[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PVESM49C5NT7SB7N3F76VS":3,"skill-same:01M6PVESM49C5NT7SB7N3F76VS":72},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":51,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6PVESM49C5NT7SB7N3F76VS","retro-to-framework",null,"Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.","muratovv\u002Fai-hats","muratovv","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7502801?v=4","01M6JGCBN4KEJX012GPJVSH04T","Fedor Muratov","01M6JGCBSNMN7CW3RGTPPE0MN2",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fretro-to-framework\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"framework","retro","retro to framework","incident","generic","single","skill update","more","about","problem","project","across","change","use","behavior","Rules","convert","projects","retrospective","component","2026-11-10 10:12:30",false,"---\nname: retro-to-framework\ndescription: >-\n  Convert an observation about agent behavior — from a retrospective or\n  from a single incident — into a framework-level change (hook, rule,\n  skill, skill update). Use after a retrospective identifies problems that\n  are not project-specific, after an incident where an agent misapplied a\n  component it had read, when CLAUDE.md band-aids accumulate (more than 3\n  per-project rules that could be generic), or when the same problem\n  recurs across multiple projects.\nlicense: MIT\nai_hats:\n  schema_version: 1\n  type: skill\n---\n\n# Retro-to-Framework\n\nConvert project-level retrospective findings into framework-level improvements.\n\n## When to Use\n\nTwo entry points, one procedure:\n\n- **Downstream of a retro** — **self-retrospective** produces the findings, this\n  skill promotes the generic ones.\n- **Downstream of an incident** — one session where an agent observably did the\n  wrong thing. No retro needed; the evidence is the session itself. Bring what\n  the agent did, what the component told it to do, and the proof it read that\n  component (otherwise the finding is \"the agent never saw it\", a different fix).\n\nTwo boundaries — the finding must be **cross-project generic** (a project-local\nfix stays in that project's CLAUDE.md), and trimming or dedup of components that\nalready exist is **skill-optimization**, not this.\n\n## Procedure\n\n1. **Classify findings:**\n   For each retrospective finding, ask: \"Would this same problem occur in a\n   different project using the same role?\"\n   - YES → framework candidate (rule, skill, or skill update)\n   - NO → project-specific (stays in project CLAUDE.md)\n\n2. **Map to component type — mechanism first:**\n   | Finding type                                          | Framework component                 |\n   | ----------------------------------------------------- | ----------------------------------- |\n   | Invariant a machine can decide (\"never write X to Y\") | Hook \u002F gate \u002F CLI check — not prose |\n   | Behavioral constraint (\"always do X\")                 | Rule                                |\n   | Multi-step process (\"when X, do Y then Z\")            | Skill                               |\n   | Missing check in existing process                     | Skill update                        |\n   | Knowledge gap                                         | Reference doc or injection update   |\n\n   The first row is first on purpose: prose costs tokens every turn and asks the\n   agent to comply, a hook costs nothing and does not ask. Rank the options with\n   the mechanism ladder in trait `skill-engineer` before picking a row.\n\n   **If prose for this finding was already tried and did not hold, the first row\n   is the only honest answer.** A component the agent demonstrably read and did\n   not apply will not be fixed by rewording it in the same place — that is the\n   evidence that the mechanism, not the wording, is wrong. Record what was tried\n   and how it was measured, so the next reader does not re-run the experiment.\n\n3. **Draft the improvement:**\n   Follow **skill-template** for new skills, rule naming convention for rules.\n\n4. **Wire into composition:**\n   Determine which trait should include the new component.\n   Update trait config.yaml. Run composer validation for all affected roles.\n\n5. **Propagate to projects:**\n   Roles are composed fresh at every session launch, so a library edit needs no\n   per-project command — it is live for the next session. A project pinned to a\n   published `ai-hats-library` needs `ai-hats self update` to pull the new\n   version; `self init` does not fetch one.\n   Remove corresponding band-aids from the project's own CLAUDE.md.\n   Verify with `ai-hats config status` (composition tree) or `ai-hats --dry-run`\n   (the exact artifacts a launch would deliver).\n\n6. **Close the loop:**\n   Update the original retrospective with a link to the framework change.\n   File a backlog card if the change is non-trivial.\n\n## Completion\n\n- Findings classified as framework vs project-specific\n- Framework improvements implemented and validated (composer 0 errors, tests green)\n- All projects using affected roles bumped\n- Per-project band-aids removed\n- Original retrospective updated with provenance\n\n## Anti-Patterns\n\n- Leaving band-aids in project CLAUDE.md after framework fixes exist — remove them\n- Making everything a framework change — some things are truly project-specific\n- Skipping composer validation — always verify after wiring changes\n","# Retro-to-Framework\n\nConvert project-level retrospective findings into framework-level improvements.\n\n## When to Use\n\nTwo entry points, one procedure:\n\n- **Downstream of a retro** — **self-retrospective** produces the findings, this\n  skill promotes the generic ones.\n- **Downstream of an incident** — one session where an agent observably did the\n  wrong thing. No retro needed; the evidence is the session itself. Bring what\n  the agent did, what the component told it to do, and the proof it read that\n  component (otherwise the finding is \"the agent never saw it\", a different fix).\n\nTwo boundaries — the finding must be **cross-project generic** (a project-local\nfix stays in that project's CLAUDE.md), and trimming or dedup of components that\nalready exist is **skill-optimization**, not this.\n\n## Procedure\n\n1. **Classify findings:**\n   For each retrospective finding, ask: \"Would this same problem occur in a\n   different project using the same role?\"\n   - YES → framework candidate (rule, skill, or skill update)\n   - NO → project-specific (stays in project CLAUDE.md)\n\n2. **Map to component type — mechanism first:**\n   | Finding type                                          | Framework component                 |\n   | ----------------------------------------------------- | ----------------------------------- |\n   | Invariant a machine can decide (\"never write X to Y\") | Hook \u002F gate \u002F CLI check — not prose |\n   | Behavioral constraint (\"always do X\")                 | Rule                                |\n   | Multi-step process (\"when X, do Y then Z\")            | Skill                               |\n   | Missing check in existing process                     | Skill update                        |\n   | Knowledge gap                                         | Reference doc or injection update   |\n\n   The first row is first on purpose: prose costs tokens every turn and asks the\n   agent to comply, a hook costs nothing and does not ask. Rank the options with\n   the mechanism ladder in trait `skill-engineer` before picking a row.\n\n   **If prose for this finding was already tried and did not hold, the first row\n   is the only honest answer.** A component the agent demonstrably read and did\n   not apply will not be fixed by rewording it in the same place — that is the\n   evidence that the mechanism, not the wording, is wrong. Record what was tried\n   and how it was measured, so the next reader does not re-run the experiment.\n\n3. **Draft the improvement:**\n   Follow **skill-template** for new skills, rule naming convention for rules.\n\n4. **Wire into composition:**\n   Determine which trait should include the new component.\n   Update trait config.yaml. Run composer validation for all affected roles.\n\n5. **Propagate to projects:**\n   Roles are composed fresh at every session launch, so a library edit needs no\n   per-project command — it is live for the next session. A project pinned to a\n   published `ai-hats-library` needs `ai-hats self update` to pull the new\n   version; `self init` does not fetch one.\n   Remove corresponding band-aids from the project's own CLAUDE.md.\n   Verify with `ai-hats config status` (composition tree) or `ai-hats --dry-run`\n   (the exact artifacts a launch would deliver).\n\n6. **Close the loop:**\n   Update the original retrospective with a link to the framework change.\n   File a backlog card if the change is non-trivial.\n\n## Completion\n\n- Findings classified as framework vs project-specific\n- Framework improvements implemented and validated (composer 0 errors, tests green)\n- All projects using affected roles bumped\n- Per-project band-aids removed\n- Original retrospective updated with provenance\n\n## Anti-Patterns\n\n- Leaving band-aids in project CLAUDE.md after framework fixes exist — remove them\n- Making everything a framework change — some things are truly project-specific\n- Skipping composer validation — always verify after wiring changes\n",{"name":5,"ai_hats":49,"license":15,"description":7},{"type":50,"schema_version":51},"skill",1,"master","f922a7f627276366873d546942d9ad899a86f71a","packages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fretro-to-framework","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats","https:\u002F\u002Fgithub.com\u002Fmuratovv","2026-11-05 20:59:10",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add muratovv\u002Fai-hats --skill retro-to-framework",{"tool":64,"command":65},"bunx","bunx skills add muratovv\u002Fai-hats --skill retro-to-framework",{"tool":67,"command":68},"pnpm","pnpm dlx skills add muratovv\u002Fai-hats --skill retro-to-framework","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fretro-to-framework\u002FSKILL.md",true,[],[73,98,122,141,163,177],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":44},"01M6PVFB1SM738R2SRSRSF7CY6","tool-evaluation-protocol","Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML\u002FLLM frameworks, testing approaches), or following up on a hype-driven recommendation.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Ftool-evaluation-protocol\u002FSKILL.md",[],[80,81,82,83,37,84,85,86,87,34,88,89,90,91,92,93,94,95,96,97],"tool evaluation protocol","tool","Evaluation","protocol","candidate","bounded","for","recommendation","time","frameworks","up","dependency","testing","Tools","methodology","adoption","libraries","ml",{"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":44},"01M6PVF7HATBEX1G7N50E2QT57","systematic-debugging","4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[105,106,107,108,109,110,111,112,113,114,115,116,37,117,38,118,119,120,83,121],"systematic","debugging","systematic debugging","phase","bug-fix","with","error","users","pattern","reports","bug","evidence","fix","verify","hypothesis","monitoring","test",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":44},"01M6PVF3MTQN3RPF73AN34856J","skill-template","Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fskill-template\u002FSKILL.md",[128],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[130,131,37,132,86,133,134,135,113,136,137,38,138,139,140],"skill template","template","Existing","which","canonical","structural","new skill","guide","hats","compliance","validation",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":44},"01M6PVF06SCV28QARM5MQPANC9","skill-optimization","Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fskill-optimization\u002FSKILL.md",[147],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[149,150,151,152,153,154,155,37,39,156,157,158,159,160,43,161,162],"skill optimization","Optimization","library","token budget","token","maintenance","periodic","Budget","refactor","audit","role","issues","components","high",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":44},"01M6PVEXM9717016T9MW82HDCT","silent-fallback-gate","PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fsilent-fallback-gate\u002FSKILL.md",[],[170,171,172,173,86,174,175,176,37],"silent fallback gate","fallback","gate","python","hook","write","edit",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":44},"01M6PVEQ05ETVVB2NX7FSYXRV2","py-security-lint","PostToolUse hook — reports the project's own ruff security (`S`) findings on every `.py` you Edit\u002FWrite, non-blockingly; fail-open, no manual invocation.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fpy-security-lint\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",[187,188,189,190,114,34,191,175,176,174,192,193],"security","lint","py security lint","ruff","open","you","manual"]