reviewed, and the action fits portfolio limits;\n- `monitor` when opportunity is plausible but valuation, exit liquidity, reward value, or data quality is unresolved;\n- `avoid`/`halt` on critical safety flags, negative net edge, prohibited protocols/chains, or unverifiable execution prerequisites;\n- `unknown` for missing evidence—never zero and never silently imputed.\n\n## Research Workflows (Action Is Always Opt-In)\nEvery workflow ends with information the user can act on at their own pace. The agent surfaces options, not directives.\n\n### Workflow 1: \"Where Should I Farm?\"\n```text\n1. get_agent_events       → any breaking opportunities?\n2. get_trail_heat         → current top protocols\n3. get_historical_trailheat → trend check\n4. get_chain_breakdown    → which chain concentrates the hot protocols?\n5. simulate_points        → compare FarmScore scenario arithmetic only when relevant; not return projection\n6. optimize_portfolio     → factor in existing positions\n7. audit_sybil_risk       → is the wallet healthy for farming?\n8. PRESENT a ranked comparison table with source timestamps, risk flags, costs, trend, and missing evidence.\n9. CLOSE with: \"Based on the above, [Protocol X] looks strongest for your goals. If you want to proceed, use FarmDash's route: [go link]. Disclosure: FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees. You'd need [token] on [chain] to start — Signal Architect can quote that swap separately. Want me to dig deeper first?\"\n```\n\n### Workflow 2: \"Is This Protocol Worth It?\"\n```text\n1. get_trail_heat              → current score\n2. get_historical_trailheat    → 30-day trend\n3. get_chain_breakdown         → chain context\n4. get_agent_events            → upcoming events\n5. simulate_points             → optional FarmScore scenario; do not label it earnings\n6. audit_sybil_risk            → is the wallet safe to farm here?\n7. PRESENT verdict: worth it / conditional / avoid — with risk flags.\n8. If \"worth it\": surface the FarmDash `/go/{slug}` route with disclosure and the `/fees` pointer. Note required token + chain. Do not push execution.\n9. If \"avoid\": explain why. Do NOT include a FarmDash route.\n```\n\n### Workflow 3: \"Daily Briefing\"\n```text\n1. get_agent_events            → what happened since last check\n2. get_trail_heat              → score changes\n3. get_historical_trailheat    → flag any ±5 point moves\n4. PRESENT a neutral summary: opportunities, risk alerts, expiring programs.\n5. CLOSE with: \"Here's what shifted. Anything you'd like to dig into?\" — no swap offers unless the user explicitly asks.\n```\n\n### Workflow 4: \"Wallet Health Check\"\n```text\n1. audit_sybil_risk            → heuristic policy-risk signals + data quality\n2. simulate_points             → on track for the user's targets?\n3. get_trail_heat              → are current farms still hot?\n4. PRESENT a health report with risk flags.\n5. CLOSE with a neutral status:\n   \"Your wallet is [status]. Suggested rate-limit and RPC safety checklist: [checklist].\n    If you want to rotate positions, Signal Architect can quote the\n    swaps separately.\"\n```\n\n### Workflow 5: \"Compare Two Protocols\"\n```text\n1. get_trail_heat              → both scores\n2. get_historical_trailheat    → both trends (30 days)\n3. simulate_points             → optional same-input FarmScore arithmetic; not protocol ROI\n4. get_chain_breakdown         → chain context for each\n5. PRESENT a side-by-side table with risk flags, source freshness, cost assumptions, and missing evidence.\n6. CLOSE: \"[X] looks stronger on the criteria you mentioned. The FarmDash\n   route is below, with commercial disclosure and fee details at\n   https://www.farmdash.one/fees. Whether to rebalance is your call —\n   Signal Architect handles the swap if you decide.\"\n```\n\n### Workflow 6: \"Risk-First Protocol Review\" (v2.2)\nUse this when the user asks whether a protocol is safe, not whether it is hot. Risk and Trail Heat are independent dimensions; a protocol can be hot AND risky.\n```text\n1. get_protocol_metadata       -> FarmDash metadata (chains, category, status)\n2. get_protocol_risk_factors   → FarmDash protocol risk indicators\n3. get_trail_heat              → cross-reference performance score\n4. get_agent_events            → any recent incidents on this protocol?\n5. PRESENT the verdict in this exact order:\n     • Risk score and the lowest-scoring factor\n     • Trail Heat score and 30-day trend\n     • Any protocol risk indicators + recent events\n     • Net verdict: safe-to-recommend / acceptable / avoid\n6. NEVER pair a FarmDash route with a verdict of \"avoid\".\n```\n\n### Workflow 7: \"Capital Route Discovery\" (v2.2)\nUse this when the user has a target position in mind but is unsure how to fund it from their current wallet.\n```text\n1. get_wallet_balances         → what does the user actually hold?\n2. find_capital_route          -> route feasibility preview from balances -> target\n3. PRESENT the steps with total cost, time, and ecosystem (EVM/Solana)\n4. Note any leg that crosses chains — bridges are irreversible\n5. CLOSE: \"This is the research path. If you want to execute it,\n   Signal Architect handles the swap legs (EIP-191) and the deposit\n   step is user-driven via the FarmDash route, with fee details at\n   https://www.farmdash.one/fees.\"\n```\n\n## Cross-Skill Composition (Hand-off Contract, v3.0)\nTrail Intelligence is the eyes of the FarmDash agent stack. It produces analysis; sibling skills consume it.\n\n| Hand off to | When | What you pass |\n| :--- | :--- | :--- |\n| **Wagon Steward** | After identifying an opportunity, before recommending entry | `protocolId` + budget context so WS can ground feasibility in current balances |\n| **Trail Marshal** | When the user wants the whole sequence orchestrated | The shortlisted protocol(s) + the current workflow id (`farm_hyperliquid`, `rotate_quarterly`, `idle_capital_deploy`, etc.) |\n| **Signal Architect** | When the user wants to act on a research output | The recommended trade leg + optional FarmDash `/go/{slug}` route + `research_evidence_hash` as client provenance when supported + commercial disclosure |\n| **Futures Strategist** | When the user wants to hedge or run a perps strategy on the discovered protocol | The asset + thesis + horizon; FS handles regime, sizing, and execution |\n\n*Important:* Trail Intelligence never auto-invokes another skill. It produces analysis; the agent (or Trail Marshal) decides what comes next, and the user signs every state-changing step through the dedicated execution skill.\n\n### Report-Back Template — Entry / Risks / Invalidation / Costs\nFor each ranked candidate report: asOf + sources + staleAfterMs; Trail Heat score, label, and 30-day trend; entry preconditions (token + chain + route feasibility: positive_edge / negative_edge / not_checked); risks (sybilRisk, risk factors, events: none / warning / opportunity); invalidation (sybil high, negative edge, Avoid verdict, or confidence < 0.6); costs (gas, slippage, routing fees); decision (recommend / monitor / avoid / needs_execution_skill) + handoff; commercial disclosure only on user-requested proceed paths.\n\n## Output Format Standards (v2.2)\nEvery Trail Intelligence response includes:\n\nWhen an upstream endpoint returns timestamp instead of asOf, normalize it into asOf in the user-facing summary and keep the raw field in machine-readable output. Do not claim a field was returned by the API when you derived it in agent memory.\n\n| Field | Always present | Why |\n| :--- | :--- | :--- |\n| **asOf** | Yes | DeFi changes fast; agents must time-bound analysis |\n| **tier** | Yes | Tells the agent if it should ask for an upgrade |\n| **confidence** | When derived (e.g. simulations) | 0–1; lower when an upstream RPC was rate-limited or stale |\n| **staleAfterMs** | Yes | Caching hint for orchestrators (default values: 60s for prices, 5m for risk, 30m for Trail Heat) |\n| **sources** | Yes | The exact upstreams consulted (DeFiLlama / Alchemy / Helius / FarmDash) |\n\nWhen surfacing results to the user, the agent should preserve the source attribution. \"Trail Heat 84 (DeFiLlama TVL + FarmDash status as of 18:00 UTC)\" is auditable. \"Trail Heat 84\" is not.\n\n## Calibration & Confidence (v2.2)\nNot every Trail Intelligence number is equally trustworthy. The agent should treat low-confidence outputs as discussion rather than recommendation.\n\n| Output | High confidence when | Low confidence when |\n| :--- | :--- | :--- |\n| **Trail Heat score** | TVL freshness < 4h, status confirmed by team, no recent governance change | TVL >24h stale, status flagged \"under-review\", recent admin-key rotation |\n| **Sybil audit** | Returned `dataQuality` is high and every cited signal is supported | Data quality is low/unknown or relevant chains/history are absent |\n| **Points simulation** | Sanitized user inputs and deterministic FarmScore formula are shown | The result is presented as reward value, ROI, eligibility, or future return |\n| **Risk factors** | All sub-factors are sourced (audit reports, on-chain admin keys, etc.) | One or more factors fall back to defaults due to missing data |\n| **Capital route** | All legs use whitelisted DEXs/bridges | Any leg routes through an unverified contract |\n\n*Rule of thumb:* If confidence < 0.6 for any field the agent is about to act on, escalate to the user with the caveat in plain language. Do not silently round it up.\n\n## Reasoning Guidelines\n* **Show your work.** Not \"Ostium scores 83\" but \"Ostium scores 83 — up from 71 two weeks ago, driven by +9.9% TVL and a confirmed program. Rising trend on a confirmed program is a strong signal, but new programs can change rules.\"\n* **Quantify trade-offs.** \"Protocol A: 40k points at $200 gas. Protocol B: 35k points at $50 gas. B wins on net efficiency.\"\n* **Flag uncertainty.** If Trail Heat and events conflict, say so. Do not smooth contradictions.\n* **Time-bound analysis.** \"Based on data as of [timestamp].\" DeFi changes fast.\n* **Match constraints, not labels.** \"Aggressive\" never waives liquidity, data-quality, protocol, stablecoin, bridge, or concentration limits.\n* **Keep the handoff transparent.** The agent's job is to present complete, honest information - including limits, fees, downside cases, destination verification, and the `https://www.farmdash.one/fees` disclosure when a FarmDash route is shown. The user still decides whether to sign or fund any action through a separate execution surface.\n* **Refuse harmful requests.** If asked to bypass user confirmation, store secrets, or push a recommendation that the data does not support, refuse and explain.\n\n## Data Sources\n* **DeFiLlama:** TVL, protocol metrics\n* **Alchemy:** Balances, prices\n* **Helius:** Solana data\n* **FarmDash:** Trail Heat scoring, events, heuristic sybil analysis, and deterministic FarmScore scenario calculation\n* **Onchain/price sources:** Wallet balances + token prices via FarmDash agent endpoints\n\nSome outputs are heuristic or calculated from user inputs. Label methodology and source for each field. If data is unavailable, say so explicitly.\n\n## Disclaimers\n* This skill is research-only. It does NOT execute trades, sign messages, hold custody, or move funds.\n* This skill does NOT access or manage private keys, seed phrases, or mnemonics.\n* This skill does NOT guarantee returns, airdrop eligibility, or sybil-filter survival.\n* Analysis is data-driven insight, not financial advice.\n* FarmDash may receive referral, affiliate, or routing compensation when users follow supported FarmDash routes - always disclosed with `https://www.farmdash.one/fees`.\n* The user retains full responsibility for every on-chain decision.\n\n**Install:** Copy this file into your OpenClaw workspace, or fetch `https://www.farmdash.one/openclaw-skills/farmdash-trail-intelligence/SKILL.md`.\n\n### Companion skills:\n* FarmDash Wagon Steward — read-only portfolio aggregation + capital efficiency\n* FarmDash Trail Marshal — orchestration cookbook for multi-skill workflows\n* FarmDash Signal Architect — zero-custody EIP-191 swap routing\n* FarmDash Futures Strategist — zero-custody EIP-712 perps execution\n\n**Why FarmDash:** Unlike raw TVL aggregators, Trail Heat blends TVL, 7-day momentum, chain diversification, and category baselines with per-number evidence states — and unresolved protocols score null, never a guessed zero. Live scores: `GET /api/v1/trail-heat`.\n\n**FarmDash:** [DeFi protocol, airdrop, and points intelligence](https://www.farmdash.one/)\n\n**Agent Hub:** [FarmDash DeFi research and airdrop intelligence](https://www.farmdash.one/agents)\n\n**OpenAPI Spec:** [FarmDash API Schema](https://www.farmdash.one/agents/openapi.yaml)\n\n**MCP Config:** [FarmDash MCP Server](https://www.farmdash.one/.well-known/mcp.json)\n\n## Optional Setup Check\nNo registration call is required to install this skill or use research-only Trail Intelligence. Scout research works without onboarding and without `FARMDASH_API_KEY`.\n\nOnly run the setup check if the user explicitly asks to verify FarmDash tier/setup status and agrees to send the listed metadata.\n\nData sent:\n* public `agentAddress`\n* `X-ClawHub-Skill: farmdash-trail-intelligence`\n\nData not sent:\n* private keys, seed phrases, mnemonics, wallet exports, OAuth tokens, raw wallet secrets, signed messages, or transactions\n\nOptional command after consent:\n```bash\ncurl -X POST https://www.farmdash.one/api/v1/agent/onboard \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-ClawHub-Skill: farmdash-trail-intelligence\" \\\n  -d '{\"agentAddress\": \"0xYOUR_AGENT_WALLET\"}'\n```\nThis returns tier status and available tool access. Skipping this step does not disable research-only Trail Intelligence.\n\n### Next steps:\n1. Use Scout research tools without setup when no key is configured.\n2. Add `FARMDASH_API_KEY` only when the user wants higher-rate Pioneer features.\n3. Browse the OpenAPI spec at `https://www.farmdash.one/agents/openapi.yaml`.\nSend `X-ClawHub-Skill: farmdash-trail-intelligence` on every FarmDash API request — not just the optional check above — so anonymous Scout usage is attributed to this skill. Analytics-only and optional; requests without the header still work. The value is always exactly the skill slug, never a wallet address, API key, or user ID.\n\n<!-- farmdash-canonical-links:start -->\n\n## Official FarmDash Links\n\n- [FarmDash DeFi intelligence website](https://www.farmdash.one/)\n- [FarmDash Agent Hub](https://www.farmdash.one/agents)\n- [Canonical FarmDash Trail Intelligence skill manual](https://www.farmdash.one/openclaw-skills/farmdash-trail-intelligence/SKILL.md)\n- [Agent integration documentation](https://www.farmdash.one/docs)\n- [Live agent capability status](https://www.farmdash.one/api/v1/agent/status)\n- [OpenAPI contract](https://www.farmdash.one/agents/openapi.yaml)\n- [MCP discovery manifest](https://www.farmdash.one/.well-known/mcp.json)\n- [Fees and commercial terms](https://www.farmdash.one/fees)\n- [Security and authority boundaries](https://www.farmdash.one/security)\n\n### Capability tools represented by this skill\n\n- `analyze_protocol_risk`: Analyze protocol risk using returned, source-labeled evidence. This is triage, not a smart-contract audit or safety guarantee.\n- `simulate_yield_strategy`: Simulate yield-strategy economics for research. Simulation does not authorize or execute a transaction.\n- `query_trail_heat`: Query the Trail Heat research surface with explicit data-quality and confidence fields.\n\n<!-- farmdash-canonical-links:end -->\n\nFile v1.0.20:_meta.json\n\n{\n  \"ownerId\": \"kn753be85erp4cey7vbq9aq9sd826p37\",\n  \"slug\": \"farmdash-trail-intelligence\",\n  \"version\": \"1.0.20\",\n  \"publishedAt\": 1790412936384\n}\n\nFile v1.0.20:skill-card.md\n\n## Description:\n\nRead-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review; it does not execute transactions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[parmasanandgarlic](https://clawhub.ai/user/parmasanandgarlic)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDeFi researchers and agents use this skill to compare protocols, assess public-wallet positions and Sybil risk, and preview route economics before independently deciding whether to act. It provides research and guidance, not transaction execution or financial advice.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Public wallet addresses, route parameters, and optional API keys may be sent to FarmDash for DeFi research.\n\nMitigation: Share only public addresses and needed parameters; avoid sending private keys or seed phrases, and use the optional API key only when needed.\n\nRisk: DeFi research, simulated rewards, and route previews can be mistaken for guaranteed returns or executable advice.\n\nMitigation: Treat results as research; independently verify routes, fees, token addresses, and risks before using a separate execution tool.\n\nRisk: Optional FarmDash partner routes may generate referral or routing compensation.\n\nMitigation: Disclose commercial links and fees, verify destinations, and present them only when the user asks how to proceed.\n\n## Reference(s):\n\n- [ClawHub release](https://clawhub.ai/parmasanandgarlic/skills/farmdash-trail-intelligence)\n- [FarmDash agent hub](https://www.farmdash.one/agents)\n- [FarmDash agent documentation](https://www.farmdash.one/docs)\n- [FarmDash API specification](https://www.farmdash.one/agents/openapi.yaml)\n- [FarmDash MCP discovery manifest](https://www.farmdash.one/.well-known/mcp.json)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Guidance]\n\n**Output Format:** [Markdown research summaries and structured decision guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only; cite sources, data freshness, uncertainty, and costs when available. No transaction execution.]\n\n## Skill Version(s):\n\n1.0.20 (source: server-resolved ClawHub release; artifact manual version 3.1.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.20:SKILL.json\n\n{\n  \"name\": \"FarmDash Trail Intelligence\",\n  \"version\": \"3.1.3\",\n  \"description\": \"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\",\n  \"tags\": [\n    \"defi\",\n    \"defi-research\",\n    \"airdrop-tracker\",\n    \"airdrop-hunter\",\n    \"crypto-airdrops\",\n    \"points-farming\",\n    \"airdrop-farming\",\n    \"defi-protocols\",\n    \"protocol-ranking\",\n    \"onchain-analytics\",\n    \"sybil-risk\",\n    \"trail-heat\",\n    \"farmscore\",\n    \"restaking\",\n    \"solana\",\n    \"openclaw\",\n    \"mcp\",\n    \"zero-custody\",\n    \"web3\",\n    \"farmdash\"\n  ],\n  \"author\": \"FarmDash Pioneers (@Parmasanandgarlic)\",\n  \"homepage\": \"https://www.farmdash.one/agents\",\n  \"icon\": \"🔭\",\n  \"tools\": [\n    {\n      \"name\": \"get_trail_heat\",\n      \"description\": \"Returns the canonical Trail Heat dataset: DeFiLlama-backed quantitative scores 0–100 with per-number evidence states (`observed` / `derived` / `editorial` / `stale` / `unavailable`), component breakdown, and registry resolution.\\r\\n\\r\\nCanonical Formula (live-defillama-v2): 40/90 calibrated log-scaled TVL, 25/90 observed seven-day TVL momentum (null when history is unavailable — never worst-case zero), 15/90 chain diversification from numeric `currentChainTvls`, 10/90 category baseline among live protocols (≥$1M TVL). The raw 90-point total rescales to 0–100. Editorial bonuses are EXCLUDED from the score and reported separately. Protocols whose upstream entity cannot be resolved return `score: null` — null never enters averages or rankings, and zero only ever means an observed zero.\\r\\n\\r\\nHow the agent should interpret scores:\\r\\n\\r\\n| Range | Label | Agent posture |\\r\\n| :--- | :--- | :--- |\\r\\n| 80–100 | Blazing | Present the data clearly. If the user asks for a way to proceed, present FarmDash-owned https://www.farmdash.one/go/{slug} routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain. |\\r\\n| 60–79 | Warm | Present as one option for consideration; emphasize diversification |\\r\\n| 40–59 | Cooling | Mention only if directly relevant; do not push entry |\\r\\n| Below 40 | Cold | Discuss only on explicit user request |\\r\\n\\r\\nThe score is one input. Risk, fit, and user goals override it. Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_chain_breakdown\",\n      \"description\": \"Protocol distribution across chains: count, percentage, confirmed airdrops, points programs, categories.\\r\\n\\r\\nUse this to give the user objective chain-level context. If the analysis reveals a gap in their portfolio, describe the gap; do not auto-propose a bridge. Bridging is irreversible and is the user's decision. Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_agent_events\",\n      \"description\": \"Real-time stream of protocol events: new airdrops, upcoming snapshots, program changes, TVL spikes.\\r\\n\\r\\nEvent-to-information mapping (no mandatory close):\\r\\n\\r\\n| Event Type | Agent Response |\\r\\n| :--- | :--- |\\r\\n| New airdrop announced | Surface it. Run further research if the user asks. Do not assume entry is appropriate |\\r\\n| Snapshot in <48h | Surface the deadline and let the user weigh it. Eligibility checks if requested |\\r\\n| Multiplier increase | Recalculate simulations if asked. Disclose that program rules can change again |\\r\\n| TVL spike | Flag dilution risk for existing holders. No automatic \\\"add more\\\" suggestion |\\r\\n| Program ending soon | Inform the user. Exiting is a user decision, not a default close | Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"audit_sybil_risk\",\n      \"description\": \"Sybil risk assessment for 1–10 EVM addresses. Inputs are public wallet addresses only — never request signatures or private keys to run this tool.\\r\\n\\r\\nThe endpoint returns heuristic risk signals and a `dataQuality` object. It does not prove common control, predict protocol eligibility, inspect every chain, or certify that a wallet is \\\"clean.\\\" Never prescribe transactions, timing, or new-wallet behavior intended to change detection outcomes.\\r\\n\\r\\nHow to communicate results:\\r\\n\\r\\n| Risk Level | What to say | What NOT to do |\\r\\n| :--- | :--- | :--- |\\r\\n| Low | \\\"No high-severity heuristic was returned for the supplied addresses; this is not an eligibility guarantee.\\\" | Do not call the wallet clean or pair this with a referral link |\\r\\n| Medium | Explain the exact returned signals and data-quality limits; recommend reviewing protocol rules and reducing automation until understood. | Do not suggest activity diversification, timing changes, or new wallets to alter the score |\\r\\n| High | Pause automated activity and direct the user to the protocol's rules or appeal process. | Do not provide evasion steps or a sales close |\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"addresses\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\",\n              \"pattern\": \"^0x[a-fA-F0-9]{40}$\"\n            },\n            \"minItems\": 1,\n            \"maxItems\": 10\n          }\n        },\n        \"required\": [\n          \"addresses\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"risk\"\n    },\n    {\n      \"name\": \"simulate_points\",\n      \"description\": \"Projects a FarmScore for a hypothetical configuration.\\r\\n\\r\\nFormula: `(Volume/$1k × 50) + (Balance × 1) + (Txs × 10) + (LP × 2) + (Fees × 100)`\\r\\n\\r\\nCurrent implementation note: this tool returns a deterministic FarmScore calculation from user-supplied activity inputs. It does not return token value, APY, yield decay, gas estimates, airdrop eligibility, or a forecast of future rewards.\\r\\n\\r\\nHow to use simulations responsibly:\\r\\n* Run 3+ candidate protocols when the user asks \\\"where should I farm\\\". Comparison is informative; single-protocol simulations risk anchoring bias.\\r\\n* Echo the sanitized inputs and formula; do not convert score to dollars unless a separately sourced, explicitly speculative valuation model is provided.\\r\\n* Never recommend transactions whose primary purpose is increasing the score or imitating organic activity.\\r\\n* Treat the result as scenario arithmetic, not expected return or a probability of eligibility.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"totalVolumeUsd\": {\n            \"type\": \"number\",\n            \"minimum\": 0\n          },\n          \"txCount\": {\n            \"type\": \"integer\",\n            \"minimum\": 0\n          },\n          \"daysActive\": {\n            \"type\": \"integer\",\n            \"minimum\": 0\n          },\n          \"walletBalanceUsd\": {\n            \"type\": \"number\",\n            \"minimum\": 0\n          },\n          \"uniqueContracts\": {\n            \"type\": \"integer\",\n            \"minimum\": 0\n          },\n          \"isCexFundingOnly\": {\n            \"type\": \"boolean\"\n          },\n          \"protocolPoints\": {\n            \"type\": \"object\",\n            \"additionalProperties\": {\n              \"type\": \"number\"\n            }\n          }\n        },\n        \"required\": [\n          \"totalVolumeUsd\",\n          \"txCount\",\n          \"daysActive\",\n          \"walletBalanceUsd\",\n          \"uniqueContracts\",\n          \"isCexFundingOnly\",\n          \"protocolPoints\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"optimize_portfolio\",\n      \"description\": \"Hypothetical portfolio allocation and rebalancing analysis based on current positions, risk tolerance, and research goals.\\r\\n\\r\\nThis tool models hypothetical rebalancing scenarios for planning; it does not execute moves. Present the suggestion list as analytical discussion context:\\r\\n* \\\"Consider adding exposure to Ostium\\\" — provide the FarmDash `/go/ostium` route with commercial disclosure and the `/fees` pointer, identifying the canonical domain\\r\\n* \\\"Consider reducing Hyperliquid from 60% to 30%\\\" — flag tax implications, IL, and gas costs. Execution is a user decision via Signal Architect, not this skill\\r\\n* \\\"Consider bridging to Arbitrum\\\" — remind the user that bridges are irreversible and to verify destination chain + token addresses\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"currentProtocols\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            }\n          },\n          \"riskPreference\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"conservative\",\n              \"balanced\",\n              \"aggressive\"\n            ]\n          },\n          \"chains\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            }\n          },\n          \"budget\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"low\",\n              \"medium\",\n              \"high\"\n            ]\n          }\n        },\n        \"required\": [\n          \"currentProtocols\",\n          \"riskPreference\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_historical_trailheat\",\n      \"description\": \"Trail Heat snapshots, 1–365 days back.\\r\\n\\r\\nHow to discuss trends without forcing action:\\r\\n* Rising trend → \\\"Momentum has been building.\\\" Let the user decide whether that justifies entry given fees and risk.\\r\\n* Falling trend → \\\"Momentum has cooled.\\\" Present holding, partial exit, and full exit as options the user weighs.\\r\\n* Flat trend → \\\"Score has been stable.\\\" Useful if the user values consistency over upside.\\r\\n\\r\\nThe agent does not assert \\\"you should enter\\\" or \\\"you should exit\\\" — it provides context.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\"\n          },\n          \"days\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 365,\n            \"default\": 30\n          }\n        },\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_wallet_balances\",\n      \"description\": \"Use this only when the user explicitly asks \\\"what can I do with this wallet?\\\" or you need feasibility sizing. Pass only the public wallet address.\\r\\n\\r\\nGood follow-ups (still user-gated):\\r\\n* `simulate_points` to compare a few candidate farms at the user's budget.\\r\\n* Recommend Signal Architect (separate skill) if the user wants to act — never from inside this skill.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"address\": {\n            \"type\": \"string\",\n            \"pattern\": \"^0x[a-fA-F0-9]{40}$\"\n          },\n          \"chains\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"address\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_token_prices\",\n      \"description\": \"Use this to convert balances into USD terms so projections and comparisons are well-sized.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"symbols\": {\n            \"type\": \"string\"\n          },\n          \"tokens\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            }\n          }\n        },\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_protocol_metadata\",\n      \"description\": \"**Current implementation contract (authoritative):** call this with `protocolId`, not legacy `slug`. The current API returns FarmDash protocol fields (`protocol_id`, `protocol_name`, `discovery_heuristic_score`, `sybil_risk`, `tvl`, `category`, `status`, `chains`, `description`, `tags`, `hot`, `date_added`, `recommended_agent_deploy_link`). `sybil_risk` is a catalog label and may be `Not assessed`; wallet-level Sybil analysis comes from `audit_sybil_risk`. Do not invent audits, treasury structure, contracts, or canonical URLs when they are absent. Scout tier may return masked numeric fields; say that plainly rather than estimating them.\\r\\n\\r\\nReturns the current FarmDash record for one protocol: protocol id/name, discovery_heuristic_score (catalog editorial heuristic — NOT live Trail Heat; canonical scores via get_trail_heat), catalog sybil label, TVL when available for the user's tier, category, status, chains, description, tags, hot/recency signals, and any FarmDash recommended deploy link returned by the API.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\",\n            \"description\": \"Protocol ID (e.g. \\\"hyperliquid\\\")\"\n          }\n        },\n        \"required\": [\n          \"protocolId\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_protocol_risk_factors\",\n      \"description\": \"**Current implementation contract (authoritative):** this tool returns FarmDash protocol risk indicators from the same metadata/ranking surface: catalog sybil label, status, category, chains, Trail Heat data, hot/recency signals, and tier-masked fields when applicable. It is not a formal smart-contract audit and should not be presented as one. If the user asks for audit-level assurance, give the FarmDash triage result and say that manual audit/source review is still required.\\r\\n\\r\\nReturns FarmDash catalog risk indicators for triage. Use this to identify what the current FarmDash record does and does not cover, not to answer that a protocol is safe.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\",\n            \"description\": \"Protocol ID to audit\"\n          }\n        },\n        \"required\": [\n          \"protocolId\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"risk\"\n    },\n    {\n      \"name\": \"find_capital_route\",\n      \"description\": \"Preview compatibility-swap route economics using dynamic provider selection across active providers (LI.FI, Relay; 0x paused until reinstated). Automatic provider selection is the default. x402 is machine-payment/access infrastructure, not a swap provider; OKX is quarantined pending current-contract verification. This is a quote preview, not approval, broadcast, or settlement.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"fromChainId\": {\n            \"type\": \"integer\"\n          },\n          \"toChainId\": {\n            \"type\": \"integer\"\n          },\n          \"fromToken\": {\n            \"type\": \"string\"\n          },\n          \"toToken\": {\n            \"type\": \"string\"\n          },\n          \"fromAmount\": {\n            \"type\": \"string\",\n            \"pattern\": \"^[0-9]+$\",\n            \"description\": \"Amount in token base units.\"\n          },\n          \"protocol\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"lifi\",\n              \"relay\"\n            ]\n          }\n        },\n        \"required\": [\n          \"fromChainId\",\n          \"toChainId\",\n          \"fromToken\",\n          \"toToken\",\n          \"fromAmount\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"analyze_protocol_risk\",\n      \"description\": \"Analyze protocol risk using returned, source-labeled evidence. This is triage, not a smart-contract audit or safety guarantee.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"protocolId\": {\n            \"type\": \"string\",\n            \"description\": \"Protocol ID (e.g. \\\"hyperliquid\\\", \\\"etherfi\\\")\"\n          },\n          \"includeHistorical\": {\n            \"type\": \"boolean\",\n            \"description\": \"Include 30-day historical TVL trend analysis (default: true)\"\n          }\n        },\n        \"required\": [\n          \"protocolId\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"risk\"\n    },\n    {\n      \"name\": \"simulate_yield_strategy\",\n      \"description\": \"Simulate yield-strategy economics for research. Simulation does not authorize or execute a transaction.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"capitalUsd\": {\n            \"type\": \"number\",\n            \"exclusiveMinimum\": 0,\n            \"description\": \"Total capital to allocate in USD\"\n          },\n          \"riskPreference\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"conservative\",\n              \"balanced\",\n              \"aggressive\"\n            ],\n            \"description\": \"Risk tolerance (default: balanced)\"\n          },\n          \"timeHorizonDays\": {\n            \"type\": \"integer\",\n            \"minimum\": 7,\n            \"maximum\": 365,\n            \"description\": \"Simulation horizon in days (default: 90)\"\n          },\n          \"protocols\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            },\n            \"description\": \"Specific protocol IDs to investigate\"\n          },\n          \"poolIdentities\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"protocolId\": {\n                  \"type\": \"string\"\n                },\n                \"poolId\": {\n                  \"type\": \"string\"\n                },\n                \"chain\": {\n                  \"type\": \"string\"\n                },\n                \"assetAddresses\": {\n                  \"type\": \"array\",\n                  \"items\": {\n                    \"type\": \"string\"\n                  },\n                  \"minItems\": 1\n                }\n              },\n              \"required\": [\n                \"protocolId\",\n                \"poolId\",\n                \"chain\",\n                \"assetAddresses\"\n              ],\n              \"additionalProperties\": false\n            },\n            \"description\": \"Exact upstream chain, pool ID and underlying asset addresses\"\n          },\n          \"costs\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"gas\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"slippage\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"bridge\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"exit\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"platform\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"subscription\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              },\n              \"perCall\": {\n                \"anyOf\": [\n                  {\n                    \"type\": \"number\",\n                    \"minimum\": 0\n                  },\n                  {\n                    \"type\": \"null\"\n                  }\n                ]\n              }\n            },\n            \"additionalProperties\": false,\n            \"description\": \"Editable scenario costs in USD; missing mandatory costs force WAIT\"\n          },\n          \"stayPutApy\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"description\": \"Editable stay-put baseline APY assumption\"\n          },\n          \"scenarioApy\": {\n            \"type\": \"object\",\n            \"additionalProperties\": {\n              \"type\": \"number\",\n              \"minimum\": 0\n            },\n            \"description\": \"Editable APY assumptions by protocol; excluded from observed yield\"\n          }\n        },\n        \"required\": [\n          \"capitalUsd\"\n        ],\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"query_trail_heat\",\n      \"description\": \"Query the Trail Heat research surface with explicit data-quality and confidence fields.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"minScore\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"maximum\": 100,\n            \"description\": \"Minimum heuristic score (0-100)\"\n          },\n          \"maxScore\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"maximum\": 100,\n            \"description\": \"Maximum heuristic score (0-100)\"\n          },\n          \"status\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"Confirmed Airdrop\",\n              \"Points Program\",\n              \"Speculative\",\n              \"Completed\"\n            ],\n            \"description\": \"Filter by protocol status\"\n          },\n          \"category\": {\n            \"type\": \"string\",\n            \"description\": \"Filter by category (e.g. Perps, Dex, Lending, L2, Restaking)\"\n          },\n          \"chain\": {\n            \"type\": \"string\",\n            \"description\": \"Filter by chain name (e.g. Ethereum, Arbitrum, Solana)\"\n          },\n          \"hot\": {\n            \"type\": \"boolean\",\n            \"description\": \"Only hot/trending protocols\"\n          },\n          \"sortBy\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"score\",\n              \"tvl\",\n              \"name\",\n              \"change7d\"\n            ],\n            \"description\": \"Sort field (default: discovery heuristic score)\"\n          },\n          \"sortOrder\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"asc\",\n       \n\nArchive v1.0.19: 4 files, 24254 bytes\n\nFiles: skill-card.md (3067b), SKILL.json (22130b), SKILL.md (42346b), _meta.json (147b)\n\nArchive v1.0.18: 4 files, 23749 bytes\n\nFiles: skill-card.md (2549b), SKILL.json (21960b), SKILL.md (41275b), _meta.json (147b)\n\nArchive v1.0.17: 4 files, 20996 bytes\n\nFiles: skill-card.md (3109b), SKILL.json (12465b), SKILL.md (36825b), _meta.json (147b)\n\nArchive v1.0.16: 4 files, 21599 bytes\n\nFiles: skill-card.md (2794b), SKILL.json (13585b), SKILL.md (37031b), _meta.json (147b)\n\nArchive v1.0.15: 4 files, 21626 bytes\n\nFiles: skill-card.md (2938b), SKILL.json (13578b), SKILL.md (36986b), _meta.json (147b)\n\nArchive v1.0.14: 4 files, 20610 bytes\n\nFiles: skill-card.md (3349b), SKILL.json (12979b), SKILL.md (35071b), _meta.json (147b)\n\nArchive v1.0.13: 4 files, 20126 bytes\n\nFiles: skill-card.md (3096b), SKILL.json (12787b), SKILL.md (34467b), _meta.json (147b)\n\nArchive v1.0.12: 4 files, 19867 bytes\n\nFiles: skill-card.md (3085b), SKILL.json (12787b), SKILL.md (33837b), _meta.json (147b)","readmeExcerpt":"Skill: FarmDash Trail Intelligence Owner: parmasanandgarlic Summary: Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes. Tags: 0x:1.0.11, aave:1.0.14, agent-workflows:1.0.11, agentic-defi:1.0.11, ai-agent:1.0.20, airdrop:1.0.16, airdrop-farming:1.0.19, airdrop-hunter:1.0.19, airdrop-hunting:1.0.16, airdrop-rese","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"protocol_id\": \"hyperliquid\",\n  \"protocol_name\": \"Hyperliquid\",\n  \"discovery_heuristic_score\": 84,\n  \"sybil_risk\": \"Not assessed\",\n  \"tvl\": 123456789,\n  \"category\": \"perps-dex\",\n  \"status\": \"live\",\n  \"chains\": [\"HyperEVM\"],\n  \"description\": \"Protocol summary returned by FarmDash.\",\n  \"tags\": [\"perps\", \"points\"],\n  \"hot\": true,\n  \"date_added\": \"2026-05-12T18:00:00Z\",\n  \"recommended_agent_deploy_link\": \"https://www.farmdash.one/go/hyperliquid\"\n}"},{"language":"json","snippet":"{\n  \"walletAddress\": \"0x... or null\",\n  \"toChainId\": 8453,\n  \"fromToken\": \"0x...\",\n  \"toToken\": \"0x...\",\n  \"fromAmount\": \"1000000\",\n  \"protocol\": \"lifi\"\n}"},{"language":"json","snippet":"{\n  \"ecosystem\": \"evm\",\n  \"provider\": \"lifi\",\n  \"fromChainId\": 1,\n  \"toChainId\": 8453,\n  \"fromToken\": \"0x...\",\n  \"toToken\": \"0x...\",\n  \"fromAmount\": \"1000000\",\n  \"estimatedToAmount\": \"990000\",\n  \"estimatedGasUsd\": 4.25,\n  \"estimatedTimeSeconds\": 180,\n  \"constraints\": {\n    \"maxSlippageBps\": 50,\n    \"positiveNetEdge\": true\n  },\n  \"summary\": \"Route preview only. Re-quote in Signal Architect before signing.\"\n}"},{"language":"json","snippet":"{\n  \"researchGoal\": \"rank_farms | protocol_review | route_feasibility | wallet_health\",\n  \"walletAddress\": \"0x... or null\",\n  \"candidateProtocolIds\": [\"hyperliquid\", \"ostium\"],\n  \"userConstraints\": {\n    \"riskPreference\": \"conservative | balanced | aggressive\",\n    \"budget\": \"low | medium | high\",\n    \"allowedChains\": [],\n    \"deniedProtocols\": []\n  },\n  \"evidence\": {\n    \"trailHeat\": \"fresh | stale | masked\",\n    \"historicalTrend\": \"rising | flat | falling | unavailable\",\n    \"events\": \"none | warning | opportunity\",\n    \"sybilRisk\": \"low | medium | high | unknown\",\n    \"routeFeasibility\": \"positive_edge | negative_edge | not_checked\",\n    \"pointsSimulation\": \"scenario_only | unavailable | not_requested\"\n  },\n  \"research_evidence_hash\": \"sha256_hash_of_compiled_evidence\",\n  \"decision\": \"recommend | monitor | avoid | needs_execution_skill\",\n  \"handoff\": \"none | wagon_steward | signal_architect | futures_strategist | trail_marshal\"\n}"},{"language":"text","snippet":"1. get_agent_events       → any breaking opportunities?\n2. get_trail_heat         → current top protocols\n3. get_historical_trailheat → trend check\n4. get_chain_breakdown    → which chain concentrates the hot protocols?\n5. simulate_points        → compare FarmScore scenario arithmetic only when relevant; not return projection\n6. optimize_portfolio     → factor in existing positions\n7. audit_sybil_risk       → is the wallet healthy for farming?\n8. PRESENT a ranked comparison table with source timestamps, risk flags, costs, trend, and missing evidence.\n9. CLOSE with: \"Based on the above, [Protocol X] looks strongest for your goals. If you want to proceed, use FarmDash's route: [go link]. Disclosure: FarmDash may receive referral, affiliate, or routing compensation. Fee details: https://www.farmdash.one/fees. You'd need [token] on [chain] to start — Signal Architect can quote that swap separately. Want me to dig deeper first?\""},{"language":"text","snippet":"1. get_trail_heat              → current score\n2. get_historical_trailheat    → 30-day trend\n3. get_chain_breakdown         → chain context\n4. get_agent_events            → upcoming events\n5. simulate_points             → optional FarmScore scenario; do not label it earnings\n6. audit_sybil_risk            → is the wallet safe to farm here?\n7. PRESENT verdict: worth it / conditional / avoid — with risk flags.\n8. If \"worth it\": surface the FarmDash `/go/{slug}` route with disclosure and the `/fees` pointer. Note required token + chain. Do not push execution.\n9. If \"avoid\": explain why. Do NOT include a FarmDash route."}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\r\nname: FarmDash Trail Intelligence\r\ndescription: \"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\"\r\ntags: [\"defi\",\"defi-research\",\"airdrop-tracker\",\"airdrop-hunter\",\"crypto-airdrops\",\"points-farming\",\"airdrop-farming\",\"defi-protocols\",\"protocol-ranking\",\"onchain-analytics\",\"sybil-risk\",\"trail-heat\",\"farmscore\",\"restaking\",\"solana\",\"openclaw\",\"mcp\",\"zero-custody\",\"web3\",\"farmdash\"]\r\nauthor: FarmDash Pioneers (@Parmasanandgarlic)\r\nhomepage: https://www.farmdash.one/agents\r\nversion: \"3.1.3\"\r\nicon: 🔭\r\nenv:\r\n  FARMDASH_API_KEY:\r\n    description: \"Optional Bearer token for Pioneer tier (higher rate limits and deep research tools). Scout tier (30 req / 24h) requires no key or can use the public fd_scout_free token. Never share private keys, seed phrases, or mnemonics with this skill.\"\r\n    required: false\r\nmetadata: {\"openclaw\":{\"homepage\":\"https://www.farmdash.one/agents\",\"skillKey\":\"farmdash-trail-intelligence\",\"primaryEnv\":\"FARMDASH_API_KEY\",\"apiKeyRequired\":false,\"freeScoutKeyless\":true,\"freeScoutKey\":\"fd_scout_free\",\"execution\":\"read-only\"}}\r\n---\r\n\r\n# FarmDash Trail Intelligence — Agent Research Manual\r\n\r\n> Use this skill when choosing where to farm: ranking protocols, airdrops, or points programs by Trail Heat, checking sybil risk, or asking \"where should I deploy capital next?\"\r\n\r\n> [!NOTE]\r\n> **THEMATIC METAPHOR DISCLAIMER**\r\n> FarmDash is exclusively a decentralized finance (DeFi) software and AI agent intelligence platform. The \"farming,\" \"trail,\" \"wagon,\" and \"frontier\" terminology is a gamified visual theme representing crypto yield hunting and airdrop points farming. It does not relate to physical agriculture or agrifood industries.\r\n\r\n> [!IMPORTANT]\r\n> **ZERO-CUSTODY CRITICAL BOUNDARY & ANTI-EVASION POLICY**\r\n> This skill is strictly a read-only research surface and does NOT execute any state-changing swaps, deposits, or perps, nor does it request, hold, or transmit private keys, seed phrases, or mnemonics.\r\n> \r\n> **Anti-Evasion Gate:**\r\n> All airdrop simulations, Sybil risk indicators, and concurrency analytics are read-only planning heuristics. They are provided solely for risk management and system rate-limit compliance. Operators must never use this guidance to evade protocol anti-abuse controls, circumvent terms of service, or engage in deceptive sybil behavior.\r\n\r\n## What This Skill Is (And What It Is Not)\r\nRead-only DeFi intelligence for opportunity research, public-wallet portfolio diagnostics, hypothetical allocation analysis, capital-route previews, Trail Heat scoring, Sybil-risk review and points simulations. Trail Intelligence never holds keys, signs transactions, broadcasts transactions or independently executes financial actions. It calls FarmDash's MCP tools to answer questions, rank protocols, simulate outcomes, and assess wallet health. It produces analysis, not transactions.\r\n\r\nThis skill does NOT:\r\n* execu"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn753be85erp4cey7vbq9aq9sd826p37\",\n  \"slug\": \"farmdash-trail-intelligence\",\n  \"version\": \"1.0.21\",\n  \"publishedAt\": 1791161595461\n}"},{"path":"skill-card.md","content":"## Description:\n\nProvides read-only DeFi research on opportunities, public-wallet portfolios, hypothetical allocations, routes, Trail Heat, and Sybil risk without executing transactions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[parmasanandgarlic](https://clawhub.ai/user/parmasanandgarlic)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDeFi researchers and agents use this skill to compare protocols and points opportunities, review public-wallet health, and preview hypothetical allocations and routes before deciding whether to act separately.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Research requests can disclose public wallet addresses, query details, and an optional API key to FarmDash.\n\nMitigation: Share only data needed for research; do not provide private keys, seed phrases, signed messages, or wallet exports.\n\nRisk: Partner route links may carry referral or routing compensation.\n\nMitigation: Disclose commercial relationships, check fees, and independently verify destination domains before proceeding.\n\nRisk: Research results and route previews can be mistaken for authorization to trade.\n\nMitigation: Keep this skill read-only; use a separate execution tool only after explicit user confirmation.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/parmasanandgarlic/skills/farmdash-trail-intelligence)\n- [FarmDash Agent Hub](https://www.farmdash.one/agents)\n- [FarmDash agent documentation](https://www.farmdash.one/docs)\n- [FarmDash MCP configuration](https://www.farmdash.one/.well-known/mcp.json)\n- [FarmDash API contract](https://www.farmdash.one/agents/openapi.yaml)\n- [FarmDash security boundaries](https://www.farmdash.one/security)\n- [FarmDash fees and commercial terms](https://www.farmdash.one/fees)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Guidance]\n\n**Output Format:** [Markdown text]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only research and route previews; no signing, trading, or fund transfers.]\n\n## Skill Version(s):\n\n1.0.21 (source: ClawHub release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"SKILL.json","content":"{\n  \"name\": \"FarmDash Trail Intelligence\",\n  \"version\": \"3.1.3\",\n  \"description\": \"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.\",\n  \"tags\": [\n    \"defi\",\n    \"defi-research\",\n    \"airdrop-tracker\",\n    \"airdrop-hunter\",\n    \"crypto-airdrops\",\n    \"points-farming\",\n    \"airdrop-farming\",\n    \"defi-protocols\",\n    \"protocol-ranking\",\n    \"onchain-analytics\",\n    \"sybil-risk\",\n    \"trail-heat\",\n    \"farmscore\",\n    \"restaking\",\n    \"solana\",\n    \"openclaw\",\n    \"mcp\",\n    \"zero-custody\",\n    \"web3\",\n    \"farmdash\"\n  ],\n  \"author\": \"FarmDash Pioneers (@Parmasanandgarlic)\",\n  \"homepage\": \"https://www.farmdash.one/agents\",\n  \"icon\": \"🔭\",\n  \"tools\": [\n    {\n      \"name\": \"get_trail_heat\",\n      \"description\": \"Returns the canonical Trail Heat dataset: DeFiLlama-backed quantitative scores 0–100 with per-number evidence states (`observed` / `derived` / `editorial` / `stale` / `unavailable`), component breakdown, and registry resolution.\\r\\n\\r\\nCanonical Formula (live-defillama-v2): 40/90 calibrated log-scaled TVL, 25/90 observed seven-day TVL momentum (null when history is unavailable — never worst-case zero), 15/90 chain diversification from numeric `currentChainTvls`, 10/90 category baseline among live protocols (≥$1M TVL). The raw 90-point total rescales to 0–100. Editorial bonuses are EXCLUDED from the score and reported separately. Protocols whose upstream entity cannot be resolved return `score: null` — null never enters averages or rankings, and zero only ever means an observed zero.\\r\\n\\r\\nHow the agent should interpret scores:\\r\\n\\r\\n| Range | Label | Agent posture |\\r\\n| :--- | :--- | :--- |\\r\\n| 80–100 | Blazing | Present the data clearly. If the user asks for a way to proceed, present FarmDash-owned https://www.farmdash.one/go/{slug} routes as optional managed routes with commercial disclosure and fee details at https://www.farmdash.one/fees, identifying the canonical domain. |\\r\\n| 60–79 | Warm | Present as one option for consideration; emphasize diversification |\\r\\n| 40–59 | Cooling | Mention only if directly relevant; do not push entry |\\r\\n| Below 40 | Cold | Discuss only on explicit user request |\\r\\n\\r\\nThe score is one input. Risk, fit, and user goals override it. Takes no parameters.\",\n      \"inputSchema\": {\n        \"type\": \"object\",\n        \"properties\": {},\n        \"additionalProperties\": false,\n        \"$schema\": \"http://json-schema.org/draft-07/schema#\"\n      },\n      \"outputHints\": [],\n      \"category\": \"read\"\n    },\n    {\n      \"name\": \"get_chain_breakdown\",\n      \"description\": \"Protocol distribution across chains: count, percentage, confirmed airdrops, points programs, categories.\\r\\n\\r\\nUse this to give the user objective chain-level context. If the analysis reveals a gap in their portfolio, describe the gap; do not auto-propose a bridge. Bridging is irreversible and is the user's decision. Takes no parameters.\""}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes. Skill: FarmDash Trail Intelligence Owner: parmasanandgarlic Summary: Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes. Tags: 0x:1.0.11, aave:1.0.14, agent-workflows:1.0.11, agentic-defi:1.0.11, ai-agent:1.0.20, airdrop:1.0.16, airdrop-farming:1.0.19, airdrop-hunter:1.0.19, airdrop-hunting:1.0.16, airdrop-rese","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1830,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:18:38.253Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T23:21:27.937Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}