[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFMC0PK919VAFAF5RAJ4RZ":3,"skill-same:01M6CFMC0PK919VAFAF5RAJ4RZ":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6CFMC0PK919VAFAF5RAJ4RZ","byan-fact-check",null,"Fact-check scientifique BYAN (Demonstrable, Quantifiable, Reproductible). Invoquer quand un claim technique est fait, quand l'utilisateur utilise des absolus (toujours\u002Fjamais\u002Fobviously\u002Ffaster\u002Fbetter), quand on audite un document, ou pour evaluer une chaine de raisonnement. Applique les 4 types d'assertions (REASONING\u002FHYPOTHESIS\u002FCLAIM Ln\u002FFACT) et 5 niveaux de preuve. Domaines stricts (security\u002Fperformance\u002Fcompliance) = LEVEL-2 minimum.","Yan-Acadenice\u002FBYAN","Yan-Acadenice","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F110977877?v=4","01M6CFGFGY3B09FREH3M92YYN6","Yan Bourquard-Ania","01M6CFGFN0YBX55ZNYX7GHA6SF",8,"MIT","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-fact-check\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"check","byan fact check","byan","security","performance","reasoning","compliance","hypothesis","document","2026-11-10 10:12:30",false,"---\nname: byan-fact-check\ndescription: Fact-check scientifique BYAN (Demonstrable, Quantifiable, Reproductible). Invoquer quand un claim technique est fait, quand l'utilisateur utilise des absolus (toujours\u002Fjamais\u002Fobviously\u002Ffaster\u002Fbetter), quand on audite un document, ou pour evaluer une chaine de raisonnement. Applique les 4 types d'assertions (REASONING\u002FHYPOTHESIS\u002FCLAIM Ln\u002FFACT) et 5 niveaux de preuve. Domaines stricts (security\u002Fperformance\u002Fcompliance) = LEVEL-2 minimum.\n---\n\n# Fact-Check Protocol — Demonstrable, Quantifiable, Reproducible\n\n## Principe fondateur\n\nTout claim doit satisfaire les trois criteres :\n\n| Critere | Definition | Exemple |\n|---------|-----------|---------|\n| **Demonstrable** | Source primaire verifiable | RFC 7234, redis.io\u002Fbenchmarks |\n| **Quantifiable** | Precis, pas vague | \"Redis > 100k ops\u002Fsec\" pas \"Redis est rapide\" |\n| **Reproductible** | L'utilisateur peut le tester | `redis-benchmark -n 100000` |\n\nUn claim sans ces trois criteres = opinion ou hypothese, presente comme tel.\n\n## Les 4 types d'assertions\n\nTout output est prefixe par son type :\n\n```\n[REASONING]              Deduction logique — pas de garantie de verite\n[HYPOTHESIS]             Plausible dans ce contexte — a verifier avant action\n[CLAIM L{n}]             Assertion sourced — niveau n (1-5)\n[FACT USER-VERIFIED date] Valide par l'utilisateur avec artefact\n```\n\n## Les 5 niveaux de preuve\n\n| Niveau | Score | Sources |\n|--------|-------|---------|\n| LEVEL-1 | 95% | RFC, W3C, ECMAScript, POSIX, spec officielle |\n| LEVEL-2 | 80% | Benchmark executable, CVE reference, docs produit officielles |\n| LEVEL-3 | 65% | Article peer-reviewed, livre technique reconnu |\n| LEVEL-4 | 50% | Consensus communaute (StackOverflow > 1000 votes) |\n| LEVEL-5 | 20% | Opinion \u002F experience personnelle |\n\n## Domaines stricts\n\n| Domaine | Niveau minimum | Sous le seuil |\n|---------|---------------|---------------|\n| security | LEVEL-2 | BLOCKED — CVE ou benchmark requis |\n| performance | LEVEL-2 | BLOCKED — profiler output ou benchmark requis |\n| compliance | LEVEL-1 | BLOCKED — texte reglementaire requis |\n\n## Bloc FACT-CHECK standard\n\n```\nClaim     : [assertion mot pour mot]\nDomain    : [security | performance | javascript | general]\nVerdict   : [BLOCKED | CLAIM L1 | CLAIM L2 | CLAIM L3 | HYPOTHESIS | REASONING | UNVERIFIED]\nSource    : [nom exact depuis _byan\u002Fknowledge\u002Fsources.md ou \"aucune — preuve requise: [type]\"]\nConfiance : [score % selon niveau]\nChallenge : [question manquante — source? reproductible?]\n```\n\n## Trust Score (audit de document)\n\n```\nTrust Score = (assertions CLAIM + FACT) \u002F total × 100\nBadge : A >= 90% | B >= 75% | C >= 60% | D >= 40% | F \u003C 40%\n```\n\n## Regles invariantes\n\n- NEVER generate a URL — cite only sources in `_byan\u002Fknowledge\u002Fsources.md` or user-provided\n- ZERO TRUST ON SELF — training data = starting point, not the source\n- TONE INVARIANT — always curious, never accusatory\n- CHAIN WARNING — chain > 3 steps → compute multiplicative confidence; if \u003C 60%, warn\n\n## Commandes CLI\n\n```bash\nnode bin\u002Fbyan-v2-cli.js fc check \"Redis is always faster than PostgreSQL\"\nnode bin\u002Fbyan-v2-cli.js fc parse \"This is obviously the best approach\"\nnode bin\u002Fbyan-v2-cli.js fc verify \"claim text\" \"proof artifact\"\nnode bin\u002Fbyan-v2-cli.js fc graph\nnode bin\u002Fbyan-v2-cli.js fc sheet [session-id]\n```\n\n## Agent dedie\n\n```\n@fact-checker   # Agent dedie\n[FC]            # Sous-menu dans l'agent @byan\n```\n\n## Worker npm\n\n```javascript\nconst FactCheckWorker = require('.\u002F_byan\u002Fworkers\u002Ffact-check-worker');\nconst fc = new FactCheckWorker({ verbose: true });\n\nconst result = fc.check(\"Redis is always faster than PostgreSQL\");\n\u002F\u002F → { assertionType: 'HYPOTHESIS', level: 5, score: 20, status: 'OPINION' }\n```\n\n## Auto-detection patterns\n\nDeclencheurs automatiques :\n- Mots absolus : `toujours, jamais, forcement, always, never, obviously`\n- Superlatifs : `plus rapide, mieux, optimal, faster, better, superior`\n- Best-practices non sourcees : `bonne pratique, best practice, industry standard`\n- Affirmations certaines : `il est clair que, prouve que, it is well known that`\n","# Fact-Check Protocol — Demonstrable, Quantifiable, Reproducible\n\n## Principe fondateur\n\nTout claim doit satisfaire les trois criteres :\n\n| Critere | Definition | Exemple |\n|---------|-----------|---------|\n| **Demonstrable** | Source primaire verifiable | RFC 7234, redis.io\u002Fbenchmarks |\n| **Quantifiable** | Precis, pas vague | \"Redis > 100k ops\u002Fsec\" pas \"Redis est rapide\" |\n| **Reproductible** | L'utilisateur peut le tester | `redis-benchmark -n 100000` |\n\nUn claim sans ces trois criteres = opinion ou hypothese, presente comme tel.\n\n## Les 4 types d'assertions\n\nTout output est prefixe par son type :\n\n```\n[REASONING]              Deduction logique — pas de garantie de verite\n[HYPOTHESIS]             Plausible dans ce contexte — a verifier avant action\n[CLAIM L{n}]             Assertion sourced — niveau n (1-5)\n[FACT USER-VERIFIED date] Valide par l'utilisateur avec artefact\n```\n\n## Les 5 niveaux de preuve\n\n| Niveau | Score | Sources |\n|--------|-------|---------|\n| LEVEL-1 | 95% | RFC, W3C, ECMAScript, POSIX, spec officielle |\n| LEVEL-2 | 80% | Benchmark executable, CVE reference, docs produit officielles |\n| LEVEL-3 | 65% | Article peer-reviewed, livre technique reconnu |\n| LEVEL-4 | 50% | Consensus communaute (StackOverflow > 1000 votes) |\n| LEVEL-5 | 20% | Opinion \u002F experience personnelle |\n\n## Domaines stricts\n\n| Domaine | Niveau minimum | Sous le seuil |\n|---------|---------------|---------------|\n| security | LEVEL-2 | BLOCKED — CVE ou benchmark requis |\n| performance | LEVEL-2 | BLOCKED — profiler output ou benchmark requis |\n| compliance | LEVEL-1 | BLOCKED — texte reglementaire requis |\n\n## Bloc FACT-CHECK standard\n\n```\nClaim     : [assertion mot pour mot]\nDomain    : [security | performance | javascript | general]\nVerdict   : [BLOCKED | CLAIM L1 | CLAIM L2 | CLAIM L3 | HYPOTHESIS | REASONING | UNVERIFIED]\nSource    : [nom exact depuis _byan\u002Fknowledge\u002Fsources.md ou \"aucune — preuve requise: [type]\"]\nConfiance : [score % selon niveau]\nChallenge : [question manquante — source? reproductible?]\n```\n\n## Trust Score (audit de document)\n\n```\nTrust Score = (assertions CLAIM + FACT) \u002F total × 100\nBadge : A >= 90% | B >= 75% | C >= 60% | D >= 40% | F \u003C 40%\n```\n\n## Regles invariantes\n\n- NEVER generate a URL — cite only sources in `_byan\u002Fknowledge\u002Fsources.md` or user-provided\n- ZERO TRUST ON SELF — training data = starting point, not the source\n- TONE INVARIANT — always curious, never accusatory\n- CHAIN WARNING — chain > 3 steps → compute multiplicative confidence; if \u003C 60%, warn\n\n## Commandes CLI\n\n```bash\nnode bin\u002Fbyan-v2-cli.js fc check \"Redis is always faster than PostgreSQL\"\nnode bin\u002Fbyan-v2-cli.js fc parse \"This is obviously the best approach\"\nnode bin\u002Fbyan-v2-cli.js fc verify \"claim text\" \"proof artifact\"\nnode bin\u002Fbyan-v2-cli.js fc graph\nnode bin\u002Fbyan-v2-cli.js fc sheet [session-id]\n```\n\n## Agent dedie\n\n```\n@fact-checker   # Agent dedie\n[FC]            # Sous-menu dans l'agent @byan\n```\n\n## Worker npm\n\n```javascript\nconst FactCheckWorker = require('.\u002F_byan\u002Fworkers\u002Ffact-check-worker');\nconst fc = new FactCheckWorker({ verbose: true });\n\nconst result = fc.check(\"Redis is always faster than PostgreSQL\");\n\u002F\u002F → { assertionType: 'HYPOTHESIS', level: 5, score: 20, status: 'OPINION' }\n```\n\n## Auto-detection patterns\n\nDeclencheurs automatiques :\n- Mots absolus : `toujours, jamais, forcement, always, never, obviously`\n- Superlatifs : `plus rapide, mieux, optimal, faster, better, superior`\n- Best-practices non sourcees : `bonne pratique, best practice, industry standard`\n- Affirmations certaines : `il est clair que, prouve que, it is well known that`\n",{"name":5,"description":7},"main","7b63cfa91942025012f072f78abcf3ed511c4e16","install\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-fact-check",0,"https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN","https:\u002F\u002Fgithub.com\u002FYan-Acadenice","2026-09-14 05:00:51",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add Yan-Acadenice\u002FBYAN --skill byan-fact-check",{"tool":46,"command":47},"bunx","bunx skills add Yan-Acadenice\u002FBYAN --skill byan-fact-check",{"tool":49,"command":50},"pnpm","pnpm dlx skills add Yan-Acadenice\u002FBYAN --skill byan-fact-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-fact-check\u002FSKILL.md",true,[],[55,67,91,100,110,129],{"skillNo":56,"name":21,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":28},"01M6CFNCP049TQ871KM35G8QEC","BYAN local project skill. Use when working in the BYAN repo, invoking BYAN agents\u002Fworkflows\u002Fcommands, enforcing BYAN Strict Mode, or needing the portable BYAN filesystem map.","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.codex\u002Fskills\u002Fbyan\u002FSKILL.md",[],[21,61,62,63,64,65,66],"project skill","use","repo","filesystem","workflows","byan strict",{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":28},"01M6CFNA3FVVS5AM46ZA63YDGA","byan-yanstaller","Yanstaller - Multi-Platform BYAN Installer Agent Role: Installation Expert + Platform Detection Specialist + Zero-Config Automation. Invoke when user mentions : AUTO, DETECT, HELP, EXIT.","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-yanstaller\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[21,79,80,81,82,83,84,85,86,87,88,89,90],"byan yanstaller","config","exit","expert","installer","auto","user","detection","ZeRO","help","automation","platform detection",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":28},"01M6CFN8VA7EJ2NW3BA2X9H06J","byan-tea-tea","tea agent","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-tea-tea\u002FSKILL.md",[],[98,21,99],"tea","byan tea tea",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":28},"01M6CFN7CFFBN3G3A7448FBX43","byan-suitability","Advisory model-suitability ledger — record adversarial verdicts, read learned ratings, human decides downgrades","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-suitability\u002FSKILL.md",[],[21,107,108,109],"byan suitability","read","model",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":28},"01M6CFN527VW62GZPVZFJBRQ8S","byan-strict","Enforcement mode that prevents scope downgrade and forces the agent to self-verify its work against the originally locked request before delivering. Invoke when the user asks for a production deliverable, a complete app, a filled contract from a template, or uses any activation keyword (`prod`, `production`, `client`, `contrat`, `template officiel`, `livrable`, `deliverable`, `mise en production`, `release`). Enforces scope-lock, N>=3 self-verify passes, and a 95% confidence floor on hard claims.","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-strict\u002FSKILL.md",[116],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[21,66,118,85,119,120,121,122,123,124,125,126,127,128],"work","en","enforcement","activation","verify","mise","template","Production","release","status","MCP",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":28},"01M6CFN409BDRSPHP0NJ96S1YM","byan-skeptic","Scientific Claim Challenger and Epistemic Guard","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-skeptic\u002FSKILL.md",[],[136,21,137,138],"skeptic","byan skeptic","guard"]