{ "schemaVersion": "1.0", "item": { "slug": "fact-checker", "name": "Fact Checker", "source": "tencent", "type": "skill", "category": "数据分析", "sourceUrl": "https://clawhub.ai/nissan/fact-checker", "canonicalUrl": "https://clawhub.ai/nissan/fact-checker", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/fact-checker", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fact-checker", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/fact_check.py", "scripts/test_fact_check.py" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/fact-checker" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/fact-checker", "agentPageUrl": "https://openagent3.xyz/skills/fact-checker/agent", "manifestUrl": "https://openagent3.xyz/skills/fact-checker/agent.json", "briefUrl": "https://openagent3.xyz/skills/fact-checker/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Fact-Checker: Verify Markdown Claims Against Source Data", "body": "Given 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." }, { "title": "Usage", "body": "python3 skills/fact-checker/scripts/fact_check.py \npython3 skills/fact-checker/scripts/fact_check.py --output report.md" }, { "title": "Claim types extracted", "body": "Numeric claims — integers and floats with surrounding context\nModel references — model/task (phi4/classify) and model:tag (phi4:latest)\nDates — YYYY-MM-DD format\nScore values — decimal scores like 0.923, 1.000\nPercentages — 42%, 95.3%" }, { "title": "Source data consulted (in priority order)", "body": "projects/hybrid-control-plane/FINDINGS.md — primary source of truth\nControl Plane /status API at http://localhost:8765/status — live scored run data\nprojects/hybrid-control-plane/data/scores/*.json — raw scored run files on disk\nmemory/*.md — daily logs with timestamps and decisions\ngit log in projects/hybrid-control-plane/ — commit hashes, dates, authorship\nprojects/hybrid-control-plane/CHANGELOG.md — sprint history" }, { "title": "Output Format", "body": "Each claim produces one line:\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\nFollowed by a summary count of confirmed / unverifiable / contradicted claims." }, { "title": "When To Use This Skill", "body": "When 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." }, { "title": "Instructions for Agent", "body": "Run the script with the path to the draft file.\nParse the output report.\nSummarise key findings — especially any ❌ CONTRADICTED claims.\nSuggest specific corrections with the correct values from the evidence.\nIf the /status API is unavailable, note it and rely on FINDINGS.md + score files." } ], "body": "Fact-Checker: Verify Markdown Claims Against Source Data\n\nGiven a markdown draft file, this skill extracts every verifiable claim (numbers, dates, model names, scores, causal statements) and cross-references them against available source data to produce a verification report.\n\nUsage\npython3 skills/fact-checker/scripts/fact_check.py \npython3 skills/fact-checker/scripts/fact_check.py --output report.md\n\nWhat It Checks\nClaim types extracted\nNumeric claims — integers and floats with surrounding context\nModel references — model/task (phi4/classify) and model:tag (phi4:latest)\nDates — YYYY-MM-DD format\nScore values — decimal scores like 0.923, 1.000\nPercentages — 42%, 95.3%\nSource data consulted (in priority order)\nprojects/hybrid-control-plane/FINDINGS.md — primary source of truth\nControl Plane /status API at http://localhost:8765/status — live scored run data\nprojects/hybrid-control-plane/data/scores/*.json — raw scored run files on disk\nmemory/*.md — daily logs with timestamps and decisions\ngit log in projects/hybrid-control-plane/ — commit hashes, dates, authorship\nprojects/hybrid-control-plane/CHANGELOG.md — sprint history\nOutput Format\n\nEach claim produces one line:\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\nWhen To Use This Skill\n\nWhen asked to \"fact-check\" or \"verify\" a draft blog post, report, or documentation file — run this skill and present the report to the user. If any claims are ❌ CONTRADICTED, flag them prominently and suggest corrections.\n\nInstructions for Agent\nRun the script with the path to the draft file.\nParse the output report.\nSummarise key findings — especially any ❌ CONTRADICTED claims.\nSuggest specific corrections with the correct values from the evidence.\nIf the /status API is unavailable, note it and rely on FINDINGS.md + score files." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/nissan/fact-checker", "publisherUrl": "https://clawhub.ai/nissan/fact-checker", "owner": "nissan", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/fact-checker", "downloadUrl": "https://openagent3.xyz/downloads/fact-checker", "agentUrl": "https://openagent3.xyz/skills/fact-checker/agent", "manifestUrl": "https://openagent3.xyz/skills/fact-checker/agent.json", "briefUrl": "https://openagent3.xyz/skills/fact-checker/agent.md" } }