{"id":"0e2e9475-5ee0-4601-a489-ed2bf82b7580","entityType":"agent","slug":"clawhub-teahann-stock-picker-orchestrator","name":"Stock Picker Orchestrator","canonicalUrl":"https://www.xpersona.co/agent/clawhub-teahann-stock-picker-orchestrator","canonicalPath":"/agent/clawhub-teahann-stock-picker-orchestrator","generatedAt":"2026-10-10T03:02:34.766Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T18:27:50.076Z","emptyReason":null},"description":"Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r... Skill: Stock Picker Orchestrator Owner: teahann Summary: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-05-22T00:21:43.229Z | user Update Vietnam institutional stock skill system with D1 governance, trade decision policy, and harness agent guide. v1.0.2 |","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.1K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s172d4r9d0h6bvvd3mpq517yrn861np5:stock-picker-orchestrator","sourceUrl":"https://clawhub.ai/teahann/stock-picker-orchestrator","homepage":"https://clawhub.ai/teahann/skills/stock-picker-orchestrator","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/teahann/stock-picker-orchestrator","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/teahann/skills/stock-picker-orchestrator","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":67,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:27:50.076Z","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":"2026-10-09T18:27:50.076Z","emptyReason":null},"stars":null,"forks":null,"downloads":2132,"packageName":null,"latestVersion":"1.0.3","tractionLabel":"2.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:27:50.076Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T18:27:50.076Z","lastCrawledAt":"2026-10-09T18:27:50.076Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T18:27:50.076Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.3","createdAt":"2026-05-22T00:21:43.229Z","changelog":"Update Vietnam institutional stock skill system with D1 governance, trade decision policy, and harness agent guide.","fileCount":4,"zipByteSize":6149},{"version":"1.0.2","createdAt":"2026-02-24T15:58:21.311Z","changelog":"**Expanded portfolio risk management and governance in orchestration logic** - Added `portfolio-risk-manager` as a required skill dependency. - Enhanced the \"Portfolio Refresh\" workflow to include running risk manager for IPS mini, position sizing, and ticker-level triggers. - Added rule: when user provides holdings/watchlist, only propose drafts—do not self-modify. - Updated governance section to clarify single source of truth behavior for user holdings. - Other clarifications to ensure risk controls and output trustworthiness.","fileCount":3,"zipByteSize":4206},{"version":"1.0.1","createdAt":"2026-02-23T10:14:45.193Z","changelog":"**Expanded documentation and scope note, plus added compatibility section and trigger examples.** - Clarified that this skill coordinates other skills and does not replace their domain logic. - Added a new compatibility section specifying required dependencies in the workspace. - Reorganized workflow into an explicit 7-step execution process. - Included new trigger example queries for clarity. - No changes to core orchestration logic or routing policies.","fileCount":3,"zipByteSize":4017},{"version":"1.0.0","createdAt":"2026-02-23T09:03:38.853Z","changelog":"- Initial release of the Stock Picker Orchestrator skill. - Supports end-to-end stock analysis by selecting and sequencing relevant data, macro, news, and valuation skills. - Enforces API and news data budgets based on user tier and preset risk levels. - Classifies user intent into distinct modes (deep dive, screening, macro/news investigation, portfolio refresh) and orchestrates appropriate analysis pipelines. - Standardizes outputs with clear sections: data fetched, pipeline choice, assumptions, results, confidence/gaps, risk flags, and next steps. - Applies consistent confidence scoring, conflict resolution, and governance to ensure transparent, reproducible recommendations.","fileCount":3,"zipByteSize":3670}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s172d4r9d0h6bvvd3mpq517yrn861np5:stock-picker-orchestrator","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-teahann-stock-picker-orchestrator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T03:02:34.765Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-teahann-stock-picker-orchestrator/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":"2026-10-09T18:27:50.076Z","emptyReason":null},"readme":"Skill: Stock Picker Orchestrator\n\nOwner: teahann\n\nSummary: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r...\n\nTags: latest:1.0.3\n\nVersion history:\n\nv1.0.3 | 2026-05-22T00:21:43.229Z | user\n\nUpdate Vietnam institutional stock skill system with D1 governance, trade decision policy, and harness agent guide.\n\nv1.0.2 | 2026-02-24T15:58:21.311Z | auto\n\n**Expanded portfolio risk management and governance in orchestration logic**\n\n- Added `portfolio-risk-manager` as a required skill dependency.\n- Enhanced the \"Portfolio Refresh\" workflow to include running risk manager for IPS mini, position sizing, and ticker-level triggers.\n- Added rule: when user provides holdings/watchlist, only propose drafts—do not self-modify.\n- Updated governance section to clarify single source of truth behavior for user holdings.\n- Other clarifications to ensure risk controls and output trustworthiness.\n\nv1.0.1 | 2026-02-23T10:14:45.193Z | auto\n\n**Expanded documentation and scope note, plus added compatibility section and trigger examples.**\n\n- Clarified that this skill coordinates other skills and does not replace their domain logic.\n- Added a new compatibility section specifying required dependencies in the workspace.\n- Reorganized workflow into an explicit 7-step execution process.\n- Included new trigger example queries for clarity.\n- No changes to core orchestration logic or routing policies.\n\nv1.0.0 | 2026-02-23T09:03:38.853Z | auto\n\n- Initial release of the Stock Picker Orchestrator skill.\n- Supports end-to-end stock analysis by selecting and sequencing relevant data, macro, news, and valuation skills.\n- Enforces API and news data budgets based on user tier and preset risk levels.\n- Classifies user intent into distinct modes (deep dive, screening, macro/news investigation, portfolio refresh) and orchestrates appropriate analysis pipelines.\n- Standardizes outputs with clear sections: data fetched, pipeline choice, assumptions, results, confidence/gaps, risk flags, and next steps.\n- Applies consistent confidence scoring, conflict resolution, and governance to ensure transparent, reproducible recommendations.\n\nArchive index:\n\nArchive v1.0.3: 4 files, 6149 bytes\n\nFiles: _meta.json (144b), agents/openai.yaml (319b), skill-card.md (2308b), SKILL.md (9867b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: stock-picker-orchestrator\ndescription: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and risk skills under explicit budget controls.\ncompatibility: Requires dependent skills (`vnstock-free-expert`, macro/news monitors, `strategy-backtester`, `earnings-quality-reviewer`, `equity-valuation-framework`, `portfolio-analytics`, and `portfolio-risk-manager`) to be available in the same workspace.\nmetadata: {\"openclaw\":{\"emoji\":\"🧩\"}}\n---\n\n# Stock Picker Orchestrator\n\nUse this skill to coordinate the full analysis system from user intent to final recommendation framing.\n\n## Purpose\n- Convert user request into the right analysis pipeline.\n- Control budget: vnstock API calls, breadth of news scraping, depth of valuation work.\n- Produce transparent outputs: what was fetched, assumptions, confidence, gaps.\n- Scope boundary: this skill coordinates other skills and does not replace their domain-specific logic.\n\n## Skill graph (preferred dependencies)\n1. `vnstock-free-expert` for structured market/fundamental data.\n2. `nso-macro-monitor` for Vietnam macro snapshot.\n3. `us-macro-news-monitor` for global macro spillover signals.\n4. `vn-market-news-monitor` for domestic market narrative.\n5. `strategy-backtester` for historical ranking/strategy validation.\n6. `earnings-quality-reviewer` for earnings quality before valuation conviction.\n7. `equity-valuation-framework` for decision-grade valuation and report standard.\n8. `portfolio-analytics` for portfolio risk metrics before sizing/rebalance.\n9. `portfolio-risk-manager` for IPS mini + position sizing + risk triggers (no-margin).\n10. `trade-decision-policy` for `BUY`, `ADD`, `HOLD`, `TRIM`, `EXIT`, target weights, and action drafts.\n11. `institutional-governance` for D1 approvals, compliance checks, audit logs, and approved target portfolio state.\n\n## Trigger conditions\n- \"Find best stock(s)\"\n- \"Screen this sector\"\n- \"Analyze ticker X deeply\"\n- \"How do macro/news affect these stocks\"\n- \"Value this stock like a professional\"\n\n## First step: intent classification\nClassify user request into one of these modes:\n- `Single-Ticker Deep Dive`\n- `Multi-Ticker/Universe Screening`\n- `Macro/News-Led Investigation`\n- `Portfolio Refresh`\n\nIf ambiguous, choose the most conservative high-signal mode and note assumption.\n\n## Execution workflow (ordered)\n1. Parse user intent and select one routing mode.\n2. Set budget preset (`Light`, `Standard`, `Deep`) and hard request limits.\n3. Execute required upstream skills for the chosen route.\n4. Validate intermediate outputs for freshness, completeness, and conflicts.\n5. Run valuation layer only at the required depth.\n6. Aggregate confidence across modules using the shared rubric.\n7. Return output using the mandatory output contract.\n\n## Budget policy (required)\nDefine and enforce budget at start:\n- `API budget`: max vnstock calls\n- `News budget`: max headlines/articles per source\n- `Valuation depth`: quick multiples vs full DCF\n\nDefault safe presets:\n- `Light`: 20-40 vnstock calls, headlines-only news, quick valuation\n- `Standard`: 40-120 calls, mixed headlines + selected deep reads, scenario valuation\n- `Deep`: 120-240 vnstock calls, full context package, full valuation + sensitivity\n\nPrefer free-tier-safe pacing when using vnstock.\n\n## Free-tier budget mapping (required)\nUse these hard limits for vnstock runs:\n- Guest/no API key: max `20 requests/min` (recommended pacing >= `3.2s/request`).\n- Community API key: max `60 requests/min` (recommended pacing >= `1.1s/request`; keep `3.2s/request` if unstable).\n\nPolicy actions:\n1. Estimate call count before execution and choose the smallest viable preset.\n2. If estimated calls exceed current budget, reduce scope (smaller universe or fewer modules).\n3. Reuse cached artifacts before making new requests.\n4. Stop scope expansion when remaining call budget < 10% and report partial results.\n\n## Routing logic\n\n### A) Single ticker request\nPriority: depth over breadth.\nPipeline:\n1. `vnstock-free-expert` fetch financials + price behavior.\n2. Optional macro/news context if user asks or risk is macro-sensitive.\n3. Run `earnings-quality-reviewer` before valuation when financial statements are available.\n4. `equity-valuation-framework` full thesis + valuation + risks.\n\n### B) Multi-ticker/sector screening\nPriority: breadth first, then depth on finalists.\nPipeline:\n1. `vnstock-free-expert` broad screener/ranking.\n2. Run `strategy-backtester` before treating the ranking as high-conviction when historical signal/price data is available.\n3. Select top candidates by objective criteria and backtest confidence.\n4. Run `earnings-quality-reviewer` on finalists when statement data is available.\n5. Run quick valuation layer on shortlist.\n6. Deep valuation only for top 1-3 names.\n\n### C) Macro/news-led request\nPriority: context first, valuation second.\nPipeline:\n1. `nso-macro-monitor` + `us-macro-news-monitor` + `vn-market-news-monitor`.\n2. Map exposures to sectors/tickers.\n3. Run quick vnstock validation on impacted names.\n4. Use `earnings-quality-reviewer` for decision-critical names after quantitative validation when statement data is available.\n5. If needed, run `equity-valuation-framework` for decision-critical names.\n\n### D) Portfolio refresh\nPriority: risk control + monitoring triggers + sizing discipline.\nPipeline:\n1. Re-score holdings and benchmark against alternatives.\n2. Macro/news stress overlay.\n3. Run `portfolio-analytics` before risk sizing when holdings and price history are available.\n4. Run `equity-valuation-framework` at least quick depth on key holdings/watchlist.\n5. Run `portfolio-risk-manager` to produce IPS mini + position sizing policy + per-ticker triggers/invalidation.\n6. Flag rebalance candidates with confidence and data gaps.\n\n## Mandatory output contract\nAlways include these sections in final response:\n\n1. `What Was Fetched`\n- Data sources used, date/time, and coverage.\n\n2. `Pipeline Chosen`\n- Why this route was selected for current user intent.\n\n3. `Assumptions`\n- Explicit assumptions on macro, valuation parameters, and data quality.\n\n4. `Results`\n- Ranked outputs or thesis summary with concise evidence.\n\n5. `Confidence and Gaps`\n- Confidence level + missing data + potential impact.\n\n6. `Risk Flags`\n- Top risks and monitoring triggers.\n\n7. `Next-Step Options`\n- 2-3 practical follow-up actions (e.g., deepen 1 ticker, expand peer set, update after next macro release).\n\n8. `Decision and Governance`\n- Recommendation label: `BUY`, `ADD`, `HOLD`, `TRIM`, or `EXIT`.\n- Draft target weight and maximum weight.\n- Compliance status.\n- Approval requirement.\n- D1 write intent.\n- Broker execution status: `Disabled` in the current phase.\n\n## Shared confidence rubric (required)\nUse a unified confidence output across pipeline steps:\n- `High`: all critical modules complete with no material data blockers.\n- `Medium`: one critical module has partial gaps but overall conclusion remains stable.\n- `Low`: key module(s) missing or conflicting evidence makes conclusion fragile.\n\nAggregation rule:\n1. Compute per-module confidence first (`vnstock`, `macro`, `news`, `backtest`, `earnings_quality`, `valuation`, `portfolio_analytics`, `risk_management`).\n2. Overall confidence = minimum of critical modules used in the chosen pipeline.\n3. If module outputs conflict, cap overall confidence at `Medium` unless conflict is resolved with stronger evidence.\n4. If a required professional-grade module is skipped because inputs are unavailable, cap overall confidence at `Medium` and list the missing module and input.\n5. Always state which module is the bottleneck for confidence.\n\n## Governance and quality rules\n- Single source of truth: if user provides ACTIVE_WATCHLIST/holdings, do not self-modify it; only propose drafts requiring user confirmation.\n- Never present uncertain outputs as facts.\n- Separate observed data from inference.\n- Prefer reproducible logic over ad-hoc narratives.\n- When data is insufficient, downgrade confidence and narrow claims.\n- May issue structured `BUY`, `ADD`, `HOLD`, `TRIM`, or `EXIT` labels only through `trade-decision-policy`.\n- Must not place orders, call broker APIs, execute trades, or imply that an approved target portfolio state is an executable order.\n- Must route all approved target-state mutations through `institutional-governance`.\n- Require downstream outputs to be English when preparing reusable reports or handoff bundles.\n- Carry missing data forward across modules; do not drop gaps when aggregating results.\n- If a downstream skill omits confidence or data gaps, cap overall confidence at `Medium` and state the omission.\n\n## Conflict resolution rules\nIf outputs from different modules disagree:\n1. Trust data quality hierarchy first (freshness/completeness/consistency).\n2. Prefer broad consensus metrics over fragile point estimates.\n3. Keep both interpretations and state decision boundary (what would change the conclusion).\n\n## Fallback behavior\n- If macro/news skills are unavailable: continue with vnstock + valuation only and mark missing context.\n- If valuation inputs are weak: provide screening + directional view; defer full valuation.\n- If API budget is near limit: stop expanding scope, summarize partial results, request user confirmation for deeper run.\n\n## Example orchestration prompts\n- \"Run a single-ticker deep dive for HPG with full valuation and risk register.\"\n- \"Screen VN30 for top value-quality names, then deep value top 3.\"\n- \"Start from macro shock signals, then identify Vietnamese sector winners/losers and value 2 candidates.\"\n\n## Trigger examples\n- \"Find the best Vietnam stocks this week with full reasoning.\"\n- \"Compare three candidate tickers and tell me which one is strongest.\"\n- \"Start from macro and news, then shortlist potential winners.\"\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn7aqz9b9xv2mmyvsg54n5kecn81kkaf\",\n  \"slug\": \"stock-picker-orchestrator\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1779409303229\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nActs as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and risk skills under explicit budget controls.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[teahann](https://clawhub.ai/user/teahann)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nInvestors, analysts, and agent builders use this skill to route stock-analysis requests through budget-aware screening, macro/news context, valuation, portfolio analytics, and risk-management workflows. It frames recommendations with assumptions, confidence, gaps, risk flags, and governance status.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can draft financial recommendation labels and target weights that may be mistaken for trading authorization.\n\nMitigation: Treat outputs as research, require human review for decisions, and keep broker execution disabled.\n\nRisk: The skill may coordinate costly or broad data and news collection through dependent skills.\n\nMitigation: Confirm budgets before deeper runs, reuse cached artifacts, and stop scope expansion when remaining call budget is low.\n\nRisk: Missing or unavailable dependent skills can leave macro, valuation, portfolio, or risk context incomplete.\n\nMitigation: Report missing modules, carry gaps into the final answer, and cap confidence when required inputs are unavailable.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/teahann/skills/stock-picker-orchestrator)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance, configuration]\n\n**Output Format:** [Markdown with structured sections for fetched data, pipeline choice, assumptions, results, confidence, risks, next steps, and governance.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs are recommendation framing and workflow guidance only; broker execution is disabled.]\n\n## Skill Version(s):\n\n1.0.3 (source: server 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 v1.0.3:agents/openai.yaml\n\ndisplay_name: Stock Picker Orchestrator\nshort_description: Intent-aware pipeline router for stock screening, macro/news context, and valuation.\ndefault_prompt: Orchestrate a budget-aware stock analysis pipeline, choose the right skills in sequence, and return assumptions, confidence, gaps, and risk-aware conclusions.\n\nArchive v1.0.2: 3 files, 4206 bytes\n\nFiles: agents/openai.yaml (319b), SKILL.md (7774b), _meta.json (144b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: stock-picker-orchestrator\ndescription: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, and valuation skills under explicit budget controls; used when users ask to find candidates, compare stocks, or run end-to-end expert analysis.\ncompatibility: Requires dependent skills (`vnstock-free-expert`, macro/news monitors, and `equity-valuation-framework`) to be available in the same workspace.\nmetadata: {\"openclaw\":{\"emoji\":\"🧩\"}}\n---\n\n# Stock Picker Orchestrator\n\nUse this skill to coordinate the full analysis system from user intent to final recommendation framing.\n\n## Purpose\n- Convert user request into the right analysis pipeline.\n- Control budget: vnstock API calls, breadth of news scraping, depth of valuation work.\n- Produce transparent outputs: what was fetched, assumptions, confidence, gaps.\n- Scope boundary: this skill coordinates other skills and does not replace their domain-specific logic.\n\n## Skill graph (preferred dependencies)\n1. `vnstock-free-expert` for structured market/fundamental data.\n2. `nso-macro-monitor` for Vietnam macro snapshot.\n3. `us-macro-news-monitor` for global macro spillover signals.\n4. `vn-market-news-monitor` for domestic market narrative.\n5. `equity-valuation-framework` for decision-grade valuation and report standard.\n6. `portfolio-risk-manager` for IPS mini + position sizing + risk triggers (no-margin).\n\n## Trigger conditions\n- \"Find best stock(s)\"\n- \"Screen this sector\"\n- \"Analyze ticker X deeply\"\n- \"How do macro/news affect these stocks\"\n- \"Value this stock like a professional\"\n\n## First step: intent classification\nClassify user request into one of these modes:\n- `Single-Ticker Deep Dive`\n- `Multi-Ticker/Universe Screening`\n- `Macro/News-Led Investigation`\n- `Portfolio Refresh`\n\nIf ambiguous, choose the most conservative high-signal mode and note assumption.\n\n## Execution workflow (ordered)\n1. Parse user intent and select one routing mode.\n2. Set budget preset (`Light`, `Standard`, `Deep`) and hard request limits.\n3. Execute required upstream skills for the chosen route.\n4. Validate intermediate outputs for freshness, completeness, and conflicts.\n5. Run valuation layer only at the required depth.\n6. Aggregate confidence across modules using the shared rubric.\n7. Return output using the mandatory output contract.\n\n## Budget policy (required)\nDefine and enforce budget at start:\n- `API budget`: max vnstock calls\n- `News budget`: max headlines/articles per source\n- `Valuation depth`: quick multiples vs full DCF\n\nDefault safe presets:\n- `Light`: 20-40 vnstock calls, headlines-only news, quick valuation\n- `Standard`: 40-120 calls, mixed headlines + selected deep reads, scenario valuation\n- `Deep`: 120+ calls, full context package, full valuation + sensitivity\n\nPrefer free-tier-safe pacing when using vnstock.\n\n## Free-tier budget mapping (required)\nUse these hard limits for vnstock runs:\n- Guest/no API key: max `20 requests/min` (recommended pacing >= `3.2s/request`).\n- Community API key: max `60 requests/min` (recommended pacing >= `1.1s/request`; keep `3.2s/request` if unstable).\n\nPolicy actions:\n1. Estimate call count before execution and choose the smallest viable preset.\n2. If estimated calls exceed current budget, reduce scope (smaller universe or fewer modules).\n3. Reuse cached artifacts before making new requests.\n4. Stop scope expansion when remaining call budget < 10% and report partial results.\n\n## Routing logic\n\n### A) Single ticker request\nPriority: depth over breadth.\nPipeline:\n1. `vnstock-free-expert` fetch financials + price behavior.\n2. Optional macro/news context if user asks or risk is macro-sensitive.\n3. `equity-valuation-framework` full thesis + valuation + risks.\n\n### B) Multi-ticker/sector screening\nPriority: breadth first, then depth on finalists.\nPipeline:\n1. `vnstock-free-expert` broad screener/ranking.\n2. Select top candidates by objective criteria.\n3. Run quick valuation layer on shortlist.\n4. Deep valuation only for top 1-3 names.\n\n### C) Macro/news-led request\nPriority: context first, valuation second.\nPipeline:\n1. `nso-macro-monitor` + `us-macro-news-monitor` + `vn-market-news-monitor`.\n2. Map exposures to sectors/tickers.\n3. Run quick vnstock validation on impacted names.\n4. If needed, run `equity-valuation-framework` for decision-critical names.\n\n### D) Portfolio refresh\nPriority: risk control + monitoring triggers + sizing discipline.\nPipeline:\n1. Re-score holdings and benchmark against alternatives.\n2. Macro/news stress overlay.\n3. Run `equity-valuation-framework` at least quick depth on key holdings/watchlist.\n4. Run `portfolio-risk-manager` to produce IPS mini + position sizing policy + per-ticker triggers/invalidation.\n5. Flag rebalance candidates with confidence and data gaps.\n\n## Mandatory output contract\nAlways include these sections in final response:\n\n1. `What Was Fetched`\n- Data sources used, date/time, and coverage.\n\n2. `Pipeline Chosen`\n- Why this route was selected for current user intent.\n\n3. `Assumptions`\n- Explicit assumptions on macro, valuation parameters, and data quality.\n\n4. `Results`\n- Ranked outputs or thesis summary with concise evidence.\n\n5. `Confidence and Gaps`\n- Confidence level + missing data + potential impact.\n\n6. `Risk Flags`\n- Top risks and monitoring triggers.\n\n7. `Next-Step Options`\n- 2-3 practical follow-up actions (e.g., deepen 1 ticker, expand peer set, update after next macro release).\n\n## Shared confidence rubric (required)\nUse a unified confidence output across pipeline steps:\n- `High`: all critical modules complete with no material data blockers.\n- `Medium`: one critical module has partial gaps but overall conclusion remains stable.\n- `Low`: key module(s) missing or conflicting evidence makes conclusion fragile.\n\nAggregation rule:\n1. Compute per-module confidence first (`vnstock`, `macro`, `news`, `valuation`).\n2. Overall confidence = minimum of critical modules used in the chosen pipeline.\n3. If module outputs conflict, cap overall confidence at `Medium` unless conflict is resolved with stronger evidence.\n4. Always state which module is the bottleneck for confidence.\n\n## Governance and quality rules\n- Single source of truth: if user provides ACTIVE_WATCHLIST/holdings, do not self-modify it; only propose drafts requiring user confirmation.\n- Never present uncertain outputs as facts.\n- Separate observed data from inference.\n- Prefer reproducible logic over ad-hoc narratives.\n- When data is insufficient, downgrade confidence and narrow claims.\n- Avoid absolute buy/sell instructions; provide valuation framing and risk-aware interpretation.\n\n## Conflict resolution rules\nIf outputs from different modules disagree:\n1. Trust data quality hierarchy first (freshness/completeness/consistency).\n2. Prefer broad consensus metrics over fragile point estimates.\n3. Keep both interpretations and state decision boundary (what would change the conclusion).\n\n## Fallback behavior\n- If macro/news skills are unavailable: continue with vnstock + valuation only and mark missing context.\n- If valuation inputs are weak: provide screening + directional view; defer full valuation.\n- If API budget is near limit: stop expanding scope, summarize partial results, request user confirmation for deeper run.\n\n## Example orchestration prompts\n- \"Run a single-ticker deep dive for HPG with full valuation and risk register.\"\n- \"Screen VN30 for top value-quality names, then deep value top 3.\"\n- \"Start from macro shock signals, then identify Vietnamese sector winners/losers and value 2 candidates.\"\n\n## Trigger examples\n- \"Find the best Vietnam stocks this week with full reasoning.\"\n- \"Compare three candidate tickers and tell me which one is strongest.\"\n- \"Start from macro and news, then shortlist potential winners.\"\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7aqz9b9xv2mmyvsg54n5kecn81kkaf\",\n  \"slug\": \"stock-picker-orchestrator\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1771948701311\n}\n\nFile v1.0.2:agents/openai.yaml\n\ndisplay_name: Stock Picker Orchestrator\nshort_description: Intent-aware pipeline router for stock screening, macro/news context, and valuation.\ndefault_prompt: Orchestrate a budget-aware stock analysis pipeline, choose the right skills in sequence, and return assumptions, confidence, gaps, and risk-aware conclusions.\n\nArchive v1.0.1: 3 files, 4017 bytes\n\nFiles: agents/openai.yaml (319b), SKILL.md (7327b), _meta.json (144b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: stock-picker-orchestrator\ndescription: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, and valuation skills under explicit budget controls; used when users ask to find candidates, compare stocks, or run end-to-end expert analysis.\ncompatibility: Requires dependent skills (`vnstock-free-expert`, macro/news monitors, and `equity-valuation-framework`) to be available in the same workspace.\nmetadata: {\"openclaw\":{\"emoji\":\"🧩\"}}\n---\n\n# Stock Picker Orchestrator\n\nUse this skill to coordinate the full analysis system from user intent to final recommendation framing.\n\n## Purpose\n- Convert user request into the right analysis pipeline.\n- Control budget: vnstock API calls, breadth of news scraping, depth of valuation work.\n- Produce transparent outputs: what was fetched, assumptions, confidence, gaps.\n- Scope boundary: this skill coordinates other skills and does not replace their domain-specific logic.\n\n## Skill graph (preferred dependencies)\n1. `vnstock-free-expert` for structured market/fundamental data.\n2. `nso-macro-monitor` for Vietnam macro snapshot.\n3. `us-macro-news-monitor` for global macro spillover signals.\n4. `vn-market-news-monitor` for domestic market narrative.\n5. `equity-valuation-framework` for decision-grade valuation and report standard.\n\n## Trigger conditions\n- \"Find best stock(s)\"\n- \"Screen this sector\"\n- \"Analyze ticker X deeply\"\n- \"How do macro/news affect these stocks\"\n- \"Value this stock like a professional\"\n\n## First step: intent classification\nClassify user request into one of these modes:\n- `Single-Ticker Deep Dive`\n- `Multi-Ticker/Universe Screening`\n- `Macro/News-Led Investigation`\n- `Portfolio Refresh`\n\nIf ambiguous, choose the most conservative high-signal mode and note assumption.\n\n## Execution workflow (ordered)\n1. Parse user intent and select one routing mode.\n2. Set budget preset (`Light`, `Standard`, `Deep`) and hard request limits.\n3. Execute required upstream skills for the chosen route.\n4. Validate intermediate outputs for freshness, completeness, and conflicts.\n5. Run valuation layer only at the required depth.\n6. Aggregate confidence across modules using the shared rubric.\n7. Return output using the mandatory output contract.\n\n## Budget policy (required)\nDefine and enforce budget at start:\n- `API budget`: max vnstock calls\n- `News budget`: max headlines/articles per source\n- `Valuation depth`: quick multiples vs full DCF\n\nDefault safe presets:\n- `Light`: 20-40 vnstock calls, headlines-only news, quick valuation\n- `Standard`: 40-120 calls, mixed headlines + selected deep reads, scenario valuation\n- `Deep`: 120+ calls, full context package, full valuation + sensitivity\n\nPrefer free-tier-safe pacing when using vnstock.\n\n## Free-tier budget mapping (required)\nUse these hard limits for vnstock runs:\n- Guest/no API key: max `20 requests/min` (recommended pacing >= `3.2s/request`).\n- Community API key: max `60 requests/min` (recommended pacing >= `1.1s/request`; keep `3.2s/request` if unstable).\n\nPolicy actions:\n1. Estimate call count before execution and choose the smallest viable preset.\n2. If estimated calls exceed current budget, reduce scope (smaller universe or fewer modules).\n3. Reuse cached artifacts before making new requests.\n4. Stop scope expansion when remaining call budget < 10% and report partial results.\n\n## Routing logic\n\n### A) Single ticker request\nPriority: depth over breadth.\nPipeline:\n1. `vnstock-free-expert` fetch financials + price behavior.\n2. Optional macro/news context if user asks or risk is macro-sensitive.\n3. `equity-valuation-framework` full thesis + valuation + risks.\n\n### B) Multi-ticker/sector screening\nPriority: breadth first, then depth on finalists.\nPipeline:\n1. `vnstock-free-expert` broad screener/ranking.\n2. Select top candidates by objective criteria.\n3. Run quick valuation layer on shortlist.\n4. Deep valuation only for top 1-3 names.\n\n### C) Macro/news-led request\nPriority: context first, valuation second.\nPipeline:\n1. `nso-macro-monitor` + `us-macro-news-monitor` + `vn-market-news-monitor`.\n2. Map exposures to sectors/tickers.\n3. Run quick vnstock validation on impacted names.\n4. If needed, run `equity-valuation-framework` for decision-critical names.\n\n### D) Portfolio refresh\nPriority: risk control + monitoring triggers.\nPipeline:\n1. Re-score holdings and benchmark against alternatives.\n2. Macro/news stress overlay.\n3. Flag rebalance candidates with confidence and data gaps.\n\n## Mandatory output contract\nAlways include these sections in final response:\n\n1. `What Was Fetched`\n- Data sources used, date/time, and coverage.\n\n2. `Pipeline Chosen`\n- Why this route was selected for current user intent.\n\n3. `Assumptions`\n- Explicit assumptions on macro, valuation parameters, and data quality.\n\n4. `Results`\n- Ranked outputs or thesis summary with concise evidence.\n\n5. `Confidence and Gaps`\n- Confidence level + missing data + potential impact.\n\n6. `Risk Flags`\n- Top risks and monitoring triggers.\n\n7. `Next-Step Options`\n- 2-3 practical follow-up actions (e.g., deepen 1 ticker, expand peer set, update after next macro release).\n\n## Shared confidence rubric (required)\nUse a unified confidence output across pipeline steps:\n- `High`: all critical modules complete with no material data blockers.\n- `Medium`: one critical module has partial gaps but overall conclusion remains stable.\n- `Low`: key module(s) missing or conflicting evidence makes conclusion fragile.\n\nAggregation rule:\n1. Compute per-module confidence first (`vnstock`, `macro`, `news`, `valuation`).\n2. Overall confidence = minimum of critical modules used in the chosen pipeline.\n3. If module outputs conflict, cap overall confidence at `Medium` unless conflict is resolved with stronger evidence.\n4. Always state which module is the bottleneck for confidence.\n\n## Governance and quality rules\n- Never present uncertain outputs as facts.\n- Separate observed data from inference.\n- Prefer reproducible logic over ad-hoc narratives.\n- When data is insufficient, downgrade confidence and narrow claims.\n- Avoid absolute buy/sell instructions; provide valuation framing and risk-aware interpretation.\n\n## Conflict resolution rules\nIf outputs from different modules disagree:\n1. Trust data quality hierarchy first (freshness/completeness/consistency).\n2. Prefer broad consensus metrics over fragile point estimates.\n3. Keep both interpretations and state decision boundary (what would change the conclusion).\n\n## Fallback behavior\n- If macro/news skills are unavailable: continue with vnstock + valuation only and mark missing context.\n- If valuation inputs are weak: provide screening + directional view; defer full valuation.\n- If API budget is near limit: stop expanding scope, summarize partial results, request user confirmation for deeper run.\n\n## Example orchestration prompts\n- \"Run a single-ticker deep dive for HPG with full valuation and risk register.\"\n- \"Screen VN30 for top value-quality names, then deep value top 3.\"\n- \"Start from macro shock signals, then identify Vietnamese sector winners/losers and value 2 candidates.\"\n\n## Trigger examples\n- \"Find the best Vietnam stocks this week with full reasoning.\"\n- \"Compare three candidate tickers and tell me which one is strongest.\"\n- \"Start from macro and news, then shortlist potential winners.\"\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7aqz9b9xv2mmyvsg54n5kecn81kkaf\",\n  \"slug\": \"stock-picker-orchestrator\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1771841685193\n}\n\nFile v1.0.1:agents/openai.yaml\n\ndisplay_name: Stock Picker Orchestrator\nshort_description: Intent-aware pipeline router for stock screening, macro/news context, and valuation.\ndefault_prompt: Orchestrate a budget-aware stock analysis pipeline, choose the right skills in sequence, and return assumptions, confidence, gaps, and risk-aware conclusions.\n\nArchive v1.0.0: 3 files, 3670 bytes\n\nFiles: agents/openai.yaml (319b), SKILL.md (6403b), _meta.json (144b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: stock-picker-orchestrator\ndescription: Orchestrates end-to-end stock analysis pipelines by selecting and sequencing the right skills (vnstock data, macro, news, valuation) under request-budget constraints. Use when users ask to find best stocks, compare candidates, or run expert-style analysis.\nmetadata: {\"openclaw\":{\"emoji\":\"🧩\"}}\n---\n\n# Stock Picker Orchestrator\n\nUse this skill to coordinate the full analysis system from user intent to final recommendation framing.\n\n## Purpose\n- Convert user request into the right analysis pipeline.\n- Control budget: vnstock API calls, breadth of news scraping, depth of valuation work.\n- Produce transparent outputs: what was fetched, assumptions, confidence, gaps.\n\n## Skill graph (preferred dependencies)\n1. `vnstock-free-expert` for structured market/fundamental data.\n2. `nso-macro-monitor` for Vietnam macro snapshot.\n3. `us-macro-news-monitor` for global macro spillover signals.\n4. `vn-market-news-monitor` for domestic market narrative.\n5. `equity-valuation-framework` for decision-grade valuation and report standard.\n\n## Trigger conditions\n- \"Find best stock(s)\"\n- \"Screen this sector\"\n- \"Analyze ticker X deeply\"\n- \"How do macro/news affect these stocks\"\n- \"Value this stock like a professional\"\n\n## First step: intent classification\nClassify user request into one of these modes:\n- `Single-Ticker Deep Dive`\n- `Multi-Ticker/Universe Screening`\n- `Macro/News-Led Investigation`\n- `Portfolio Refresh`\n\nIf ambiguous, choose the most conservative high-signal mode and note assumption.\n\n## Budget policy (required)\nDefine and enforce budget at start:\n- `API budget`: max vnstock calls\n- `News budget`: max headlines/articles per source\n- `Valuation depth`: quick multiples vs full DCF\n\nDefault safe presets:\n- `Light`: 20-40 vnstock calls, headlines-only news, quick valuation\n- `Standard`: 40-120 calls, mixed headlines + selected deep reads, scenario valuation\n- `Deep`: 120+ calls, full context package, full valuation + sensitivity\n\nPrefer free-tier-safe pacing when using vnstock.\n\n## Free-tier budget mapping (required)\nUse these hard limits for vnstock runs:\n- Guest/no API key: max `20 requests/min` (recommended pacing >= `3.2s/request`).\n- Community API key: max `60 requests/min` (recommended pacing >= `1.1s/request`; keep `3.2s/request` if unstable).\n\nPolicy actions:\n1. Estimate call count before execution and choose the smallest viable preset.\n2. If estimated calls exceed current budget, reduce scope (smaller universe or fewer modules).\n3. Reuse cached artifacts before making new requests.\n4. Stop scope expansion when remaining call budget < 10% and report partial results.\n\n## Routing logic\n\n### A) Single ticker request\nPriority: depth over breadth.\nPipeline:\n1. `vnstock-free-expert` fetch financials + price behavior.\n2. Optional macro/news context if user asks or risk is macro-sensitive.\n3. `equity-valuation-framework` full thesis + valuation + risks.\n\n### B) Multi-ticker/sector screening\nPriority: breadth first, then depth on finalists.\nPipeline:\n1. `vnstock-free-expert` broad screener/ranking.\n2. Select top candidates by objective criteria.\n3. Run quick valuation layer on shortlist.\n4. Deep valuation only for top 1-3 names.\n\n### C) Macro/news-led request\nPriority: context first, valuation second.\nPipeline:\n1. `nso-macro-monitor` + `us-macro-news-monitor` + `vn-market-news-monitor`.\n2. Map exposures to sectors/tickers.\n3. Run quick vnstock validation on impacted names.\n4. If needed, run `equity-valuation-framework` for decision-critical names.\n\n### D) Portfolio refresh\nPriority: risk control + monitoring triggers.\nPipeline:\n1. Re-score holdings and benchmark against alternatives.\n2. Macro/news stress overlay.\n3. Flag rebalance candidates with confidence and data gaps.\n\n## Mandatory output contract\nAlways include these sections in final response:\n\n1. `What Was Fetched`\n- Data sources used, date/time, and coverage.\n\n2. `Pipeline Chosen`\n- Why this route was selected for current user intent.\n\n3. `Assumptions`\n- Explicit assumptions on macro, valuation parameters, and data quality.\n\n4. `Results`\n- Ranked outputs or thesis summary with concise evidence.\n\n5. `Confidence and Gaps`\n- Confidence level + missing data + potential impact.\n\n6. `Risk Flags`\n- Top risks and monitoring triggers.\n\n7. `Next-Step Options`\n- 2-3 practical follow-up actions (e.g., deepen 1 ticker, expand peer set, update after next macro release).\n\n## Shared confidence rubric (required)\nUse a unified confidence output across pipeline steps:\n- `High`: all critical modules complete with no material data blockers.\n- `Medium`: one critical module has partial gaps but overall conclusion remains stable.\n- `Low`: key module(s) missing or conflicting evidence makes conclusion fragile.\n\nAggregation rule:\n1. Compute per-module confidence first (`vnstock`, `macro`, `news`, `valuation`).\n2. Overall confidence = minimum of critical modules used in the chosen pipeline.\n3. If module outputs conflict, cap overall confidence at `Medium` unless conflict is resolved with stronger evidence.\n4. Always state which module is the bottleneck for confidence.\n\n## Governance and quality rules\n- Never present uncertain outputs as facts.\n- Separate observed data from inference.\n- Prefer reproducible logic over ad-hoc narratives.\n- When data is insufficient, downgrade confidence and narrow claims.\n- Avoid absolute buy/sell instructions; provide valuation framing and risk-aware interpretation.\n\n## Conflict resolution rules\nIf outputs from different modules disagree:\n1. Trust data quality hierarchy first (freshness/completeness/consistency).\n2. Prefer broad consensus metrics over fragile point estimates.\n3. Keep both interpretations and state decision boundary (what would change the conclusion).\n\n## Fallback behavior\n- If macro/news skills are unavailable: continue with vnstock + valuation only and mark missing context.\n- If valuation inputs are weak: provide screening + directional view; defer full valuation.\n- If API budget is near limit: stop expanding scope, summarize partial results, request user confirmation for deeper run.\n\n## Example orchestration prompts\n- \"Run a single-ticker deep dive for HPG with full valuation and risk register.\"\n- \"Screen VN30 for top value-quality names, then deep value top 3.\"\n- \"Start from macro shock signals, then identify Vietnamese sector winners/losers and value 2 candidates.\"\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7aqz9b9xv2mmyvsg54n5kecn81kkaf\",\n  \"slug\": \"stock-picker-orchestrator\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771837418853\n}\n\nFile v1.0.0:agents/openai.yaml\n\ndisplay_name: Stock Picker Orchestrator\nshort_description: Intent-aware pipeline router for stock screening, macro/news context, and valuation.\ndefault_prompt: Orchestrate a budget-aware stock analysis pipeline, choose the right skills in sequence, and return assumptions, confidence, gaps, and risk-aware conclusions.","readmeExcerpt":"Skill: Stock Picker Orchestrator Owner: teahann Summary: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-05-22T00:21:43.229Z | user Update Vietnam institutional stock skill system with D1 governance, trade decision policy, and harness agent guide. v1.0.2 | ","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: stock-picker-orchestrator\ndescription: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and risk skills under explicit budget controls.\ncompatibility: Requires dependent skills (`vnstock-free-expert`, macro/news monitors, `strategy-backtester`, `earnings-quality-reviewer`, `equity-valuation-framework`, `portfolio-analytics`, and `portfolio-risk-manager`) to be available in the same workspace.\nmetadata: {\"openclaw\":{\"emoji\":\"🧩\"}}\n---\n\n# Stock Picker Orchestrator\n\nUse this skill to coordinate the full analysis system from user intent to final recommendation framing.\n\n## Purpose\n- Convert user request into the right analysis pipeline.\n- Control budget: vnstock API calls, breadth of news scraping, depth of valuation work.\n- Produce transparent outputs: what was fetched, assumptions, confidence, gaps.\n- Scope boundary: this skill coordinates other skills and does not replace their domain-specific logic.\n\n## Skill graph (preferred dependencies)\n1. `vnstock-free-expert` for structured market/fundamental data.\n2. `nso-macro-monitor` for Vietnam macro snapshot.\n3. `us-macro-news-monitor` for global macro spillover signals.\n4. `vn-market-news-monitor` for domestic market narrative.\n5. `strategy-backtester` for historical ranking/strategy validation.\n6. `earnings-quality-reviewer` for earnings quality before valuation conviction.\n7. `equity-valuation-framework` for decision-grade valuation and report standard.\n8. `portfolio-analytics` for portfolio risk metrics before sizing/rebalance.\n9. `portfolio-risk-manager` for IPS mini + position sizing + risk triggers (no-margin).\n10. `trade-decision-policy` for `BUY`, `ADD`, `HOLD`, `TRIM`, `EXIT`, target weights, and action drafts.\n11. `institutional-governance` for D1 approvals, compliance checks, audit logs, and approved target portfolio state.\n\n## Trigger conditions\n- \"Find best stock(s)\"\n- \"Screen this sector\"\n- \"Analyze ticker X deeply\"\n- \"How do macro/news affect these stocks\"\n- \"Value this stock like a professional\"\n\n## First step: intent classification\nClassify user request into one of these modes:\n- `Single-Ticker Deep Dive`\n- `Multi-Ticker/Universe Screening`\n- `Macro/News-Led Investigation`\n- `Portfolio Refresh`\n\nIf ambiguous, choose the most conservative high-signal mode and note assumption.\n\n## Execution workflow (ordered)\n1. Parse user intent and select one routing mode.\n2. Set budget preset (`Light`, `Standard`, `Deep`) and hard request limits.\n3. Execute required upstream skills for the chosen route.\n4. Validate intermediate outputs for freshness, completeness, and conflicts.\n5. Run valuation layer only at the required depth.\n6. Aggregate confidence across modules using the shared rubric.\n7. Return output using the mandatory output contract.\n\n## Budget policy (required)\nDefine and enforce budget at start:\n- `API budget`: max vnstock calls\n- `News budget`: max headlines/articles per sour"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7aqz9b9xv2mmyvsg54n5kecn81kkaf\",\n  \"slug\": \"stock-picker-orchestrator\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1779409303229\n}"},{"path":"skill-card.md","content":"## Description:\n\nActs as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and risk skills under explicit budget controls.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[teahann](https://clawhub.ai/user/teahann)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nInvestors, analysts, and agent builders use this skill to route stock-analysis requests through budget-aware screening, macro/news context, valuation, portfolio analytics, and risk-management workflows. It frames recommendations with assumptions, confidence, gaps, risk flags, and governance status.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can draft financial recommendation labels and target weights that may be mistaken for trading authorization.\n\nMitigation: Treat outputs as research, require human review for decisions, and keep broker execution disabled.\n\nRisk: The skill may coordinate costly or broad data and news collection through dependent skills.\n\nMitigation: Confirm budgets before deeper runs, reuse cached artifacts, and stop scope expansion when remaining call budget is low.\n\nRisk: Missing or unavailable dependent skills can leave macro, valuation, portfolio, or risk context incomplete.\n\nMitigation: Report missing modules, carry gaps into the final answer, and cap confidence when required inputs are unavailable.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/teahann/skills/stock-picker-orchestrator)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance, configuration]\n\n**Output Format:** [Markdown with structured sections for fetched data, pipeline choice, assumptions, results, confidence, risks, next steps, and governance.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs are recommendation framing and workflow guidance only; broker execution is disabled.]\n\n## Skill Version(s):\n\n1.0.3 (source: server 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":"agents/openai.yaml","content":"display_name: Stock Picker Orchestrator\nshort_description: Intent-aware pipeline router for stock screening, macro/news context, and valuation.\ndefault_prompt: Orchestrate a budget-aware stock analysis pipeline, choose the right skills in sequence, and return assumptions, confidence, gaps, and risk-aware conclusions."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r... Skill: Stock Picker Orchestrator Owner: teahann Summary: Acts as a meta-orchestrator that routes stock-analysis requests across data, macro/news, backtesting, earnings quality, valuation, portfolio analytics, and r... Tags: latest:1.0.3 Version history: v1.0.3 | 2026-05-22T00:21:43.229Z | user Update Vietnam institutional stock skill system with D1 governance, trade decision policy, and harness agent guide. v1.0.2 |","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1348,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T18:27:50.076Z","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":"2026-10-09T18:27:50.076Z","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":"2026-10-10T03:02:34.766Z","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"}]}}}