[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JGXHET3JBSHRE7BBT45YCS":3,"skill-same:01M6JGXHET3JBSHRE7BBT45YCS":71},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6JGXHET3JBSHRE7BBT45YCS","tool-evaluation-protocol",null,"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.","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\u002Fusage\u002Fskills\u002Ftool-evaluation-protocol\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tool evaluation protocol","protocol","Evaluation","tool","dependency","candidate","bounded","for","recommendation","project","time","frameworks","up","testing","use","Tools","methodology","adoption","libraries","ml","2026-11-10 10:12:30",false,"---\nname: tool-evaluation-protocol\ndescription: >-\n  Time-bounded protocol for evaluating new tools, libraries, or\n  methodologies before adoption. Use when evaluating a candidate\n  dependency for the project, researching a methodology (e.g. ML\u002FLLM\n  frameworks, testing approaches), or following up on a hype-driven\n  recommendation.\nlicense: MIT\n---\n# Tool Evaluation Protocol\n\nDecide whether to adopt an external tool, library, or methodology with bounded effort.\n\n## When to Use\nOnly for a *candidate* — a tool\u002Flibrary\u002Fmethodology not yet adopted, especially\na hype-driven one. Not for tools already standard in the stack (just use them),\nand not a written feature-comparison essay — the protocol is a time-boxed PoC\nthat ends in an adopt\u002Freject call, not analysis for its own sake.\n\n## Procedure\n\n1. **Frame** — Candidate (name, version, source). Purpose: what it enables or replaces. Known alternatives.\n\n2. **Kill-criteria check** — Hard blockers warranting immediate `reject` without PoC: license incompatibility, dormant upstream (no commits\u002Fissues for >12 months without maintainer note), runtime incompatibility, non-OSS dependency where OSS-only is required. Document any fired criterion and stop.\n\n3. **Maturity assessment** — Signals: years in production, contributor count, breaking-change history, ecosystem adoption. Apply **Lindy bias** for core paths (older + boring beats newer + exciting); apply **Hype Cycle skepticism** for ML\u002FLLM-fresh tools (heavy stars in last 12mo → halve confidence). Output: signals + bias-adjusted readout, not yes\u002Fno.\n\n4. **PoC** — Set budget **before execution**: time (one working session unless justified) and scope (one real project artifact, end-to-end, not a toy). List explicit **assumptions** the PoC will validate, in categories: functional, integration, performance, cost. Run within budget. Record per-assumption pass\u002Ffail. **Stop on time-budget exhaustion regardless of completion %.**\n\n5. **Decision** — `adopt` \u002F `evaluate-further` \u002F `reject` + ADR (see references\u002Fadr-template.md). Document assumption verdicts, PoC results, residual risk. Pick `evaluate-further` **only if** a specific blocker can be resolved with bounded effort; indefinite \"monitoring\" counts as `reject`.\n\n## Completion\n- ADR written using `references\u002Fadr-template.md` structure\n- Decision recorded with per-assumption verdicts\n- For `adopt` — follow-up tickets for integration; for `reject` — re-open criteria documented\n\n## Anti-Patterns\n- Skipping the kill-criteria check (\"we'll see during PoC\") — wastes time on doomed candidates\n- Letting PoC overflow the budget because \"we're close\" — anti-Hofstadter rule violated\n- Choosing `evaluate-further` as a way to defer the decision indefinitely\n- Tuning the candidate to pass the metric rather than testing real fit — once the metric becomes the target, it stops measuring fit (Goodhart's law)\n","# Tool Evaluation Protocol\n\nDecide whether to adopt an external tool, library, or methodology with bounded effort.\n\n## When to Use\nOnly for a *candidate* — a tool\u002Flibrary\u002Fmethodology not yet adopted, especially\na hype-driven one. Not for tools already standard in the stack (just use them),\nand not a written feature-comparison essay — the protocol is a time-boxed PoC\nthat ends in an adopt\u002Freject call, not analysis for its own sake.\n\n## Procedure\n\n1. **Frame** — Candidate (name, version, source). Purpose: what it enables or replaces. Known alternatives.\n\n2. **Kill-criteria check** — Hard blockers warranting immediate `reject` without PoC: license incompatibility, dormant upstream (no commits\u002Fissues for >12 months without maintainer note), runtime incompatibility, non-OSS dependency where OSS-only is required. Document any fired criterion and stop.\n\n3. **Maturity assessment** — Signals: years in production, contributor count, breaking-change history, ecosystem adoption. Apply **Lindy bias** for core paths (older + boring beats newer + exciting); apply **Hype Cycle skepticism** for ML\u002FLLM-fresh tools (heavy stars in last 12mo → halve confidence). Output: signals + bias-adjusted readout, not yes\u002Fno.\n\n4. **PoC** — Set budget **before execution**: time (one working session unless justified) and scope (one real project artifact, end-to-end, not a toy). List explicit **assumptions** the PoC will validate, in categories: functional, integration, performance, cost. Run within budget. Record per-assumption pass\u002Ffail. **Stop on time-budget exhaustion regardless of completion %.**\n\n5. **Decision** — `adopt` \u002F `evaluate-further` \u002F `reject` + ADR (see references\u002Fadr-template.md). Document assumption verdicts, PoC results, residual risk. Pick `evaluate-further` **only if** a specific blocker can be resolved with bounded effort; indefinite \"monitoring\" counts as `reject`.\n\n## Completion\n- ADR written using `references\u002Fadr-template.md` structure\n- Decision recorded with per-assumption verdicts\n- For `adopt` — follow-up tickets for integration; for `reject` — re-open criteria documented\n\n## Anti-Patterns\n- Skipping the kill-criteria check (\"we'll see during PoC\") — wastes time on doomed candidates\n- Letting PoC overflow the budget because \"we're close\" — anti-Hofstadter rule violated\n- Choosing `evaluate-further` as a way to defer the decision indefinitely\n- Tuning the candidate to pass the metric rather than testing real fit — once the metric becomes the target, it stops measuring fit (Goodhart's law)\n",{"name":5,"license":15,"description":7},"master","b4819add93efbaf4d80627118ec34680406b309b","packages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fusage\u002Fskills\u002Ftool-evaluation-protocol",1,"https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats","https:\u002F\u002Fgithub.com\u002Fmuratovv","2026-11-05 20:59:10",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add muratovv\u002Fai-hats --skill tool-evaluation-protocol",{"tool":57,"command":58},"bunx","bunx skills add muratovv\u002Fai-hats --skill tool-evaluation-protocol",{"tool":60,"command":61},"pnpm","pnpm dlx skills add muratovv\u002Fai-hats --skill tool-evaluation-protocol","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\u002Fusage\u002Fskills\u002Ftool-evaluation-protocol\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fadr-template.md","REFERENCE","参考文档",1278,"https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fusage\u002Fskills\u002Ftool-evaluation-protocol\u002Freferences\u002Fadr-template.md",[72,77,102,125,149,163],{"skillNo":73,"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":74,"categories":75,"keywords":76,"publishedAt":39},"01M6PVFB1SM738R2SRSRSF7CY6","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",[],[20,21,22,19,32,38,37,36,35,34,33,23,31,30,29,28,27,26,25,24],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":39},"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",[],[84,85,86,87,20,88,89,90,91,92,33,93,94,95,96,97,98,99,100,101],"systematic debugging","debugging","systematic","test","monitoring","hypothesis","verify","behavior","fix","evidence","bug","reports","pattern","users","error","with","bug-fix","phase",{"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":113,"publishedAt":39},"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",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[114,115,116,117,118,91,119,33,120,96,121,122,123,26,124],"template","skill template","validation","compliance","hats","guide","new skill","structural","canonical","which","Existing",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":132,"publishedAt":39},"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",[131],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},[133,134,135,136,137,138,139,140,141,142,33,143,144,145,146,147,148],"Optimization","skill optimization","components","component","issues","library","audit","refactor","Budget","Rules","periodic","maintenance","token","token budget","role","high",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":39},"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",[],[156,157,158,159,160,161,33,162,26],"gate","fallback","silent fallback gate","python","write","edit","hook",{"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":170,"publishedAt":39},"01M6PVESM49C5NT7SB7N3F76VS","retro-to-framework","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.","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",[169],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},[171,172,173,174,136,175,176,177,142,91,33,178,179,28,180,181,182,183,184,185],"framework","retro","retro to framework","change","retrospective","projects","convert","incident","across","problem","about","more","skill update","single","generic"]