{"id":"fbc9b5d5-b1d4-410d-b6c1-e9d9ac8f4943","entityType":"agent","slug":"pillarhq-openclaw-agent-score","name":"agent-score","canonicalUrl":"https://www.xpersona.co/agent/pillarhq-openclaw-agent-score","canonicalPath":"/agent/pillarhq-openclaw-agent-score","generatedAt":"2026-10-09T14:57:43.671Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Evaluate a website's agent-friendliness and return a structured JSON score report. --- name: agent-score description: Evaluate a website's agent-friendliness and return a structured JSON score report. --- Agent Score — AI Agent Readiness Test Test how easy a website is for AI agents to use. Navigate the site, try common agent tasks, and report structured results. When to use Run this skill when asked to evaluate a website's agent-friendliness, test a site for AI readiness, or run an \"agent score\" t","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 4/15/2026.","installCommand":"git clone https://github.com/pillarhq/openclaw-agent-score.git","sourceUrl":"https://github.com/pillarhq/openclaw-agent-score","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/pillarhq/openclaw-agent-score","kind":"source"}],"safetyScore":94,"overallRank":31.9,"popularityScore":8,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Evaluate a website's agent-friendliness and return a structured JSON score report. --- name: agent-score description: Evaluate a website's agent-friendliness an"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"MCP","label":"MCP","status":"self-declared","notes":"Declared in the public agent profile."},{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"you","status":"self-declared"},{"label":"only","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":4,"capabilityMatrix":{"rows":[{"key":"MCP","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"you","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"only","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:MCP|unknown|profile protocol:OPENCLEW|unknown|profile capability:you|supported|profile capability:only|supported|profile"}},"adoption":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"stars":1,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"1 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-15T01:15:27.127Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-15T01:15:27.127Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-16T01:15:27.127Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/pillarhq/openclaw-agent-score.git","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/pillarhq-openclaw-agent-score/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["MCP","OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T14:57:43.671Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/pillarhq-openclaw-agent-score/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":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: agent-score\ndescription: Evaluate a website's agent-friendliness and return a structured JSON score report.\n---\n\n# Agent Score — AI Agent Readiness Test\n\nTest how easy a website is for AI agents to use. Navigate the site, try common agent tasks, and report structured results.\n\n## When to use\n\nRun this skill when asked to evaluate a website's agent-friendliness, test a site for AI readiness, or run an \"agent score\" test.\n\n## Browser tool usage\n\nYou MUST use the `browser` tool to interact with websites. Every browser tool call requires an `action` field and action-specific fields. Here are the actions you will use:\n\n- **Navigate to a URL:** `{ \"action\": \"navigate\", \"targetUrl\": \"https://example.com\" }`\n- **Take a snapshot (read the page):** `{ \"action\": \"snapshot\" }`\n- **Click an element:** `{ \"action\": \"click\", \"ref\": \"<element_ref_from_snapshot>\" }`\n- **Type into a field:** `{ \"action\": \"type\", \"ref\": \"<element_ref_from_snapshot>\", \"text\": \"hello\" }`\n- **Take a screenshot:** `{ \"action\": \"screenshot\" }`\n\nAlways start by navigating to the target URL, then take a snapshot to see what's on the page. Use refs from the snapshot to click and type.\n\n## Instructions\n\nYou are an AI agent evaluating how easy a website is for agents like you to use. Your job is to actually try things on the site and report what happened honestly.\n\n### What to try\n\nWork through these tasks in order. Skip any that don't apply to the site:\n\n1. **Navigate and understand** — Call the browser tool with `{ \"action\": \"navigate\", \"targetUrl\": \"<the_url>\" }` to open the site. Then call `{ \"action\": \"snapshot\" }` to read the page. Figure out what the site does and what its primary function is.\n\n2. **Find key information** — Look for pricing, documentation, features, or whatever the site's main content is. Can you find what you need without getting lost?\n\n3. **Create an account** — If the site has a signup or registration flow, try to create an account using these details:\n   - Name: Pillar Agent Test\n   - Email: agent-test@score.trypillar.com\n   - Password: PillarTest!2026\n   - If you hit a CAPTCHA, stop and note it. If payment is required, stop and note it. Do NOT use OAuth/SSO buttons.\n\n4. **Look for MCP tools** — Check if the site exposes MCP tools via `navigator.modelContext`. If tools are registered, try to use one.\n\n5. **Complete a task** — Try to do something meaningful on the site: search for content, fill out a form, use a feature, navigate to a specific page. Pick whatever seems most representative.\n\n6. **Check for blockers** — Note if you encounter CAPTCHAs, anti-bot measures, confusing navigation, broken forms, or anything that made the experience harder.\n\n### Reporting rules\n\n- **Report what you observed, not why it happened.** Do not speculate about root causes. Do not attribute failures to the automation tooling, the browser, or the website unless you have direct evidence.\n- **Do not use the phrase \"OpenClaw issue\" or say \"not the website.\"** You do not have enough information to make that distinction. Just describe what happened.\n- **Examples of good reporting:**\n  - \"Browser control timed out while attempting to click 'Get Started'\"\n  - \"Page loaded but the signup form did not respond to input\"\n  - \"Navigation worked but account creation could not be completed\"\n- **Examples of bad reporting:**\n  - \"This was due to an OpenClaw browser control issue, not the website\"\n  - \"The timeout was caused by a bug in the automation framework\"\n- **If you cannot complete a core flow** (signup, checkout, search) due to timeouts, unresponsive elements, or repeated failures, **treat that as a poor agent experience and score accordingly.** The score reflects what an agent could actually accomplish, regardless of the underlying cause.\n\n### How to respond\n\nWhen you're done, respond with ONLY this JSON (no markdown fencing, no extra text):\n\n```json\n{\n  \"score\": 75,\n  \"summary\": \"2-3 sentences describing the overall agent experience on this site.\",\n  \"what_worked\": [\n    \"Navigation was straightforward\",\n    \"Forms were well-labeled\"\n  ],\n  \"what_didnt\": [\n    \"Signup was blocked by CAPTCHA\",\n    \"No MCP tools found\"\n  ],\n  \"mcp_found\": false,\n  \"mcp_usable\": false,\n  \"signup_attempted\": true,\n  \"signup_succeeded\": false,\n  \"tasks_tried\": [\n    {\n      \"task\": \"Navigate to pricing page\",\n      \"succeeded\": true,\n      \"detail\": \"Found pricing link in main nav, page loaded with clear tier comparison.\"\n    },\n    {\n      \"task\": \"Create an account\",\n      \"succeeded\": false,\n      \"detail\": \"Found signup form but blocked by reCAPTCHA on submission.\"\n    }\n  ],\n  \"full_report_url\": \"https://trypillar.com/agent-score?domain=DOMAIN_HERE\"\n}\n```\n\n### Scoring guidelines\n\n- **90-100**: Everything worked smoothly. Agent could navigate, sign up, use MCP tools, and complete tasks with no friction.\n- **70-89**: Most things worked. Minor issues like missing labels or unclear navigation, but agent could accomplish its goals.\n- **50-69**: Mixed experience. Some tasks worked, others were difficult or impossible. Significant friction points.\n- **30-49**: Mostly difficult. Agent struggled with basic tasks. Many blockers or confusing patterns.\n- **0-29**: Site is effectively unusable by agents. CAPTCHAs everywhere, no semantic structure, broken forms.\n\nIf you cannot access the site at all or cannot complete any interactive tasks due to timeouts or interaction failures, still respond with the JSON format above. Set the score based on what you could actually accomplish. A site where the agent can only read but not interact deserves a low score.\n\nBe honest. Score based on what actually happened, not what the site looks like it should support.\n","readmeExcerpt":"--- name: agent-score description: Evaluate a website's agent-friendliness and return a structured JSON score report. --- Agent Score — AI Agent Readiness Test Test how easy a website is for AI agents to use. Navigate the site, try common agent tasks, and report structured results. When to use Run this skill when asked to evaluate a website's agent-friendliness, test a site for AI readiness, or run an \"agent score\" t","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"score\": 75,\n  \"summary\": \"2-3 sentences describing the overall agent experience on this site.\",\n  \"what_worked\": [\n    \"Navigation was straightforward\",\n    \"Forms were well-labeled\"\n  ],\n  \"what_didnt\": [\n    \"Signup was blocked by CAPTCHA\",\n    \"No MCP tools found\"\n  ],\n  \"mcp_found\": false,\n  \"mcp_usable\": false,\n  \"signup_attempted\": true,\n  \"signup_succeeded\": false,\n  \"tasks_tried\": [\n    {\n      \"task\": \"Navigate to pricing page\",\n      \"succeeded\": true,\n      \"detail\": \"Found pricing link in main nav, page loaded with clear tier comparison.\"\n    },\n    {\n      \"task\": \"Create an account\",\n      \"succeeded\": false,\n      \"detail\": \"Found signup form but blocked by reCAPTCHA on submission.\"\n    }\n  ],\n  \"full_report_url\": \"https://trypillar.com/agent-score?domain=DOMAIN_HERE\"\n}"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Evaluate a website's agent-friendliness and return a structured JSON score report. --- name: agent-score description: Evaluate a website's agent-friendliness and return a structured JSON score report. --- Agent Score — AI Agent Readiness Test Test how easy a website is for AI agents to use. Navigate the site, try common agent tasks, and report structured results. When to use Run this skill when asked to evaluate a website's agent-friendliness, test a site for AI readiness, or run an \"agent score\" t","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":378,"uniquenessScore":61,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","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":"2026-04-15T05:21:22.124Z","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":"2026-10-09T14:57:43.671Z","emptyReason":null},"items":[{"id":"2d0ce267-ccff-48fc-bef6-6ddad9c50d20","entityType":"agent","canonicalPath":"/agent/ard-urn-air-io-github-deesmo-mcp-arch-tools-mcp","slug":"ard-urn-air-io-github-deesmo-mcp-arch-tools-mcp","name":"io.github.Deesmo/arch-tools-mcp","description":"63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.","url":"https://archtools.dev/mcp","homepage":"https://archtools.dev/mcp","source":"ARD_REGISTRY","protocols":["MCP"],"capabilities":["mcp","mcp-registry"],"safetyScore":95,"overallRank":93.5,"updatedAt":"2026-10-09T14:36:24.781Z","createdAt":"2026-10-09T02:32:09.920Z","downloads":null},{"id":"03e8460e-4e22-46ea-967a-1f32180fd24c","entityType":"agent","canonicalPath":"/agent/ard-urn-air-io-github-cyanheads-mcp-reliefweb-mcp-server","slug":"ard-urn-air-io-github-cyanheads-mcp-reliefweb-mcp-server","name":"io.github.cyanheads/reliefweb-mcp-server","description":"Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP.","url":"https://reliefweb.caseyjhand.com/mcp","homepage":"https://reliefweb.caseyjhand.com/mcp","source":"ARD_REGISTRY","protocols":["MCP"],"capabilities":["mcp","mcp-registry"],"safetyScore":95,"overallRank":93.5,"updatedAt":"2026-10-09T12:38:51.997Z","createdAt":"2026-10-09T02:32:11.316Z","downloads":null},{"id":"207a916d-8e28-4d34-ad39-513c412c8d82","entityType":"agent","canonicalPath":"/agent/ard-urn-air-io-github-sawftware-apps-mcp-commodities-sh","slug":"ard-urn-air-io-github-sawftware-apps-mcp-commodities-sh","name":"Primary Source Commodities","description":"Primary-source commodities data for AI agents — EIA, FRED, CFTC, USDA, USGS via x402 on Base.","url":"https://api.commodities.sh/api/mcp","homepage":"https://api.commodities.sh/api/mcp","source":"ARD_REGISTRY","protocols":["MCP"],"capabilities":["mcp","mcp-registry"],"safetyScore":95,"overallRank":93.5,"updatedAt":"2026-10-09T03:15:08.952Z","createdAt":"2026-10-09T02:32:11.867Z","downloads":null},{"id":"3fa19dc2-ddd2-4258-bd2e-78923b585861","entityType":"agent","canonicalPath":"/agent/ard-urn-air-io-github-dopionut-jpg-mcp-crypto-data-market-analy","slug":"ard-urn-air-io-github-dopionut-jpg-mcp-crypto-data-market-analy","name":"Crypto Data & Market Analysis Agent","description":"One-call market verdict, plus funding, open interest, execution cost, volatility and macro","url":"https://asistent-crypto.vercel.app/mcp","homepage":"https://asistent-crypto.vercel.app/mcp","source":"ARD_REGISTRY","protocols":["MCP"],"capabilities":["mcp","mcp-registry"],"safetyScore":95,"overallRank":93.5,"updatedAt":"2026-10-09T03:15:08.952Z","createdAt":"2026-10-09T02:32:11.855Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"MCP","href":"/agent/protocol/mcp"},{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}