[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PVBK5YQZK5ZNHZ8K8G200D":3,"skill-same:01M6PVBK5YQZK5ZNHZ8K8G200D":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":28,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":50,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6PVBK5YQZK5ZNHZ8K8G200D","design-minimalism",null,"The Scope & Out-of-scope stage of the plan-gate — every primitive (class, abstraction, option, new step) in plan.md must be justified by a concrete current-epic use case; speculative additions go to Out of scope. Reached through plan-gate, not as an independent trigger.","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\u002Fcore\u002Fskills\u002Fdesign-minimalism\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42],"design","minimalism","design minimalism","go","plan","option","use","gate","stage","as","trigger","scope","case","EPIC","2026-11-10 10:12:30",false,"---\nname: design-minimalism\ndescription: >-\n  The Scope & Out-of-scope stage of the plan-gate — every primitive\n  (class, abstraction, option, new step) in plan.md must be justified by a\n  concrete current-epic use case; speculative additions go to Out of\n  scope. Reached through plan-gate, not as an independent trigger.\nlicense: MIT\nai_hats:\n  schema_version: 1\n  type: skill\n---\n\n# Design Minimalism\n\nThe **Scope & Out-of-scope stage of `plan-gate`**: each primitive (class,\nabstraction, option, new step, new dependency) in a design plan must be\njustified by a **concrete use case in the current epic**. Speculative additions\n(\"may be useful for X later\", \"central registry for future keys\", \"pre-listed\nchild tasks for unbuilt features\") belong in **Out of scope** with an explicit\nactivation trigger, or are dropped.\n\nThis complements `trait-se-mindset`'s \"Simplicity first\" — that rule is about\n**code**; this skill is about the **design phase** of a task.\n\n## When to Use\n\nReach this stage through `plan-gate`, not as a standalone brainstorm→plan\ntrigger — `plan-gate` is the single entry point and routes here to fill the\n`Scope & Out-of-scope` section of `plan.md`.\n\n- Run it when that section is being written, or a plan proposes new abstractions, options, or sub-systems.\n- Trigger inside it: noticing the urge to \"future-proof\" or \"add for completeness\".\n- Sibling stage: `requirements-interview` owns the adjacent `Requirements` section — clarify *what* to build there, *how much* here.\n- Prior stage: `devils-advocate` (`Approach & counter`) runs first and challenges *whether the value holds*; this stage takes the surviving value as given and minimises the **means**. Don't re-litigate the value here — challenge scope, not direction.\n\n## Checklist\n\n### For every primitive in the plan\n\nAsk:\n\n1. **What concrete use case in the current epic does this solve?**\n   - Answer must point to an explicit acceptance criterion or a named user-facing capability in the current task.\n2. If the answer is **\"might be useful for X later\"** \u002F **\"for a future feature\"** \u002F **\"in case we need it\"**:\n   - Move to a `## Out of scope` section with explicit activation trigger (\"re-evaluate when feature X is in scope\"), OR\n   - Drop it entirely.\n3. If the answer is **\"for symmetry \u002F completeness\"**:\n   - Same — drop or move to Out of scope. Symmetry is not a use case.\n\n### The `## Out of scope` section is load-bearing\n\n- Prefer **explicit rejection** (\"rejected because …\") over silent omission.\n- This section communicates **what we considered and chose not to do** — saves future review rounds where someone asks \"why didn't you add Y?\".\n- A rich `Out of scope` is a sign of a well-reviewed plan, not bloat.\n\n## Worked Example\n\n**A plan-design that took seven iterations of rewrites.**\n\nUser explicitly rejected, across iterations:\n\n| Proposed                                  | Rejected because                                                       |\n| ----------------------------------------- | ---------------------------------------------------------------------- |\n| `MutableStateEnvelope` class              | speculative — no current step needed mutation                          |\n| Central state schema with enumerated keys | speculative — closed schema blocks user extension                      |\n| `SaveArtifact` pipeline step              | speculative — no current pipeline declared persistence                 |\n| YAML pipeline manifests                   | speculative — bash-compose covers all current use cases                |\n| 15 pre-listed child task IDs              | speculative — child tasks file at start of phase when design is stable |\n\nEach was framed as \"future-proofing\". Each cost user time to read and reject.\nA `## Out of scope` section listing them once with rejection rationale would\nhave saved 5 iterations.\n\n## Behavioral delivery: escalation ladder\n\nCode-primitive minimalism (above) tells you \"drop speculative classes\".\n**Behavioral-delivery** tasks — edits to skill text, rule text, prompt\nshape, HYP data shape, role\u002Ftrait injection — need a different default:\n**data-only first, abstract only after signal**. The ladder lists six\nrungs from lowest to highest cost. Ship at the lowest rung that covers\nthe observable behavior end-to-end; lift one rung only after a PoC\nsweep produces signal that the lower rung misses.\n\n### When this section applies\n\nPlan-stage of any task that changes how agents observably behave\nthrough:\n\n- a skill \u002F rule text edit;\n- a prompt-shape change (handoff, intake, retro, judge);\n- HYP data shape (a new field on a hypothesis);\n- a role's composition (attached trait, attached skill, injection\n  bullet).\n\nFor code-primitive changes (new class, new abstraction, new pipeline\nstep) — the rest of this skill governs.\n\n### The ladder\n\n| Rung | Layer                     | Cost        | Description                                                                                                              |\n| ---- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 1    | **text-in-YAML**          | trivial     | New field round-trips via `extra=\"allow\"` or a free-form string in an existing config. No schema change.                 |\n| 2    | **skill text**            | low         | Edit an existing `SKILL.md` or add a new one under `library\u002F`. No engine touch.                                          |\n| 3    | **trait wiring**          | low         | Attach an existing skill to a trait's composition, or add an injection bullet to a trait. No engine touch.               |\n| 4    | **handoff \u002F runner code** | medium      | Minimal Python under `src\u002Fai_hats\u002Fretro\u002F` or `src\u002Fai_hats\u002Fcli\u002F` to surface or consume a YAML field. Unit-tested.         |\n| 5    | **CLI flags**             | medium-high | Typed flags on an existing CLI command. Owes e2e coverage.                                                            |\n| 6    | **typed schema**          | high        | Pydantic model fields, migrations, validators. Reserve for \"shape is stable and we need rejection at the storage layer\". |\n\n### Don't skip rungs\n\nIf rung N suffices to test the hypothesis end-to-end, ship at rung N.\nLift to N+1 only when the next sweep's data shows rung N misses signal.\n\"We'll probably want flags later\" is **not** signal — it's level 1–2\nspeculation in disguise.\n\n### Plan-stage shape\n\nEvery behavioral-delivery `plan.md` states the chosen rung explicitly:\n\n> *Shipping at level N — &lt;one-line why N is sufficient&gt;.\n> Level N+1 not warranted because &lt;PoC signal absent \u002F not yet\n> measured&gt;.*\n\nThis sentence is the artefact the auditor sweep reads (see the companion\nHYP authored at document-stage per `library-change-hypothesis-protocol`).\n\n### Case study — the verification-protocol PoC\n\n- **Initial plan (rejected).** Extended `ValidationLogEntry` schema\n  (rung 6) + four typed CLI flags (rung 5) + rewrote four downstream\n  skills (rungs 2–3) + legacy-HYP migration. ~30 min of plan-mode\n  iteration.\n- **User redirect.** *\"план сложный. Можем проще как-то сделать?\"*\n- **Shipped plan.** Five-step PoC: free-form `verification_protocol`\n  string under `extra=\"allow\"` in `HYP-*.yaml` (rung 1) + lightweight\n  `library-change-hypothesis-protocol` skill (rung 2) + handoff\n  formatter patch (rung 4, escalated **only** after the\n  rung-1 PoC showed the data wasn't reaching reviewers). Zero engine\n  schema changes. Same observable behavior.\n\nLesson: rungs 5–6 looked \"carefully abstract\" because they encoded the\ndata shape into the model layer. The observable behavior (auditors emit\nprotocol-matching evidence) needed only rungs 1, 2, and 4 — and rung 4\nonly after rungs 1–2 produced PoC signal that justified the lift.\nAnything higher would have locked in a shape we hadn't yet observed\nworking.\n\n## Anti-Patterns\n\n- **\"While we're at it, let's add a `--verbose` flag\"** — no concrete current use case.\n- **\"Central registry for future extension points\"** — no current consumer.\n- **\"This class is symmetric with the other one\"** — symmetry is not justification.\n- **Pre-filing child task IDs** before the parent plan is approved — premature breakdown.\n- **\"In case we need this later\" abstractions** — YAGNI applies to design, not just code.\n\n## Completion\n\nA plan passes the minimalism check when:\n\n- Every primitive has a named current-epic use case (verifiable in acceptance).\n- `## Out of scope` section is explicit and lists rejected ideas with rationale.\n- No \"future-proofing\" rationale survives in the kept-scope section.\n\n## See also\n\n- `scope-guard` — runtime equivalent: prevents implementation-stage scope creep.\n- `trait-se-mindset` \"Simplicity first\" — code-level KISS\u002FYAGNI.\n- `predictive-accounting` — for shrink\u002Frefactor tasks: predict delta + dependency cost before implementation.\n","# Design Minimalism\n\nThe **Scope & Out-of-scope stage of `plan-gate`**: each primitive (class,\nabstraction, option, new step, new dependency) in a design plan must be\njustified by a **concrete use case in the current epic**. Speculative additions\n(\"may be useful for X later\", \"central registry for future keys\", \"pre-listed\nchild tasks for unbuilt features\") belong in **Out of scope** with an explicit\nactivation trigger, or are dropped.\n\nThis complements `trait-se-mindset`'s \"Simplicity first\" — that rule is about\n**code**; this skill is about the **design phase** of a task.\n\n## When to Use\n\nReach this stage through `plan-gate`, not as a standalone brainstorm→plan\ntrigger — `plan-gate` is the single entry point and routes here to fill the\n`Scope & Out-of-scope` section of `plan.md`.\n\n- Run it when that section is being written, or a plan proposes new abstractions, options, or sub-systems.\n- Trigger inside it: noticing the urge to \"future-proof\" or \"add for completeness\".\n- Sibling stage: `requirements-interview` owns the adjacent `Requirements` section — clarify *what* to build there, *how much* here.\n- Prior stage: `devils-advocate` (`Approach & counter`) runs first and challenges *whether the value holds*; this stage takes the surviving value as given and minimises the **means**. Don't re-litigate the value here — challenge scope, not direction.\n\n## Checklist\n\n### For every primitive in the plan\n\nAsk:\n\n1. **What concrete use case in the current epic does this solve?**\n   - Answer must point to an explicit acceptance criterion or a named user-facing capability in the current task.\n2. If the answer is **\"might be useful for X later\"** \u002F **\"for a future feature\"** \u002F **\"in case we need it\"**:\n   - Move to a `## Out of scope` section with explicit activation trigger (\"re-evaluate when feature X is in scope\"), OR\n   - Drop it entirely.\n3. If the answer is **\"for symmetry \u002F completeness\"**:\n   - Same — drop or move to Out of scope. Symmetry is not a use case.\n\n### The `## Out of scope` section is load-bearing\n\n- Prefer **explicit rejection** (\"rejected because …\") over silent omission.\n- This section communicates **what we considered and chose not to do** — saves future review rounds where someone asks \"why didn't you add Y?\".\n- A rich `Out of scope` is a sign of a well-reviewed plan, not bloat.\n\n## Worked Example\n\n**A plan-design that took seven iterations of rewrites.**\n\nUser explicitly rejected, across iterations:\n\n| Proposed                                  | Rejected because                                                       |\n| ----------------------------------------- | ---------------------------------------------------------------------- |\n| `MutableStateEnvelope` class              | speculative — no current step needed mutation                          |\n| Central state schema with enumerated keys | speculative — closed schema blocks user extension                      |\n| `SaveArtifact` pipeline step              | speculative — no current pipeline declared persistence                 |\n| YAML pipeline manifests                   | speculative — bash-compose covers all current use cases                |\n| 15 pre-listed child task IDs              | speculative — child tasks file at start of phase when design is stable |\n\nEach was framed as \"future-proofing\". Each cost user time to read and reject.\nA `## Out of scope` section listing them once with rejection rationale would\nhave saved 5 iterations.\n\n## Behavioral delivery: escalation ladder\n\nCode-primitive minimalism (above) tells you \"drop speculative classes\".\n**Behavioral-delivery** tasks — edits to skill text, rule text, prompt\nshape, HYP data shape, role\u002Ftrait injection — need a different default:\n**data-only first, abstract only after signal**. The ladder lists six\nrungs from lowest to highest cost. Ship at the lowest rung that covers\nthe observable behavior end-to-end; lift one rung only after a PoC\nsweep produces signal that the lower rung misses.\n\n### When this section applies\n\nPlan-stage of any task that changes how agents observably behave\nthrough:\n\n- a skill \u002F rule text edit;\n- a prompt-shape change (handoff, intake, retro, judge);\n- HYP data shape (a new field on a hypothesis);\n- a role's composition (attached trait, attached skill, injection\n  bullet).\n\nFor code-primitive changes (new class, new abstraction, new pipeline\nstep) — the rest of this skill governs.\n\n### The ladder\n\n| Rung | Layer                     | Cost        | Description                                                                                                              |\n| ---- | ------------------------- | ----------- | ------------------------------------------------------------------------------------------------------------------------ |\n| 1    | **text-in-YAML**          | trivial     | New field round-trips via `extra=\"allow\"` or a free-form string in an existing config. No schema change.                 |\n| 2    | **skill text**            | low         | Edit an existing `SKILL.md` or add a new one under `library\u002F`. No engine touch.                                          |\n| 3    | **trait wiring**          | low         | Attach an existing skill to a trait's composition, or add an injection bullet to a trait. No engine touch.               |\n| 4    | **handoff \u002F runner code** | medium      | Minimal Python under `src\u002Fai_hats\u002Fretro\u002F` or `src\u002Fai_hats\u002Fcli\u002F` to surface or consume a YAML field. Unit-tested.         |\n| 5    | **CLI flags**             | medium-high | Typed flags on an existing CLI command. Owes e2e coverage.                                                            |\n| 6    | **typed schema**          | high        | Pydantic model fields, migrations, validators. Reserve for \"shape is stable and we need rejection at the storage layer\". |\n\n### Don't skip rungs\n\nIf rung N suffices to test the hypothesis end-to-end, ship at rung N.\nLift to N+1 only when the next sweep's data shows rung N misses signal.\n\"We'll probably want flags later\" is **not** signal — it's level 1–2\nspeculation in disguise.\n\n### Plan-stage shape\n\nEvery behavioral-delivery `plan.md` states the chosen rung explicitly:\n\n> *Shipping at level N — &lt;one-line why N is sufficient&gt;.\n> Level N+1 not warranted because &lt;PoC signal absent \u002F not yet\n> measured&gt;.*\n\nThis sentence is the artefact the auditor sweep reads (see the companion\nHYP authored at document-stage per `library-change-hypothesis-protocol`).\n\n### Case study — the verification-protocol PoC\n\n- **Initial plan (rejected).** Extended `ValidationLogEntry` schema\n  (rung 6) + four typed CLI flags (rung 5) + rewrote four downstream\n  skills (rungs 2–3) + legacy-HYP migration. ~30 min of plan-mode\n  iteration.\n- **User redirect.** *\"план сложный. Можем проще как-то сделать?\"*\n- **Shipped plan.** Five-step PoC: free-form `verification_protocol`\n  string under `extra=\"allow\"` in `HYP-*.yaml` (rung 1) + lightweight\n  `library-change-hypothesis-protocol` skill (rung 2) + handoff\n  formatter patch (rung 4, escalated **only** after the\n  rung-1 PoC showed the data wasn't reaching reviewers). Zero engine\n  schema changes. Same observable behavior.\n\nLesson: rungs 5–6 looked \"carefully abstract\" because they encoded the\ndata shape into the model layer. The observable behavior (auditors emit\nprotocol-matching evidence) needed only rungs 1, 2, and 4 — and rung 4\nonly after rungs 1–2 produced PoC signal that justified the lift.\nAnything higher would have locked in a shape we hadn't yet observed\nworking.\n\n## Anti-Patterns\n\n- **\"While we're at it, let's add a `--verbose` flag\"** — no concrete current use case.\n- **\"Central registry for future extension points\"** — no current consumer.\n- **\"This class is symmetric with the other one\"** — symmetry is not justification.\n- **Pre-filing child task IDs** before the parent plan is approved — premature breakdown.\n- **\"In case we need this later\" abstractions** — YAGNI applies to design, not just code.\n\n## Completion\n\nA plan passes the minimalism check when:\n\n- Every primitive has a named current-epic use case (verifiable in acceptance).\n- `## Out of scope` section is explicit and lists rejected ideas with rationale.\n- No \"future-proofing\" rationale survives in the kept-scope section.\n\n## See also\n\n- `scope-guard` — runtime equivalent: prevents implementation-stage scope creep.\n- `trait-se-mindset` \"Simplicity first\" — code-level KISS\u002FYAGNI.\n- `predictive-accounting` — for shrink\u002Frefactor tasks: predict delta + dependency cost before implementation.\n",{"name":5,"ai_hats":48,"license":15,"description":7},{"type":49,"schema_version":50},"skill",1,"master","f922a7f627276366873d546942d9ad899a86f71a","packages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fcore\u002Fskills\u002Fdesign-minimalism","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats","https:\u002F\u002Fgithub.com\u002Fmuratovv","2026-11-05 20:59:10",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add muratovv\u002Fai-hats --skill design-minimalism",{"tool":63,"command":64},"bunx","bunx skills add muratovv\u002Fai-hats --skill design-minimalism",{"tool":66,"command":67},"pnpm","pnpm dlx skills add muratovv\u002Fai-hats --skill design-minimalism","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\u002Fcore\u002Fskills\u002Fdesign-minimalism\u002FSKILL.md",true,[],[72,98,123,144,168,181],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":43},"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",[],[79,80,81,82,83,84,85,86,87,88,35,89,90,91,92,93,94,95,96,97],"protocol","Evaluation","tool","tool evaluation protocol","testing","ml","libraries","adoption","methodology","Tools","dependency","up","frameworks","time","project","recommendation","for","bounded","candidate",{"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":43},"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",[],[105,106,107,108,79,109,110,111,112,113,35,114,115,116,117,118,119,120,121,122],"systematic debugging","debugging","systematic","test","monitoring","hypothesis","verify","behavior","fix","evidence","bug","reports","pattern","users","error","with","bug-fix","phase",{"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":132,"publishedAt":43},"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",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[133,134,135,136,137,112,138,35,139,117,140,141,142,95,143],"template","skill template","validation","compliance","hats","guide","new skill","structural","canonical","which","Existing",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":43},"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",[150],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},[152,153,154,155,156,157,158,159,160,161,35,162,163,164,165,166,167],"Optimization","skill optimization","components","component","issues","library","audit","refactor","Budget","Rules","periodic","maintenance","token","token budget","role","high",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":43},"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",[],[36,175,176,177,178,179,35,180,95],"fallback","silent fallback gate","python","write","edit","hook",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":43},"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",[187],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},[189,190,191,192,155,193,194,195,161,112,35,196,197,93,198,199,200,201,202,203],"framework","retro","retro to framework","change","retrospective","projects","convert","incident","across","problem","about","more","skill update","single","generic"]