[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFMPMX65RQ9KJ9SN3KGFE3":3,"skill-same:01M6CFMPMX65RQ9KJ9SN3KGFE3":52},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6CFMPMX65RQ9KJ9SN3KGFE3","byan-mantra-audit",null,"Semantic embodiment audit of a BYAN persona against its applicable mantras. Out-of-band, LLM-judged, kept out of the commit gate.","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-mantra-audit\u002FSKILL.md",[],[19,20,21,22,23,24,25],"audit","byan mantra audit","byan","commit","out-of-band","persona","gate","2026-11-10 10:12:30",false,"---\nname: byan-mantra-audit\ndescription: Semantic embodiment audit of a BYAN persona against its applicable mantras. Out-of-band, LLM-judged, kept out of the commit gate.\n---\n\n# BYAN Mantra Embodiment Audit (N2)\n\nThis skill runs the deep, semantic half of mantra validation, the layer above the\ndeterministic anti-stub floor enforced at commit time. The pre-commit gate asks\n\"does this persona contain its domain vocabulary\"; this skill asks \"does this\npersona genuinely EMBODY each applicable mantra\", judged by you (the LLM), not by\nkeyword presence. It runs on demand, outside the commit path.\n\n## When to run\n\n- Auditing a persona's quality beyond the deterministic anti-stub floor.\n- After authoring or editing an agent, to check real embodiment of its mantras.\n- As a CI \u002F review step, out-of-band. Not as a commit gate (the judgment is\n  semantic and non-deterministic, so it must stay out of the commit path).\n\n## Precondition (runtime check, do this FIRST)\n\nThis audit needs the BYAN v2 runtime (`src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js`). It\nruns from the BYAN repository; a generated\u002Fnpm-installed BYAN project does not ship\nthat runtime yet. Check before running anything:\n\n```\ntest -f src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js && echo OK || echo \"N2 runtime absent\"\n```\n\nIf it prints `N2 runtime absent`, STOP and tell the user plainly: the embodiment\naudit runs from the BYAN repository and is not yet delivered to generated projects.\nDo NOT run the node commands below, they would fail with MODULE_NOT_FOUND.\n\n## Protocol (hybrid: deterministic CLI, semantic judgment)\n\n1. PREPARE (deterministic). Build the judgment packet for the target persona:\n   ```\n   node src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js prepare \u003Cpath\u002Fto\u002Fagent.md>\n   ```\n   It resolves the persona's scope (scope-resolver), lists only the applicable\n   mantras, and emits a rubric plus the persona text. Add `--json` for the raw packet.\n\n2. JUDGE (you, this turn). For each mantra in the packet decide `embodied`,\n   `partial`, or `absent`. Judge embodiment, not vocabulary: a mantra is embodied\n   when the persona's role, instructions, and red-lines enact the principle, even\n   if the exact keyword is absent. Write the verdicts to a JSON file:\n   `{ \"\u003CmantraId>\": \"embodied\" | \"partial\" | \"absent\", ... }`.\n\n3. SCORE (deterministic):\n   ```\n   node src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js score \u003Cpath\u002Fto\u002Fagent.md> \u003Cverdicts.json>\n   ```\n   It returns the embodiment score and the embodied \u002F partial \u002F absent \u002F unjudged\n   breakdown.\n\n4. REPORT. Present the embodiment score, the absent mantras, and concrete\n   suggestions to raise embodiment, what the persona should ENACT, not which\n   keyword to insert.\n\n## Boundaries\n\n- Advisory quality insight, not a gate. It does not block commits.\n- The deterministic floor (pre-commit gate, Stop hook) and this semantic audit are\n  complementary: the floor catches stubs cheaply; this measures real quality deeply.\n- Keep judgments honest: default to `partial` or `absent` when the persona only\n  alludes to a mantra without enacting it.\n","# BYAN Mantra Embodiment Audit (N2)\n\nThis skill runs the deep, semantic half of mantra validation, the layer above the\ndeterministic anti-stub floor enforced at commit time. The pre-commit gate asks\n\"does this persona contain its domain vocabulary\"; this skill asks \"does this\npersona genuinely EMBODY each applicable mantra\", judged by you (the LLM), not by\nkeyword presence. It runs on demand, outside the commit path.\n\n## When to run\n\n- Auditing a persona's quality beyond the deterministic anti-stub floor.\n- After authoring or editing an agent, to check real embodiment of its mantras.\n- As a CI \u002F review step, out-of-band. Not as a commit gate (the judgment is\n  semantic and non-deterministic, so it must stay out of the commit path).\n\n## Precondition (runtime check, do this FIRST)\n\nThis audit needs the BYAN v2 runtime (`src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js`). It\nruns from the BYAN repository; a generated\u002Fnpm-installed BYAN project does not ship\nthat runtime yet. Check before running anything:\n\n```\ntest -f src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js && echo OK || echo \"N2 runtime absent\"\n```\n\nIf it prints `N2 runtime absent`, STOP and tell the user plainly: the embodiment\naudit runs from the BYAN repository and is not yet delivered to generated projects.\nDo NOT run the node commands below, they would fail with MODULE_NOT_FOUND.\n\n## Protocol (hybrid: deterministic CLI, semantic judgment)\n\n1. PREPARE (deterministic). Build the judgment packet for the target persona:\n   ```\n   node src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js prepare \u003Cpath\u002Fto\u002Fagent.md>\n   ```\n   It resolves the persona's scope (scope-resolver), lists only the applicable\n   mantras, and emits a rubric plus the persona text. Add `--json` for the raw packet.\n\n2. JUDGE (you, this turn). For each mantra in the packet decide `embodied`,\n   `partial`, or `absent`. Judge embodiment, not vocabulary: a mantra is embodied\n   when the persona's role, instructions, and red-lines enact the principle, even\n   if the exact keyword is absent. Write the verdicts to a JSON file:\n   `{ \"\u003CmantraId>\": \"embodied\" | \"partial\" | \"absent\", ... }`.\n\n3. SCORE (deterministic):\n   ```\n   node src\u002Fbyan-v2\u002Fgeneration\u002Fmantra-audit.js score \u003Cpath\u002Fto\u002Fagent.md> \u003Cverdicts.json>\n   ```\n   It returns the embodiment score and the embodied \u002F partial \u002F absent \u002F unjudged\n   breakdown.\n\n4. REPORT. Present the embodiment score, the absent mantras, and concrete\n   suggestions to raise embodiment, what the persona should ENACT, not which\n   keyword to insert.\n\n## Boundaries\n\n- Advisory quality insight, not a gate. It does not block commits.\n- The deterministic floor (pre-commit gate, Stop hook) and this semantic audit are\n  complementary: the floor catches stubs cheaply; this measures real quality deeply.\n- Keep judgments honest: default to `partial` or `absent` when the persona only\n  alludes to a mantra without enacting it.\n",{"name":5,"description":7},"main","7b63cfa91942025012f072f78abcf3ed511c4e16","install\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-mantra-audit",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":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Yan-Acadenice\u002FBYAN --skill byan-mantra-audit",{"tool":44,"command":45},"bunx","bunx skills add Yan-Acadenice\u002FBYAN --skill byan-mantra-audit",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Yan-Acadenice\u002FBYAN --skill byan-mantra-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-mantra-audit\u002FSKILL.md",true,[],[53,65,89,98,108,127],{"skillNo":54,"name":21,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":26},"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",[],[21,59,60,61,62,63,64],"project skill","use","repo","filesystem","workflows","byan strict",{"skillNo":66,"name":67,"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":76,"publishedAt":26},"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",[71],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[21,77,78,79,80,81,82,83,84,85,86,87,88],"byan yanstaller","config","exit","expert","installer","auto","user","detection","ZeRO","help","automation","platform detection",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":26},"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",[],[96,21,97],"tea","byan tea tea",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":26},"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",[],[21,105,106,107],"byan suitability","read","model",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":115,"publishedAt":26},"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",[114],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},[21,64,116,83,117,118,119,120,121,122,123,124,125,126],"work","en","enforcement","activation","verify","mise","template","Production","release","status","MCP",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":26},"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",[],[134,21,135,136],"skeptic","byan skeptic","guard"]