[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFMM8NHC7KYNBK1Q7PSKMK":3,"skill-same:01M6CFMM8NHC7KYNBK1Q7PSKMK":110},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6CFMM8NHC7KYNBK1Q7PSKMK","byan-insight",null,"Harvest the native Claude Code outcome trails (tool-log, strict-audit gaps, suitability ledger, ELO) into a GATED self-improvement digest for BYAN. Invoke when the user asks \"what did this session teach BYAN\", \"insight digest\", \"self-improvement\", \"qu'est-ce que BYAN a appris\", or wants to review recurring gaps \u002F routing outcomes \u002F tool health before deciding what to improve. Observe and propose; the human ratifies each change.","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-insight\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"byan","byan insight","user","observe","log","outcomes","session","recurring","outcome","review","tool","improve","health","audit","code","routing","change","teach","2026-11-10 10:12:30",false,"---\nname: byan-insight\ndescription: Harvest the native Claude Code outcome trails (tool-log, strict-audit gaps, suitability ledger, ELO) into a GATED self-improvement digest for BYAN. Invoke when the user asks \"what did this session teach BYAN\", \"insight digest\", \"self-improvement\", \"qu'est-ce que BYAN a appris\", or wants to review recurring gaps \u002F routing outcomes \u002F tool health before deciding what to improve. Observe and propose; the human ratifies each change.\n---\n\n# BYAN Insight Loop (gated self-improvement)\n\nBYAN already has advisory learning surfaces (ELO trust, the suitability ledger,\nsoul-memory) and the native Claude Code hooks already leave outcome trails on\ndisk. This skill closes the loop: it READS those trails, aggregates them into a\ndigest, and surfaces GATED proposals. It does not modify a behavior surface.\n\n## The one hard rule: observe and propose, do not silently self-modify\n\nAn agent that rewrote its own routing, personas, or mantra thresholds on a\nheuristic would be the exact silent-downgrade BYAN exists to prevent. So this\nloop stops at a PROPOSAL. Applying a change (a routing tweak, a new checklist\nitem, a persona edit) stays a human decision — ideally run as its own FD. The\nadvisory data (ELO, suitability) is read-only here; behavior surfaces are left\nto the human gate.\n\n## Protocol\n\n1. **Harvest.** Call the MCP tool `byan_insight_digest` (read-only, no args). It\n   returns `{ gated: true, digest, render }` where `digest` is\n   `{ toolHealth, recurringGaps, routingOutcomes, eloTrends, proposals }`.\n   - `toolHealth` : call count, failure rate, top failing tools, output-token cost\n     (from `_byan-output\u002Ftool-log.jsonl`).\n   - `recurringGaps` : clustered self-verify gap themes with counts (from\n     `.byan-strict\u002Faudit.log`) — what BYAN keeps missing.\n   - `routingOutcomes` : per cheap-model x leaf keep-rate (from the suitability\n     ledger) — where a downgrade is proven good or bad.\n   - `eloTrends` : per-domain trust rating.\n   - `proposals` : conservative, GATED suggestions (each `gated: true`).\n2. **Present.** Show the `render` text, then the proposals as a numbered list.\n   Make explicit that nothing has been applied.\n3. **Gate.** For each proposal the user accepts, run the change as its own scoped\n   work (a short FD for a behavior change; a direct edit for a doc\u002Fchecklist).\n   Do not auto-apply a proposal.\n\n## CLI equivalent\n\n```\nnode _byan\u002Fmcp\u002Fbyan-mcp-server\u002Fbin\u002Fbyan-insight-digest.js [--root \u003Cdir>] [--json]\n```\n\nPrints the human-readable digest, or the raw JSON with `--json`. Self-disables\n(empty digest) when the trails are absent, so a fresh checkout is not an error.\n\n## What it deliberately leaves alone\n\n- It does not call `byan_elo_record` \u002F `byan_suitability_record` for you (those\n  stay where the outcome actually happens, e.g. a VALIDATE pass).\n- It does not edit `lib\u002Fdispatch.js`, `native-tiers.js`, a persona, or the mantra\n  thresholds. Those are behavior surfaces; a proposal names them, a human\n  changes them.\n","# BYAN Insight Loop (gated self-improvement)\n\nBYAN already has advisory learning surfaces (ELO trust, the suitability ledger,\nsoul-memory) and the native Claude Code hooks already leave outcome trails on\ndisk. This skill closes the loop: it READS those trails, aggregates them into a\ndigest, and surfaces GATED proposals. It does not modify a behavior surface.\n\n## The one hard rule: observe and propose, do not silently self-modify\n\nAn agent that rewrote its own routing, personas, or mantra thresholds on a\nheuristic would be the exact silent-downgrade BYAN exists to prevent. So this\nloop stops at a PROPOSAL. Applying a change (a routing tweak, a new checklist\nitem, a persona edit) stays a human decision — ideally run as its own FD. The\nadvisory data (ELO, suitability) is read-only here; behavior surfaces are left\nto the human gate.\n\n## Protocol\n\n1. **Harvest.** Call the MCP tool `byan_insight_digest` (read-only, no args). It\n   returns `{ gated: true, digest, render }` where `digest` is\n   `{ toolHealth, recurringGaps, routingOutcomes, eloTrends, proposals }`.\n   - `toolHealth` : call count, failure rate, top failing tools, output-token cost\n     (from `_byan-output\u002Ftool-log.jsonl`).\n   - `recurringGaps` : clustered self-verify gap themes with counts (from\n     `.byan-strict\u002Faudit.log`) — what BYAN keeps missing.\n   - `routingOutcomes` : per cheap-model x leaf keep-rate (from the suitability\n     ledger) — where a downgrade is proven good or bad.\n   - `eloTrends` : per-domain trust rating.\n   - `proposals` : conservative, GATED suggestions (each `gated: true`).\n2. **Present.** Show the `render` text, then the proposals as a numbered list.\n   Make explicit that nothing has been applied.\n3. **Gate.** For each proposal the user accepts, run the change as its own scoped\n   work (a short FD for a behavior change; a direct edit for a doc\u002Fchecklist).\n   Do not auto-apply a proposal.\n\n## CLI equivalent\n\n```\nnode _byan\u002Fmcp\u002Fbyan-mcp-server\u002Fbin\u002Fbyan-insight-digest.js [--root \u003Cdir>] [--json]\n```\n\nPrints the human-readable digest, or the raw JSON with `--json`. Self-disables\n(empty digest) when the trails are absent, so a fresh checkout is not an error.\n\n## What it deliberately leaves alone\n\n- It does not call `byan_elo_record` \u002F `byan_suitability_record` for you (those\n  stay where the outcome actually happens, e.g. a VALIDATE pass).\n- It does not edit `lib\u002Fdispatch.js`, `native-tiers.js`, a persona, or the mantra\n  thresholds. Those are behavior surfaces; a proposal names them, a human\n  changes them.\n",{"name":5,"description":7},"main","7b63cfa91942025012f072f78abcf3ed511c4e16","install\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-insight",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":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Yan-Acadenice\u002FBYAN --skill byan-insight",{"tool":55,"command":56},"bunx","bunx skills add Yan-Acadenice\u002FBYAN --skill byan-insight",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Yan-Acadenice\u002FBYAN --skill byan-insight","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-insight\u002FSKILL.md",true,[63,69,74,78,82,86,90,94,98,102,106],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"client-api.md","REFERENCE","参考文档",32676,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Fclient-api.md",{"path":70,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"LICENSE","许可证",1072,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002FLICENSE",{"path":75,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":76,"sourceHtmlUrl":77},"options.md",3130,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Foptions.md",{"path":79,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":80,"sourceHtmlUrl":81},"portfolio.md",2960,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Fportfolio.md",{"path":83,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":84,"sourceHtmlUrl":85},"reference.md",40357,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Freference.md",{"path":87,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":88,"sourceHtmlUrl":89},"research.md",2488,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Fresearch.md",{"path":91,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":92,"sourceHtmlUrl":93},"setup.md",6334,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Fsetup.md",{"path":95,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":96,"sourceHtmlUrl":97},"SOURCE.md",454,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002FSOURCE.md",{"path":99,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":100,"sourceHtmlUrl":101},"trade.md",11153,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Ftrade.md",{"path":103,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":104,"sourceHtmlUrl":105},"TRUST.auto.yaml",2223,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002FTRUST.auto.yaml",{"path":107,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":108,"sourceHtmlUrl":109},"watchlists.md",7402,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Frobinhood-for-agents\u002Fwatchlists.md",[111,123,146,155,165,184],{"skillNo":112,"name":19,"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":116,"publishedAt":37},"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",[],[19,117,118,119,120,121,122],"project skill","use","repo","filesystem","workflows","byan strict",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":134,"publishedAt":37},"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",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":132,"taxonomyTypeDesc":133},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[19,135,136,137,138,139,140,21,141,142,143,144,145],"byan yanstaller","config","exit","expert","installer","auto","detection","ZeRO","help","automation","platform detection",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":37},"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",[],[153,19,154],"tea","byan tea tea",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":37},"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",[],[19,162,163,164],"byan suitability","read","model",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":172,"publishedAt":37},"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",[171],{"categoryNo":130,"categoryName":131,"taxonomyType":132,"taxonomyTypeDesc":133},[19,122,173,21,174,175,176,177,178,179,180,181,182,183],"work","en","enforcement","activation","verify","mise","template","Production","release","status","MCP",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":37},"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",[],[191,19,192,193],"skeptic","byan skeptic","guard"]