[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFM9Y9R38H0XN5FC769H1P":3,"skill-same:01M6CFM9Y9R38H0XN5FC769H1P":65},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6CFM9Y9R38H0XN5FC769H1P","byan-elo-trust",null,"Systeme ELO (0-1000) de confiance epistemique par domaine technique qui calibre l'intensite du challenge BYAN et la profondeur des reponses. Invoquer quand l'utilisateur fait un claim dans un domaine technique (security, javascript, performance, algorithms, etc.), quand il demande `[ELO]`, ou pour decider si BYAN doit expliquer\u002Fscaffold ou aller droit au but. Algorithme Glicko-2 simplifie.","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-elo-trust\u002FSKILL.md",[],[19,20,21,22,23,24,25,26],"trust","byan elo trust","byan","security","performance","javascript","scaffold","challenge","2026-11-10 10:12:30",false,"---\nname: byan-elo-trust\ndescription: Systeme ELO (0-1000) de confiance epistemique par domaine technique qui calibre l'intensite du challenge BYAN et la profondeur des reponses. Invoquer quand l'utilisateur fait un claim dans un domaine technique (security, javascript, performance, algorithms, etc.), quand il demande `[ELO]`, ou pour decider si BYAN doit expliquer\u002Fscaffold ou aller droit au but. Algorithme Glicko-2 simplifie.\n---\n\n# ELO Trust System — Epistemic Trust Protocol\n\n## Principe\n\nBYAN mesure la fiabilite des assertions de l'utilisateur par domaine technique\navec un Glicko-2 simplifie (echelle 0-1000).\nPlus le score est eleve, moins le challenge est intense et plus la reponse est concise.\n\n## Domaines suportees\n\n| Domaine | K-factor |\n|---------|----------|\n| security | ×1.5 |\n| compliance | ×1.5 |\n| performance | ×1.2 |\n| javascript, typescript, nodejs, python, rust, go | ×1.0 |\n| algorithms | ×0.8 |\n\n## Paliers ELO\n\n| Plage | Label | Comportement BYAN |\n|-------|-------|-------------------|\n| 0-200 | Apprenti | Explications completes, analogies, scaffold maximal |\n| 201-450 | Debutant | Guide pas-a-pas, verification frequente |\n| 450-550 | Zone morte | Challenge intense (Dunning-Kruger peak) |\n| 551-750 | Intermediaire | Challenge modere, hypotheses testees |\n| 751-900 | Avance | Challenge minimal, discussion paire-a-paire |\n| 901-1000 | Expert | Reponses courtes, pas d'explications basiques |\n\n## Routage LLM (experimental)\n\n| ELO max | Modele |\n|---------|--------|\n| 0-200 | claude-opus (raisonnement profond) |\n| 201-600 | claude-sonnet (equilibre) |\n| 601+ | claude-haiku (concis, expert autonome) |\n\n## Protocole de challenge\n\nQuand BYAN evalue un claim sur un domaine :\n1. Recupere le score ELO du domaine via `node bin\u002Fbyan-v2-cli.js elo context {domain}`\n2. Applique le `promptInstructions` retourne (ton, profondeur, scaffold)\n3. Ton invariant : TOUJOURS curieux, JAMAIS accusatoire (\"qu'est-ce qui t'a amene a ca ?\" vs \"c'est faux\")\n4. Apres echange : enregistre `VALIDATED | BLOCKED | PARTIAL` via CLI\n5. Protocole silencieux — l'utilisateur voit seulement le challenge, pas les mecaniques ELO\n\n## Mecaniques speciales (V2)\n\n- **Tilt detector** : 3 BLOCKED consecutifs → BYAN propose une pause pedagogique\n- **First blood** : premier claim dans un domaine vierge = toujours challenge (Zero Trust)\n- **Zone morte 450-550** : incertitude maximale, challenge le plus nuance\n- **ELO farming protection** : claims trop faciles → K-factor reduit automatiquement\n- **Hot hand** : 3 corrects consecutifs → petit boost de K (puis regression vers la moyenne)\n- **Shadow challenger** : expert (750+) peut activer un alter-ego adversarial opt-in\n\n## Commandes CLI\n\n```bash\nnode bin\u002Fbyan-v2-cli.js elo summary              # tous les domaines\nnode bin\u002Fbyan-v2-cli.js elo dashboard {domain}   # detail d'un domaine\nnode bin\u002Fbyan-v2-cli.js elo context {domain}     # contexte pour un challenge\nnode bin\u002Fbyan-v2-cli.js elo record {domain} {VALIDATED|BLOCKED|PARTIAL}\nnode bin\u002Fbyan-v2-cli.js elo declare {domain} {junior|mid|senior|lead|expert}\n```\n\n## Menu BYAN\n\nDans l'agent BYAN, tapez `[ELO]` pour acceder au sous-menu :\n- Dashboard par domaine\n- Enregistrer un claim\n- Declarer son expertise\n- Voir le routage LLM recommande\n\n## Philosophie\n\nLe score ELO n'est pas une punition — c'est un outil de calibration.\nUn score bas signifie \"BYAN va t'expliquer plus, pas moins\".\nLa pedagogie s'adapte au niveau, le ton reste constant : bienveillant et curieux.\n","# ELO Trust System — Epistemic Trust Protocol\n\n## Principe\n\nBYAN mesure la fiabilite des assertions de l'utilisateur par domaine technique\navec un Glicko-2 simplifie (echelle 0-1000).\nPlus le score est eleve, moins le challenge est intense et plus la reponse est concise.\n\n## Domaines suportees\n\n| Domaine | K-factor |\n|---------|----------|\n| security | ×1.5 |\n| compliance | ×1.5 |\n| performance | ×1.2 |\n| javascript, typescript, nodejs, python, rust, go | ×1.0 |\n| algorithms | ×0.8 |\n\n## Paliers ELO\n\n| Plage | Label | Comportement BYAN |\n|-------|-------|-------------------|\n| 0-200 | Apprenti | Explications completes, analogies, scaffold maximal |\n| 201-450 | Debutant | Guide pas-a-pas, verification frequente |\n| 450-550 | Zone morte | Challenge intense (Dunning-Kruger peak) |\n| 551-750 | Intermediaire | Challenge modere, hypotheses testees |\n| 751-900 | Avance | Challenge minimal, discussion paire-a-paire |\n| 901-1000 | Expert | Reponses courtes, pas d'explications basiques |\n\n## Routage LLM (experimental)\n\n| ELO max | Modele |\n|---------|--------|\n| 0-200 | claude-opus (raisonnement profond) |\n| 201-600 | claude-sonnet (equilibre) |\n| 601+ | claude-haiku (concis, expert autonome) |\n\n## Protocole de challenge\n\nQuand BYAN evalue un claim sur un domaine :\n1. Recupere le score ELO du domaine via `node bin\u002Fbyan-v2-cli.js elo context {domain}`\n2. Applique le `promptInstructions` retourne (ton, profondeur, scaffold)\n3. Ton invariant : TOUJOURS curieux, JAMAIS accusatoire (\"qu'est-ce qui t'a amene a ca ?\" vs \"c'est faux\")\n4. Apres echange : enregistre `VALIDATED | BLOCKED | PARTIAL` via CLI\n5. Protocole silencieux — l'utilisateur voit seulement le challenge, pas les mecaniques ELO\n\n## Mecaniques speciales (V2)\n\n- **Tilt detector** : 3 BLOCKED consecutifs → BYAN propose une pause pedagogique\n- **First blood** : premier claim dans un domaine vierge = toujours challenge (Zero Trust)\n- **Zone morte 450-550** : incertitude maximale, challenge le plus nuance\n- **ELO farming protection** : claims trop faciles → K-factor reduit automatiquement\n- **Hot hand** : 3 corrects consecutifs → petit boost de K (puis regression vers la moyenne)\n- **Shadow challenger** : expert (750+) peut activer un alter-ego adversarial opt-in\n\n## Commandes CLI\n\n```bash\nnode bin\u002Fbyan-v2-cli.js elo summary              # tous les domaines\nnode bin\u002Fbyan-v2-cli.js elo dashboard {domain}   # detail d'un domaine\nnode bin\u002Fbyan-v2-cli.js elo context {domain}     # contexte pour un challenge\nnode bin\u002Fbyan-v2-cli.js elo record {domain} {VALIDATED|BLOCKED|PARTIAL}\nnode bin\u002Fbyan-v2-cli.js elo declare {domain} {junior|mid|senior|lead|expert}\n```\n\n## Menu BYAN\n\nDans l'agent BYAN, tapez `[ELO]` pour acceder au sous-menu :\n- Dashboard par domaine\n- Enregistrer un claim\n- Declarer son expertise\n- Voir le routage LLM recommande\n\n## Philosophie\n\nLe score ELO n'est pas une punition — c'est un outil de calibration.\nUn score bas signifie \"BYAN va t'expliquer plus, pas moins\".\nLa pedagogie s'adapte au niveau, le ton reste constant : bienveillant et curieux.\n",{"name":5,"description":7},"main","7b63cfa91942025012f072f78abcf3ed511c4e16","install\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-elo-trust",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":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Yan-Acadenice\u002FBYAN --skill byan-elo-trust",{"tool":45,"command":46},"bunx","bunx skills add Yan-Acadenice\u002FBYAN --skill byan-elo-trust",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Yan-Acadenice\u002FBYAN --skill byan-elo-trust","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-elo-trust\u002FSKILL.md",true,[53,59],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Ftest-shape-rules.md","REFERENCE","参考文档",4679,"https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Feng\u002Feng-test-conventions\u002Freferences\u002Ftest-shape-rules.md",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fcheck-test-conventions.py","SCRIPT","脚本",4193,"https:\u002F\u002Fgithub.com\u002Fcompozy\u002Fcompozy\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Feng\u002Feng-test-conventions\u002Fscripts\u002Fcheck-test-conventions.py",[66,78,102,111,121,140],{"skillNo":67,"name":21,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":27},"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",[],[21,72,73,74,75,76,77],"project skill","use","repo","filesystem","workflows","byan strict",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":89,"publishedAt":27},"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",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[21,90,91,92,93,94,95,96,97,98,99,100,101],"byan yanstaller","config","exit","expert","installer","auto","user","detection","ZeRO","help","automation","platform detection",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":27},"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",[],[109,21,110],"tea","byan tea tea",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":27},"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",[],[21,118,119,120],"byan suitability","read","model",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":128,"publishedAt":27},"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",[127],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[21,77,129,96,130,131,132,133,134,135,136,137,138,139],"work","en","enforcement","activation","verify","mise","template","Production","release","status","MCP",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":27},"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",[],[147,21,148,149],"skeptic","byan skeptic","guard"]