[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFN0PAH7YM6637SX2YH273":3,"skill-same:01M6CFN0PAH7YM6637SX2YH273":57},{"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":23,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6CFN0PAH7YM6637SX2YH273","byan-project",null,"Lister les projets BYAN via MCP et en choisir un a inspecter ou importer. Invoquer quand l'utilisateur dit \"liste mes projets byan\", \"choisit un projet byan\", \"import projet byan\", \"\u002Fbyan-project\", \"list byan projects\", \"pick byan project\".","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-project\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30],"byan project","byan","MCP","projects","pick","list","en","2026-11-10 10:12:30",false,"---\nname: byan-project\ndescription: Lister les projets BYAN via MCP et en choisir un a inspecter ou importer. Invoquer quand l'utilisateur dit \"liste mes projets byan\", \"choisit un projet byan\", \"import projet byan\", \"\u002Fbyan-project\", \"list byan projects\", \"pick byan project\".\n---\n\n# \u002Fbyan-project — Parcourir les projets byan_web\n\nSkill API-first : chaque etape appelle un tool MCP verifie. Pas de curl.\nOwner de la session : l'utilisateur (responsible du choix final).\nApproche simple et incremental — Ockham, KISS, minimal.\n\n## Prerequis\n\nVerifier que `$BYAN_API_TOKEN` est configure dans `.mcp.json`.\nContrainte : sans token valide, aucune action n'est possible.\nSi absent ou vide : \"Token byan_web manquant. Relance `npx create-byan-agent`.\"\nChallenge avant de continuer (IA-16) : token present ? Sinon stop.\n\n## Protocole\n\nEtapes step-by-step. Appliquer progressive disclosure : afficher uniquement ce dont\nl'utilisateur a besoin a chaque etape. Adapter le style a la reponse (feedback loop).\n\n1. Appeler `byan_list_projects`. Source : tool MCP, fait verifie.\n\n2. Si vide : \"Aucun projet trouve.\" Proposer `byan_api_projects_create`.\n   Consequence : aucune navigation possible sans projet existant.\n\n3. Sinon, afficher tableau numerote (show, don't just tell) :\n\n   | # | nom | id | type | created_at |\n   |---|-----|----|------|------------|\n   | 1 | ... | .. | ...  | ...        |\n\n4. Demander : \"Lequel ? (numero ou nom)\"\n   Clarification si ambigu. Attendre la reponse (intent preserve).\n\n5. Parser la reponse. Extraire project_id.\n   Validation : ne pas inventer un id — Zero Trust, verify avant d'agir.\n\n6. Appeler `byan_api_projects_get { id }`.\n   Validate output avant affichage.\n\n7. Afficher metadata : nom, type, visibility, my_role, description.\n   Consistent avec le schema byan_web (reference : .mcp.json).\n\n8. Proposer trois actions (priority = impact \u002F effort) :\n   1. \"Importer\" → `byan_import_project { path, name }` — branch locale creee\n   2. \"Workflows\" → `byan_api_workflows_list { projectId }`\n      Filtre si > 20 resultats (performance, pas de liste infinie).\n   3. \"Memoire\" → `byan_api_memory_list { projectId, limit: 20 }`\n\n   Attendre choix. Executer. Iterer si necessaire.\n\n## Gestion d'erreurs (fail fast, graceful degradation)\n\n- `AUTH_REQUIRED` : \"Token expire. Regenerer via \u002Fapi\u002Fauth\u002Flogin.\"\n  Rollback implicite : aucun etat modifie cote serveur.\n- Erreur reseau : \"byan_web injoignable. Verifier `$BYAN_API_URL`.\"\n  Fallback : proposer de retenter ou de verifier l'environnement (staging vs production).\n- Autre erreur : afficher le message brut (evidence directe, pas d'interpretation).\n\n## Conformite Merise Agile (contexte skill)\n\nCe skill s'inscrit dans le cycle BYAN : chaque action est tracable epic → story → task.\nAcceptance criteria : l'utilisateur peut lister, selectionner et inspecter un projet (resultat measurable et verifiable).\nTest automatise : byan_ping valide la connexion (CI\u002FCD pipeline de l'installeur).\nTDD, test-driven, test-first : verification avant chaque appel MCP.\nDefinition of Done (DoD) : projet selectionne + metadata affichee + action executee.\nDocumentation dans le README de chaque projet importe.\nVersioning semantique (semver) des projets expose par byan_web.\nRetrospective : adapter le protocole selon le feedback utilisateur.\nData dictionary \u002F schema : project_id, name, type, visibility, my_role (byan_web).\nMCD \u002F MCT validation : modele conceptuel aligne avec les workflows BYAN.\nVelocite preservee : bottom-up depuis les user stories de l'utilisateur.\nPareto 80\u002F20 : 3 actions couvrent 80% des besoins. Pas de feature YAGNI.\nChangelog maintenu par byan_web. History des sessions dans byan_api_memory_list.\nE2E, end-to-end, integration : import teste localement apres byan_import_project.\nReasoning explicite : chaque step explique pourquoi (rationale documente).\nClean, readable, self-documenting. Performance : limit: 20 par defaut.\nNo hallucinations : toutes les assertions sourcees (fact, evidence, source, verified).\n","# \u002Fbyan-project — Parcourir les projets byan_web\n\nSkill API-first : chaque etape appelle un tool MCP verifie. Pas de curl.\nOwner de la session : l'utilisateur (responsible du choix final).\nApproche simple et incremental — Ockham, KISS, minimal.\n\n## Prerequis\n\nVerifier que `$BYAN_API_TOKEN` est configure dans `.mcp.json`.\nContrainte : sans token valide, aucune action n'est possible.\nSi absent ou vide : \"Token byan_web manquant. Relance `npx create-byan-agent`.\"\nChallenge avant de continuer (IA-16) : token present ? Sinon stop.\n\n## Protocole\n\nEtapes step-by-step. Appliquer progressive disclosure : afficher uniquement ce dont\nl'utilisateur a besoin a chaque etape. Adapter le style a la reponse (feedback loop).\n\n1. Appeler `byan_list_projects`. Source : tool MCP, fait verifie.\n\n2. Si vide : \"Aucun projet trouve.\" Proposer `byan_api_projects_create`.\n   Consequence : aucune navigation possible sans projet existant.\n\n3. Sinon, afficher tableau numerote (show, don't just tell) :\n\n   | # | nom | id | type | created_at |\n   |---|-----|----|------|------------|\n   | 1 | ... | .. | ...  | ...        |\n\n4. Demander : \"Lequel ? (numero ou nom)\"\n   Clarification si ambigu. Attendre la reponse (intent preserve).\n\n5. Parser la reponse. Extraire project_id.\n   Validation : ne pas inventer un id — Zero Trust, verify avant d'agir.\n\n6. Appeler `byan_api_projects_get { id }`.\n   Validate output avant affichage.\n\n7. Afficher metadata : nom, type, visibility, my_role, description.\n   Consistent avec le schema byan_web (reference : .mcp.json).\n\n8. Proposer trois actions (priority = impact \u002F effort) :\n   1. \"Importer\" → `byan_import_project { path, name }` — branch locale creee\n   2. \"Workflows\" → `byan_api_workflows_list { projectId }`\n      Filtre si > 20 resultats (performance, pas de liste infinie).\n   3. \"Memoire\" → `byan_api_memory_list { projectId, limit: 20 }`\n\n   Attendre choix. Executer. Iterer si necessaire.\n\n## Gestion d'erreurs (fail fast, graceful degradation)\n\n- `AUTH_REQUIRED` : \"Token expire. Regenerer via \u002Fapi\u002Fauth\u002Flogin.\"\n  Rollback implicite : aucun etat modifie cote serveur.\n- Erreur reseau : \"byan_web injoignable. Verifier `$BYAN_API_URL`.\"\n  Fallback : proposer de retenter ou de verifier l'environnement (staging vs production).\n- Autre erreur : afficher le message brut (evidence directe, pas d'interpretation).\n\n## Conformite Merise Agile (contexte skill)\n\nCe skill s'inscrit dans le cycle BYAN : chaque action est tracable epic → story → task.\nAcceptance criteria : l'utilisateur peut lister, selectionner et inspecter un projet (resultat measurable et verifiable).\nTest automatise : byan_ping valide la connexion (CI\u002FCD pipeline de l'installeur).\nTDD, test-driven, test-first : verification avant chaque appel MCP.\nDefinition of Done (DoD) : projet selectionne + metadata affichee + action executee.\nDocumentation dans le README de chaque projet importe.\nVersioning semantique (semver) des projets expose par byan_web.\nRetrospective : adapter le protocole selon le feedback utilisateur.\nData dictionary \u002F schema : project_id, name, type, visibility, my_role (byan_web).\nMCD \u002F MCT validation : modele conceptuel aligne avec les workflows BYAN.\nVelocite preservee : bottom-up depuis les user stories de l'utilisateur.\nPareto 80\u002F20 : 3 actions couvrent 80% des besoins. Pas de feature YAGNI.\nChangelog maintenu par byan_web. History des sessions dans byan_api_memory_list.\nE2E, end-to-end, integration : import teste localement apres byan_import_project.\nReasoning explicite : chaque step explique pourquoi (rationale documente).\nClean, readable, self-documenting. Performance : limit: 20 par defaut.\nNo hallucinations : toutes les assertions sourcees (fact, evidence, source, verified).\n",{"name":5,"description":7},"main","7b63cfa91942025012f072f78abcf3ed511c4e16","install\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-project",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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add Yan-Acadenice\u002FBYAN --skill byan-project",{"tool":49,"command":50},"bunx","bunx skills add Yan-Acadenice\u002FBYAN --skill byan-project",{"tool":52,"command":53},"pnpm","pnpm dlx skills add Yan-Acadenice\u002FBYAN --skill byan-project","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-project\u002FSKILL.md",true,[],[58,70,90,99,109,126],{"skillNo":59,"name":25,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":31},"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",[],[25,64,65,66,67,68,69],"project skill","use","repo","filesystem","workflows","byan strict",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":77,"publishedAt":31},"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",[76],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,78,79,80,81,82,83,84,85,86,87,88,89],"byan yanstaller","config","exit","expert","installer","auto","user","detection","ZeRO","help","automation","platform detection",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":31},"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",[],[97,25,98],"tea","byan tea tea",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":31},"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",[],[25,106,107,108],"byan suitability","read","model",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":116,"publishedAt":31},"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",[115],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,69,117,84,30,118,119,120,121,122,123,124,125,26],"work","enforcement","activation","verify","mise","template","Production","release","status",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":31},"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",[],[133,25,134,135],"skeptic","byan skeptic","guard"]