{"id":"27328e0a-a8d7-4672-a946-e136b2ec4f85","entityType":"agent","slug":"clawhub-nissan-fact-checker","name":"Fact Checker","canonicalUrl":"https://www.xpersona.co/agent/clawhub-nissan-fact-checker","canonicalPath":"/agent/clawhub-nissan-fact-checker","generatedAt":"2026-10-10T08:05:17.668Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T08:07:25.728Z","emptyReason":null},"description":"Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi... Skill: Fact Checker Owner: nissan Summary: Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-03-28T04:42:10.049Z | user Add security_notes: local-only verification, subprocess is bundled Python script v1.0.3 | 2026-03-28T03:54:28.755Z | user Frontmatter fix:","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 3.4K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17f2fw07zktjmcgagf5c29tbd83rt7v:fact-checker","sourceUrl":"https://clawhub.ai/nissan/fact-checker","homepage":"https://clawhub.ai/nissan/skills/fact-checker","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/nissan/fact-checker","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/nissan/skills/fact-checker","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":58,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T08:07:25.728Z","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":"2026-10-09T08:07:25.728Z","emptyReason":null},"stars":null,"forks":null,"downloads":3433,"packageName":null,"latestVersion":"1.0.4","tractionLabel":"3.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T08:07:25.727Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T08:07:25.728Z","lastCrawledAt":"2026-10-09T08:07:25.727Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T08:07:25.727Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.4","createdAt":"2026-03-28T04:42:10.049Z","changelog":"Add security_notes: local-only verification, subprocess is bundled Python script","fileCount":5,"zipByteSize":13143},{"version":"1.0.3","createdAt":"2026-03-28T03:54:28.755Z","changelog":"Frontmatter fix: corrected malformed metadata block, added proper YAML network/subprocess flags","fileCount":4,"zipByteSize":11762},{"version":"1.0.2","createdAt":"2026-03-01T21:09:30.578Z","changelog":"Added complete frontmatter with security declarations","fileCount":4,"zipByteSize":11675},{"version":"1.0.1","createdAt":"2026-02-26T22:10:50.047Z","changelog":"Added metadata block with network disclosure (no outbound calls)","fileCount":4,"zipByteSize":11693},{"version":"1.0.0","createdAt":"2026-02-26T21:38:52.899Z","changelog":"- Initial release of the fact-checker skill. - Automatically identifies and cross-references numeric, model, date, score, and percentage claims in markdown drafts. - Verifies claims against FINDINGS.md, live API data, score files, memory logs, and git history. - Outputs a clear verification report categorizing claims as CONFIRMED, UNVERIFIABLE, or CONTRADICTED. - Summarizes results and flags contradicted claims with suggested corrections.","fileCount":4,"zipByteSize":11565}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17f2fw07zktjmcgagf5c29tbd83rt7v:fact-checker","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-nissan-fact-checker/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T08:05:17.667Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-nissan-fact-checker/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":"2026-10-09T08:07:25.728Z","emptyReason":null},"readme":"Skill: Fact Checker\n\nOwner: nissan\n\nSummary: Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi...\n\nTags: latest:1.0.4\n\nVersion history:\n\nv1.0.4 | 2026-03-28T04:42:10.049Z | user\n\nAdd security_notes: local-only verification, subprocess is bundled Python script\n\nv1.0.3 | 2026-03-28T03:54:28.755Z | user\n\nFrontmatter fix: corrected malformed metadata block, added proper YAML network/subprocess flags\n\nv1.0.2 | 2026-03-01T21:09:30.578Z | user\n\nAdded complete frontmatter with security declarations\n\nv1.0.1 | 2026-02-26T22:10:50.047Z | user\n\nAdded metadata block with network disclosure (no outbound calls)\n\nv1.0.0 | 2026-02-26T21:38:52.899Z | auto\n\n- Initial release of the fact-checker skill.\n- Automatically identifies and cross-references numeric, model, date, score, and percentage claims in markdown drafts.\n- Verifies claims against FINDINGS.md, live API data, score files, memory logs, and git history.\n- Outputs a clear verification report categorizing claims as CONFIRMED, UNVERIFIABLE, or CONTRADICTED.\n- Summarizes results and flags contradicted claims with suggested corrections.\n\nArchive index:\n\nArchive v1.0.4: 5 files, 13143 bytes\n\nFiles: scripts/fact_check.py (21144b), scripts/test_fact_check.py (19342b), skill-card.md (2386b), SKILL.md (3347b), _meta.json (131b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: fact-checker\nversion: 1.0.3\ndescription: |\n  Verify claims, numbers, and facts in markdown drafts against source data.\n  Use when: reviewing blog posts, reports, or documentation for accuracy\n  before publication. Cross-references against FINDINGS.md, live APIs,\n  scored run files, memory logs, and git history.\nauthor: nissan\ntags:\n  - fact-checking\n  - content\n  - verification\nrequires:\n  bins:\n    - python3\nmetadata:\n  openclaw:\n    emoji: \"🔍\"\n    network:\n      outbound: false\n      reason: \"All verification against local files and APIs only\"\n    subprocess:\n      note: \"Runs python3 scripts for verification — legitimate use\"\n    security_notes: \"All operations are performed locally. No data leaves the user's machine. Verification cross-references local files, local git history, and a local API (localhost). The subprocess note is for running the bundled Python fact-check script — not arbitrary code execution.\"\nallowed-tools:\n  - Read\n  - exec\n---\n**Last used:** 2026-03-24\n**Memory references:** 1\n**Status:** Active\n\n\n# Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim\n(numbers, dates, model names, scores, causal statements) and cross-references\nthem against available source data to produce a verification report.\n\n## Usage\n\n```bash\npython3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md\n```\n\n## What It Checks\n\n### Claim types extracted\n- **Numeric claims** — integers and floats with surrounding context\n- **Model references** — `model/task` (phi4/classify) and `model:tag` (phi4:latest)\n- **Dates** — `YYYY-MM-DD` format\n- **Score values** — decimal scores like `0.923`, `1.000`\n- **Percentages** — `42%`, `95.3%`\n\n### Source data consulted (in priority order)\n1. `projects/hybrid-control-plane/FINDINGS.md` — primary source of truth\n2. Control Plane `/status` API at `http://localhost:8765/status` — live scored run data\n3. `projects/hybrid-control-plane/data/scores/*.json` — raw scored run files on disk\n4. `memory/*.md` — daily logs with timestamps and decisions\n5. `git log` in `projects/hybrid-control-plane/` — commit hashes, dates, authorship\n6. `projects/hybrid-control-plane/CHANGELOG.md` — sprint history\n\n## Output Format\n\nEach claim produces one line:\n\n```\n✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)\n```\n\nFollowed by a summary count of confirmed / unverifiable / contradicted claims.\n\n## When To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or\ndocumentation file — run this skill and present the report to the user.\nIf any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\n## Instructions for Agent\n\n1. Run the script with the path to the draft file.\n2. Parse the output report.\n3. Summarise key findings — especially any ❌ CONTRADICTED claims.\n4. Suggest specific corrections with the correct values from the evidence.\n5. If the `/status` API is unavailable, note it and rely on FINDINGS.md + score files.\n\nFile v1.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn72rbtybr3jzhcj2260qz6p2181x1mr\",\n  \"slug\": \"fact-checker\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1774672930049\n}\n\nFile v1.0.4:skill-card.md\n\n## Description:\n\nVerify claims, numbers, and facts in markdown drafts against local source data before publication.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[nissan](https://clawhub.ai/user/nissan)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, editors, and documentation authors use this skill to check markdown drafts for verifiable numeric claims, dates, model references, scores, and percentages before publication. It produces a report that highlights confirmed, unverifiable, and contradicted claims with suggested corrections when contradictions are found.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can read broad workspace evidence, including memory logs that may contain private or unrelated information.\n\nMitigation: Review the skill before installation and run it only in workspaces where those local evidence sources are appropriate for the draft being checked.\n\nRisk: The skill automatically queries a localhost status API when available.\n\nMitigation: Use it when the local service is expected, and treat unavailable API data as a normal condition that shifts verification to local files.\n\nRisk: Fact-check results can be incomplete when source files, score data, logs, or the local API are missing or stale.\n\nMitigation: Review unverifiable and contradicted claims manually before publishing, and confirm corrections against the underlying source data.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/nissan/skills/fact-checker)\n- [Publisher Profile](https://clawhub.ai/user/nissan)\n- [Control Plane status API](http://localhost:8765/status)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown verification report with per-claim statuses and a summary of confirmed, unverifiable, and contradicted claims.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Can print the report to stdout or write it to a markdown file when an output path is provided.]\n\n## Skill Version(s):\n\n1.0.4 (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\nArchive v1.0.3: 4 files, 11762 bytes\n\nFiles: scripts/fact_check.py (21144b), scripts/test_fact_check.py (19342b), SKILL.md (3055b), _meta.json (131b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: fact-checker\nversion: 1.0.1\ndescription: |\n  Verify claims, numbers, and facts in markdown drafts against source data.\n  Use when: reviewing blog posts, reports, or documentation for accuracy\n  before publication. Cross-references against FINDINGS.md, live APIs,\n  scored run files, memory logs, and git history.\nauthor: nissan\ntags:\n  - fact-checking\n  - content\n  - verification\nrequires:\n  bins:\n    - python3\nmetadata:\n  openclaw:\n    emoji: \"🔍\"\n    network:\n      outbound: false\n      reason: \"All verification against local files and APIs only\"\n    subprocess:\n      note: \"Runs python3 scripts for verification — legitimate use\"\nallowed-tools:\n  - Read\n  - exec\n---\n**Last used:** 2026-03-24\n**Memory references:** 1\n**Status:** Active\n\n\n# Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim\n(numbers, dates, model names, scores, causal statements) and cross-references\nthem against available source data to produce a verification report.\n\n## Usage\n\n```bash\npython3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md\n```\n\n## What It Checks\n\n### Claim types extracted\n- **Numeric claims** — integers and floats with surrounding context\n- **Model references** — `model/task` (phi4/classify) and `model:tag` (phi4:latest)\n- **Dates** — `YYYY-MM-DD` format\n- **Score values** — decimal scores like `0.923`, `1.000`\n- **Percentages** — `42%`, `95.3%`\n\n### Source data consulted (in priority order)\n1. `projects/hybrid-control-plane/FINDINGS.md` — primary source of truth\n2. Control Plane `/status` API at `http://localhost:8765/status` — live scored run data\n3. `projects/hybrid-control-plane/data/scores/*.json` — raw scored run files on disk\n4. `memory/*.md` — daily logs with timestamps and decisions\n5. `git log` in `projects/hybrid-control-plane/` — commit hashes, dates, authorship\n6. `projects/hybrid-control-plane/CHANGELOG.md` — sprint history\n\n## Output Format\n\nEach claim produces one line:\n\n```\n✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)\n```\n\nFollowed by a summary count of confirmed / unverifiable / contradicted claims.\n\n## When To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or\ndocumentation file — run this skill and present the report to the user.\nIf any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\n## Instructions for Agent\n\n1. Run the script with the path to the draft file.\n2. Parse the output report.\n3. Summarise key findings — especially any ❌ CONTRADICTED claims.\n4. Suggest specific corrections with the correct values from the evidence.\n5. If the `/status` API is unavailable, note it and rely on FINDINGS.md + score files.\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn72rbtybr3jzhcj2260qz6p2181x1mr\",\n  \"slug\": \"fact-checker\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1774670068755\n}\n\nArchive v1.0.2: 4 files, 11675 bytes\n\nFiles: scripts/fact_check.py (21144b), scripts/test_fact_check.py (19342b), SKILL.md (2924b), _meta.json (131b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: fact-checker\nversion: 1.0.2\ndescription: Verify factual claims in content using web search and source cross-referencing. Use when reviewing content for accuracy before publishing.\nmetadata:\n  {\n      \"openclaw\": {\n            \"emoji\": \"\\u2705\",\n            \"requires\": {\n                  \"bins\": [\n                        \"python3\"\n                  ],\n                  \"env\": []\n            },\n            \"primaryEnv\": null,\n            \"network\": {\n                  \"outbound\": true,\n                  \"reason\": \"Searches the web to verify factual claims. Uses Tavily or web_search.\"\n            }\n      }\n}\n---\n\n\n# Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim\n(numbers, dates, model names, scores, causal statements) and cross-references\nthem against available source data to produce a verification report.\n\n## Usage\n\n```bash\npython3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md\n```\n\n## What It Checks\n\n### Claim types extracted\n- **Numeric claims** — integers and floats with surrounding context\n- **Model references** — `model/task` (phi4/classify) and `model:tag` (phi4:latest)\n- **Dates** — `YYYY-MM-DD` format\n- **Score values** — decimal scores like `0.923`, `1.000`\n- **Percentages** — `42%`, `95.3%`\n\n### Source data consulted (in priority order)\n1. `projects/hybrid-control-plane/FINDINGS.md` — primary source of truth\n2. Control Plane `/status` API at `http://localhost:8765/status` — live scored run data\n3. `projects/hybrid-control-plane/data/scores/*.json` — raw scored run files on disk\n4. `memory/*.md` — daily logs with timestamps and decisions\n5. `git log` in `projects/hybrid-control-plane/` — commit hashes, dates, authorship\n6. `projects/hybrid-control-plane/CHANGELOG.md` — sprint history\n\n## Output Format\n\nEach claim produces one line:\n\n```\n✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)\n```\n\nFollowed by a summary count of confirmed / unverifiable / contradicted claims.\n\n## When To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or\ndocumentation file — run this skill and present the report to the user.\nIf any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\n## Instructions for Agent\n\n1. Run the script with the path to the draft file.\n2. Parse the output report.\n3. Summarise key findings — especially any ❌ CONTRADICTED claims.\n4. Suggest specific corrections with the correct values from the evidence.\n5. If the `/status` API is unavailable, note it and rely on FINDINGS.md + score files.\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn72rbtybr3jzhcj2260qz6p2181x1mr\",\n  \"slug\": \"fact-checker\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1772399370578\n}\n\nArchive v1.0.1: 4 files, 11693 bytes\n\nFiles: scripts/fact_check.py (21144b), scripts/test_fact_check.py (19342b), SKILL.md (2897b), _meta.json (131b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: fact-checker\nversion: 1.0.1\ndescription: |\n  Verify claims, numbers, and facts in markdown drafts against source data.\nmetadata:\n  {\n    \"openclaw\": {\n      \"emoji\": \"🔍\",\n      \"requires\": { \"bins\": [\"python3\"] },\n      \"network\": { \"outbound\": false, \"reason\": \"All verification is done against local files and APIs. No external network calls.\" }\n    }\n  }\n  Use when: reviewing blog posts, reports, or documentation for accuracy\n  before publication. Cross-references against FINDINGS.md, live APIs,\n  scored run files, memory logs, and git history.\nallowed-tools:\n  - Read\n  - exec\n---\n\n# Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim\n(numbers, dates, model names, scores, causal statements) and cross-references\nthem against available source data to produce a verification report.\n\n## Usage\n\n```bash\npython3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md\n```\n\n## What It Checks\n\n### Claim types extracted\n- **Numeric claims** — integers and floats with surrounding context\n- **Model references** — `model/task` (phi4/classify) and `model:tag` (phi4:latest)\n- **Dates** — `YYYY-MM-DD` format\n- **Score values** — decimal scores like `0.923`, `1.000`\n- **Percentages** — `42%`, `95.3%`\n\n### Source data consulted (in priority order)\n1. `projects/hybrid-control-plane/FINDINGS.md` — primary source of truth\n2. Control Plane `/status` API at `http://localhost:8765/status` — live scored run data\n3. `projects/hybrid-control-plane/data/scores/*.json` — raw scored run files on disk\n4. `memory/*.md` — daily logs with timestamps and decisions\n5. `git log` in `projects/hybrid-control-plane/` — commit hashes, dates, authorship\n6. `projects/hybrid-control-plane/CHANGELOG.md` — sprint history\n\n## Output Format\n\nEach claim produces one line:\n\n```\n✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)\n```\n\nFollowed by a summary count of confirmed / unverifiable / contradicted claims.\n\n## When To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or\ndocumentation file — run this skill and present the report to the user.\nIf any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\n## Instructions for Agent\n\n1. Run the script with the path to the draft file.\n2. Parse the output report.\n3. Summarise key findings — especially any ❌ CONTRADICTED claims.\n4. Suggest specific corrections with the correct values from the evidence.\n5. If the `/status` API is unavailable, note it and rely on FINDINGS.md + score files.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn72rbtybr3jzhcj2260qz6p2181x1mr\",\n  \"slug\": \"fact-checker\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1772143850047\n}\n\nArchive v1.0.0: 4 files, 11565 bytes\n\nFiles: scripts/fact_check.py (21144b), scripts/test_fact_check.py (19342b), SKILL.md (2655b), _meta.json (131b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: fact-checker\nversion: 1.0.0\ndescription: |\n  Verify claims, numbers, and facts in markdown drafts against source data.\n  Use when: reviewing blog posts, reports, or documentation for accuracy\n  before publication. Cross-references against FINDINGS.md, live APIs,\n  scored run files, memory logs, and git history.\nallowed-tools:\n  - Read\n  - exec\n---\n\n# Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim\n(numbers, dates, model names, scores, causal statements) and cross-references\nthem against available source data to produce a verification report.\n\n## Usage\n\n```bash\npython3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md\n```\n\n## What It Checks\n\n### Claim types extracted\n- **Numeric claims** — integers and floats with surrounding context\n- **Model references** — `model/task` (phi4/classify) and `model:tag` (phi4:latest)\n- **Dates** — `YYYY-MM-DD` format\n- **Score values** — decimal scores like `0.923`, `1.000`\n- **Percentages** — `42%`, `95.3%`\n\n### Source data consulted (in priority order)\n1. `projects/hybrid-control-plane/FINDINGS.md` — primary source of truth\n2. Control Plane `/status` API at `http://localhost:8765/status` — live scored run data\n3. `projects/hybrid-control-plane/data/scores/*.json` — raw scored run files on disk\n4. `memory/*.md` — daily logs with timestamps and decisions\n5. `git log` in `projects/hybrid-control-plane/` — commit hashes, dates, authorship\n6. `projects/hybrid-control-plane/CHANGELOG.md` — sprint history\n\n## Output Format\n\nEach claim produces one line:\n\n```\n✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)\n```\n\nFollowed by a summary count of confirmed / unverifiable / contradicted claims.\n\n## When To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or\ndocumentation file — run this skill and present the report to the user.\nIf any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\n## Instructions for Agent\n\n1. Run the script with the path to the draft file.\n2. Parse the output report.\n3. Summarise key findings — especially any ❌ CONTRADICTED claims.\n4. Suggest specific corrections with the correct values from the evidence.\n5. If the `/status` API is unavailable, note it and rely on FINDINGS.md + score files.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn72rbtybr3jzhcj2260qz6p2181x1mr\",\n  \"slug\": \"fact-checker\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1772141932899\n}","readmeExcerpt":"Skill: Fact Checker Owner: nissan Summary: Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-03-28T04:42:10.049Z | user Add security_notes: local-only verification, subprocess is bundled Python script v1.0.3 | 2026-03-28T03:54:28.755Z | user Frontmatter fix: ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md"},{"language":"text","snippet":"✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)"},{"language":"bash","snippet":"python3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md"},{"language":"text","snippet":"✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)"},{"language":"bash","snippet":"python3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md"},{"language":"text","snippet":"✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: fact-checker\nversion: 1.0.3\ndescription: |\n  Verify claims, numbers, and facts in markdown drafts against source data.\n  Use when: reviewing blog posts, reports, or documentation for accuracy\n  before publication. Cross-references against FINDINGS.md, live APIs,\n  scored run files, memory logs, and git history.\nauthor: nissan\ntags:\n  - fact-checking\n  - content\n  - verification\nrequires:\n  bins:\n    - python3\nmetadata:\n  openclaw:\n    emoji: \"🔍\"\n    network:\n      outbound: false\n      reason: \"All verification against local files and APIs only\"\n    subprocess:\n      note: \"Runs python3 scripts for verification — legitimate use\"\n    security_notes: \"All operations are performed locally. No data leaves the user's machine. Verification cross-references local files, local git history, and a local API (localhost). The subprocess note is for running the bundled Python fact-check script — not arbitrary code execution.\"\nallowed-tools:\n  - Read\n  - exec\n---\n**Last used:** 2026-03-24\n**Memory references:** 1\n**Status:** Active\n\n\n# Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim\n(numbers, dates, model names, scores, causal statements) and cross-references\nthem against available source data to produce a verification report.\n\n## Usage\n\n```bash\npython3 skills/fact-checker/scripts/fact_check.py <draft.md>\npython3 skills/fact-checker/scripts/fact_check.py <draft.md> --output report.md\n```\n\n## What It Checks\n\n### Claim types extracted\n- **Numeric claims** — integers and floats with surrounding context\n- **Model references** — `model/task` (phi4/classify) and `model:tag` (phi4:latest)\n- **Dates** — `YYYY-MM-DD` format\n- **Score values** — decimal scores like `0.923`, `1.000`\n- **Percentages** — `42%`, `95.3%`\n\n### Source data consulted (in priority order)\n1. `projects/hybrid-control-plane/FINDINGS.md` — primary source of truth\n2. Control Plane `/status` API at `http://localhost:8765/status` — live scored run data\n3. `projects/hybrid-control-plane/data/scores/*.json` — raw scored run files on disk\n4. `memory/*.md` — daily logs with timestamps and decisions\n5. `git log` in `projects/hybrid-control-plane/` — commit hashes, dates, authorship\n6. `projects/hybrid-control-plane/CHANGELOG.md` — sprint history\n\n## Output Format\n\nEach claim produces one line:\n\n```\n✅ CONFIRMED:    \"phi4/classify scored 1.000\" → /status API: phi4_latest_classify mean=1.000 n=23\n⚠️ UNVERIFIABLE: \"this took about a day\" → no timestamp correlation found in logs\n❌ CONTRADICTED: \"909 runs\" → /status API shows 958 total runs (stale number?)\n```\n\nFollowed by a summary count of confirmed / unverifiable / contradicted claims.\n\n## When To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or\ndocumentation file — run this skill and present the report to the user.\nIf any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\n## Instructions for Agent\n\n1. Run the"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72rbtybr3jzhcj2260qz6p2181x1mr\",\n  \"slug\": \"fact-checker\",\n  \"version\": \"1.0.4\",\n  \"publishedAt\": 1774672930049\n}"},{"path":"skill-card.md","content":"## Description:\n\nVerify claims, numbers, and facts in markdown drafts against local source data before publication.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[nissan](https://clawhub.ai/user/nissan)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, editors, and documentation authors use this skill to check markdown drafts for verifiable numeric claims, dates, model references, scores, and percentages before publication. It produces a report that highlights confirmed, unverifiable, and contradicted claims with suggested corrections when contradictions are found.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can read broad workspace evidence, including memory logs that may contain private or unrelated information.\n\nMitigation: Review the skill before installation and run it only in workspaces where those local evidence sources are appropriate for the draft being checked.\n\nRisk: The skill automatically queries a localhost status API when available.\n\nMitigation: Use it when the local service is expected, and treat unavailable API data as a normal condition that shifts verification to local files.\n\nRisk: Fact-check results can be incomplete when source files, score data, logs, or the local API are missing or stale.\n\nMitigation: Review unverifiable and contradicted claims manually before publishing, and confirm corrections against the underlying source data.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/nissan/skills/fact-checker)\n- [Publisher Profile](https://clawhub.ai/user/nissan)\n- [Control Plane status API](http://localhost:8765/status)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown verification report with per-claim statuses and a summary of confirmed, unverifiable, and contradicted claims.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Can print the report to stdout or write it to a markdown file when an output path is provided.]\n\n## Skill Version(s):\n\n1.0.4 (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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi... Skill: Fact Checker Owner: nissan Summary: Verify claims, numbers, and facts in markdown drafts against source data. Use when: reviewing blog posts, reports, or documentation for accuracy before publi... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-03-28T04:42:10.049Z | user Add security_notes: local-only verification, subprocess is bundled Python script v1.0.3 | 2026-03-28T03:54:28.755Z | user Frontmatter fix:","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1129,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T08:07:25.728Z","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":"2026-10-09T08:07:25.728Z","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":"2026-10-10T08:05:17.668Z","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"}]}}}