[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CP5P0040F66R98ZR61FNXJ":3,"skill-same:01M7CP5P0040F66R98ZR61FNXJ":65},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7CP5P0040F66R98ZR61FNXJ","codebase-design",null,"Shared vocabulary for designing deep modules and checking value ownership. Use when designing a module's interface, choosing or deferring a seam, checking where values belong, making code testable or AI-navigable, or when another skill needs this vocabulary or the ownership check.","lutzseverino\u002Frepo-canon","lutzseverino","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28309837?v=4","01M77NN0YKH0YYGY7W7ER23MX0","Jasper","01M7CP5B58PDMK3RT3CE7F70Q2",1,"MIT","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodebase-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codebase-design\ndescription: Shared vocabulary for designing deep modules and checking value ownership. Use when designing a module's interface, choosing or deferring a seam, checking where values belong, making code testable or AI-navigable, or when another skill needs this vocabulary or the ownership check.\n---\n\nA prompt or brief naming this skill is its invocation.\n\n# Codebase Design\n\nDesign **deep modules**: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Use this language and these principles wherever code is being designed or restructured. The aim is leverage for callers, locality for maintainers, and testability for everyone.\n\n## Glossary\n\nUse these terms exactly: don't substitute \"component,\" \"service,\" \"API,\" or \"boundary.\" Consistent language is the whole point.\n\n**Module**: anything with an interface and an implementation. Deliberately scale-agnostic: a function, class, package, or tier-spanning slice. _Avoid_: unit, component, service.\n\n**Interface**: everything a caller must know to use the module correctly: the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics. _Avoid_: API, signature (too narrow, they refer only to the type-level surface).\n\n**Implementation**: what's inside a module, its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for \"adapter\" when the seam is the topic; \"implementation\" otherwise.\n\n**Depth**: leverage at the interface. The amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface, **shallow** when the interface is nearly as complex as the implementation.\n\n**Seam** _(Michael Feathers)_: a place where you can alter behaviour without editing in that place; the *location* at which a module's interface lives. Where to put the seam is its own design decision, distinct from what goes behind it. _Avoid_: boundary (overloaded with DDD's bounded context).\n\n**Adapter**: a concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside).\n\n**Leverage**: what callers get from depth. More capability per unit of interface they learn. One implementation pays back across N call sites and M tests.\n\n**Locality**: what maintainers get from depth. Change, bugs, knowledge, and verification concentrate in one place rather than spreading across callers. Fix once, fixed everywhere.\n\n## Deep vs shallow\n\n**Deep module** = small interface + lots of implementation:\n\n```\n┌─────────────────────┐\n│   Small Interface   │  ← Few methods, simple params\n├─────────────────────┤\n│                     │\n│  Deep Implementation│  ← Complex logic hidden\n│                     │\n└─────────────────────┘\n```\n\n**Shallow module** = large interface + little implementation (avoid):\n\n```\n┌─────────────────────────────────┐\n│       Large Interface           │  ← Many methods, complex params\n├─────────────────────────────────┤\n│  Thin Implementation            │  ← Just passes through\n└─────────────────────────────────┘\n```\n\nWhen designing an interface, ask:\n\n- Can I reduce the number of methods?\n- Can I simplify the parameters?\n- Can I hide more complexity inside?\n\n## Principles\n\n- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts; they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface.\n- **The deletion test.** Imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.\n- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape.\n- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it.\n\n## Ownership check\n\nUse the project's **Value owner**, **Ownership check** and **Deferred seam**\nvocabulary from `GLOSSARY.md`, when present. Check for these triggers:\n\n- **Trigger 1:** modifying or forking vendored or third-party code.\n- **Trigger 2:** adding a configuration kind or a new place a value lives.\n- **Trigger 3:** adding a second or third variant.\n- **Trigger 4:** crossing a repository, product or host boundary, or making them\n  release in lockstep.\n- **Trigger 5:** placing a file where the standard layout would not lead an agent.\n\nWithout a trigger, the whole check is one line: `No trigger`.\nWhen triggered, record the triggers and, for each value:\n\n- its **Value owner**: standard, repository, host or issue, holding the value\n  in its own file (a per-issue choice is an issue label);\n- current and likely consumers;\n- reversibility;\n- cost now and carrying cost, each **S\u002FM\u002FL**.\n\nApply these defaults to the read:\n\n- **Reversible, one consumer:** choose the cheapest path; record the seam as\n  deferred.\n- **Hard to reverse or a second consumer:** wrap.\n- **Third consumer or a seam crossing repositories:** propose extraction in\n  its own ticket for the owner to decide. Extraction covers code and\n  configuration; copied decision text is exempt.\n\nThe author may choose the nicer design immediately when they argue cost now\n**S** and lower carrying cost, and the brief or code reviewer accepts that\nargument. This is a design judgment, not another review gate.\n\n### Deferred seams and touched code\n\nRecord a **Deferred seam** in one line at its code location, for example:\n\n```text\nSeam (deferred): \u003Cwhat varies>; consumers: \u003Cn>; extract at 3.\n```\n\nUpdate the note when a consumer is added. Use an ADR only when the deferral\nitself is a one-way door. **Considered options:** an ordinary note belongs at\nits code so the next change finds and updates it; an ADR would turn a\nreversible implementation choice into a durable decision, and a separate\nseam register would drift away from the code. A friction log holds evidence,\nnever the seam register.\n\nFor existing ownership problems in touched code, take the first applicable\nroute:\n\n1. Fix in place only when cost is **S**, in files already edited,\n   behavior preserving, and listed on its own line in the PR body.\n2. Otherwise, note a seam the change does not need yet, or update its consumer\n   count when adding a consumer; the third prompts the extraction proposal.\n3. Otherwise, use the contribution guide's **Findings** route.\n\nThis permission covers that cleanup, not separate unticketed work or an\nexpansion of factory-run authority. Reviewers check whether touched problems\nwere fixed, noted or filed, and judge the implementation against its contract.\n\n### Disagreeing with a recorded contract\n\nFor a **one-way door** the agent judges wrong, stop through the contribution\nguide's existing owner-question route (`state:grill`), with the trigger and\ncost read. For a **two-way door**, implement the contract and record the\ndeferred seam or finding. Never silently deviate, or silently comply with a\none-way door judged wrong. Follow the guide's question and Findings routes;\nwhen the guide is absent, report the question and stop for a one-way door,\nor report the finding with the handoff for a two-way door.\n\n### Worked examples\n\n**Capability and policy.** In the\n[Scriptorium model-choice split](https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Fscriptorium\u002Fissues\u002F115#issuecomment-6693419305),\na repository preference had migrated between host configuration and an exact\nstandard file. Trigger 2 and Trigger 4 prompt a read: the host owns reachable models,\ncredentials and per-kind defaults in host configuration; the repository owns\nits optional model preferences and unavailable-model fallback in its policy\nfile; the standard owns the schema and check, never those policy values; the\nissue owns its model-label choice. Current consumers are the factory's\ntriage, implement\u002Fretry and review runs; other repositories are likely\nconsumers. Relocating repository values after adoption is hard to reverse:\nthis example rates cost now **M**, carrying cost **L** if values stay misplaced,\nand **S** after the split. Wrap the resolution behind an interface that reads\nissue choice, then repository policy, then host default, within host\ncapabilities. Without the optional policy file, use host defaults. A seam\nshared across repositories prompts a separate extraction proposal for the\nowner; it does not authorize implementing that extraction here.\n\n**Vendored UI.** A product needs one variation of a third-party button. Trigger 1\nprompts the read: upstream owns the copied implementation, the repository owns\nits presentation choice in its wrapper file, and the standard owns no product\nstyling value. There is one current screen consumer and a second likely one;\na local wrapper is reversible. This example rates a source edit cost now\n**S**, carrying cost **M** across upstream updates; a small wrapper costs **S**\nnow and **S** to carry. Choose the wrapper immediately when the brief or\nreviewer accepts that lower carrying cost, rather than editing vendored\nsource. Defer a shared wrapper package at the wrapper's code location with\none consumer; update the count for a second, and propose extraction in its\nown ticket for a third or a cross-repository consumer.\n\n## Designing for testability\n\nGood interfaces make testing natural:\n\n1. **Accept dependencies, don't create them.**\n\n   ```typescript\n   \u002F\u002F Testable\n   function processOrder(order, paymentGateway) {}\n\n   \u002F\u002F Hard to test\n   function processOrder(order) {\n     const gateway = new StripeGateway();\n   }\n   ```\n\n2. **Return results, don't produce side effects.**\n\n   ```typescript\n   \u002F\u002F Testable\n   function calculateDiscount(cart): Discount {}\n\n   \u002F\u002F Hard to test\n   function applyDiscount(cart): void {\n     cart.total -= discount;\n   }\n   ```\n\n3. **Small surface area.** Fewer methods = fewer tests needed. Fewer params = simpler test setup.\n\n## Relationships\n\n- A **Module** has exactly one **Interface** (the surface it presents to callers and tests).\n- **Depth** is a property of a **Module**, measured against its **Interface**.\n- A **Seam** is where a **Module**'s **Interface** lives.\n- An **Adapter** sits at a **Seam** and satisfies the **Interface**.\n- **Depth** produces **Leverage** for callers and **Locality** for maintainers.\n\n## Rejected framings\n\n- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-leverage instead.\n- **\"Interface\" as the TypeScript `interface` keyword or a class's public methods**: too narrow: interface here includes every fact a caller must know.\n- **\"Boundary\"**: overloaded with DDD's bounded context. Say **seam** or **interface**.\n\n## Going deeper\n\n- **Deepening a cluster given its dependencies**, see [DEEPENING.md](DEEPENING.md): dependency categories, seam discipline, and replace-don't-layer testing.\n- **Exploring alternative interfaces**, see [DESIGN-IT-TWICE.md](DESIGN-IT-TWICE.md): spin up parallel sub-agents to design the interface several radically different ways, then compare on depth, locality, and seam placement.\n\n## Reads\n\nPaths are relative to the repository root.\n\n- `GLOSSARY.md`: the project's domain language for ownership and Design It\n  Twice. When it is missing, use this skill's vocabulary.\n- `CONTRIBUTING.md`: Findings and owner-question routes. When it is missing,\n  use the ownership section's question and finding handoff above.\n","A prompt or brief naming this skill is its invocation.\n\n# Codebase Design\n\nDesign **deep modules**: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Use this language and these principles wherever code is being designed or restructured. The aim is leverage for callers, locality for maintainers, and testability for everyone.\n\n## Glossary\n\nUse these terms exactly: don't substitute \"component,\" \"service,\" \"API,\" or \"boundary.\" Consistent language is the whole point.\n\n**Module**: anything with an interface and an implementation. Deliberately scale-agnostic: a function, class, package, or tier-spanning slice. _Avoid_: unit, component, service.\n\n**Interface**: everything a caller must know to use the module correctly: the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics. _Avoid_: API, signature (too narrow, they refer only to the type-level surface).\n\n**Implementation**: what's inside a module, its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for \"adapter\" when the seam is the topic; \"implementation\" otherwise.\n\n**Depth**: leverage at the interface. The amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface, **shallow** when the interface is nearly as complex as the implementation.\n\n**Seam** _(Michael Feathers)_: a place where you can alter behaviour without editing in that place; the *location* at which a module's interface lives. Where to put the seam is its own design decision, distinct from what goes behind it. _Avoid_: boundary (overloaded with DDD's bounded context).\n\n**Adapter**: a concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside).\n\n**Leverage**: what callers get from depth. More capability per unit of interface they learn. One implementation pays back across N call sites and M tests.\n\n**Locality**: what maintainers get from depth. Change, bugs, knowledge, and verification concentrate in one place rather than spreading across callers. Fix once, fixed everywhere.\n\n## Deep vs shallow\n\n**Deep module** = small interface + lots of implementation:\n\n```\n┌─────────────────────┐\n│   Small Interface   │  ← Few methods, simple params\n├─────────────────────┤\n│                     │\n│  Deep Implementation│  ← Complex logic hidden\n│                     │\n└─────────────────────┘\n```\n\n**Shallow module** = large interface + little implementation (avoid):\n\n```\n┌─────────────────────────────────┐\n│       Large Interface           │  ← Many methods, complex params\n├─────────────────────────────────┤\n│  Thin Implementation            │  ← Just passes through\n└─────────────────────────────────┘\n```\n\nWhen designing an interface, ask:\n\n- Can I reduce the number of methods?\n- Can I simplify the parameters?\n- Can I hide more complexity inside?\n\n## Principles\n\n- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts; they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface.\n- **The deletion test.** Imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.\n- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape.\n- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it.\n\n## Ownership check\n\nUse the project's **Value owner**, **Ownership check** and **Deferred seam**\nvocabulary from `GLOSSARY.md`, when present. Check for these triggers:\n\n- **Trigger 1:** modifying or forking vendored or third-party code.\n- **Trigger 2:** adding a configuration kind or a new place a value lives.\n- **Trigger 3:** adding a second or third variant.\n- **Trigger 4:** crossing a repository, product or host boundary, or making them\n  release in lockstep.\n- **Trigger 5:** placing a file where the standard layout would not lead an agent.\n\nWithout a trigger, the whole check is one line: `No trigger`.\nWhen triggered, record the triggers and, for each value:\n\n- its **Value owner**: standard, repository, host or issue, holding the value\n  in its own file (a per-issue choice is an issue label);\n- current and likely consumers;\n- reversibility;\n- cost now and carrying cost, each **S\u002FM\u002FL**.\n\nApply these defaults to the read:\n\n- **Reversible, one consumer:** choose the cheapest path; record the seam as\n  deferred.\n- **Hard to reverse or a second consumer:** wrap.\n- **Third consumer or a seam crossing repositories:** propose extraction in\n  its own ticket for the owner to decide. Extraction covers code and\n  configuration; copied decision text is exempt.\n\nThe author may choose the nicer design immediately when they argue cost now\n**S** and lower carrying cost, and the brief or code reviewer accepts that\nargument. This is a design judgment, not another review gate.\n\n### Deferred seams and touched code\n\nRecord a **Deferred seam** in one line at its code location, for example:\n\n```text\nSeam (deferred): \u003Cwhat varies>; consumers: \u003Cn>; extract at 3.\n```\n\nUpdate the note when a consumer is added. Use an ADR only when the deferral\nitself is a one-way door. **Considered options:** an ordinary note belongs at\nits code so the next change finds and updates it; an ADR would turn a\nreversible implementation choice into a durable decision, and a separate\nseam register would drift away from the code. A friction log holds evidence,\nnever the seam register.\n\nFor existing ownership problems in touched code, take the first applicable\nroute:\n\n1. Fix in place only when cost is **S**, in files already edited,\n   behavior preserving, and listed on its own line in the PR body.\n2. Otherwise, note a seam the change does not need yet, or update its consumer\n   count when adding a consumer; the third prompts the extraction proposal.\n3. Otherwise, use the contribution guide's **Findings** route.\n\nThis permission covers that cleanup, not separate unticketed work or an\nexpansion of factory-run authority. Reviewers check whether touched problems\nwere fixed, noted or filed, and judge the implementation against its contract.\n\n### Disagreeing with a recorded contract\n\nFor a **one-way door** the agent judges wrong, stop through the contribution\nguide's existing owner-question route (`state:grill`), with the trigger and\ncost read. For a **two-way door**, implement the contract and record the\ndeferred seam or finding. Never silently deviate, or silently comply with a\none-way door judged wrong. Follow the guide's question and Findings routes;\nwhen the guide is absent, report the question and stop for a one-way door,\nor report the finding with the handoff for a two-way door.\n\n### Worked examples\n\n**Capability and policy.** In the\n[Scriptorium model-choice split](https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Fscriptorium\u002Fissues\u002F115#issuecomment-6693419305),\na repository preference had migrated between host configuration and an exact\nstandard file. Trigger 2 and Trigger 4 prompt a read: the host owns reachable models,\ncredentials and per-kind defaults in host configuration; the repository owns\nits optional model preferences and unavailable-model fallback in its policy\nfile; the standard owns the schema and check, never those policy values; the\nissue owns its model-label choice. Current consumers are the factory's\ntriage, implement\u002Fretry and review runs; other repositories are likely\nconsumers. Relocating repository values after adoption is hard to reverse:\nthis example rates cost now **M**, carrying cost **L** if values stay misplaced,\nand **S** after the split. Wrap the resolution behind an interface that reads\nissue choice, then repository policy, then host default, within host\ncapabilities. Without the optional policy file, use host defaults. A seam\nshared across repositories prompts a separate extraction proposal for the\nowner; it does not authorize implementing that extraction here.\n\n**Vendored UI.** A product needs one variation of a third-party button. Trigger 1\nprompts the read: upstream owns the copied implementation, the repository owns\nits presentation choice in its wrapper file, and the standard owns no product\nstyling value. There is one current screen consumer and a second likely one;\na local wrapper is reversible. This example rates a source edit cost now\n**S**, carrying cost **M** across upstream updates; a small wrapper costs **S**\nnow and **S** to carry. Choose the wrapper immediately when the brief or\nreviewer accepts that lower carrying cost, rather than editing vendored\nsource. Defer a shared wrapper package at the wrapper's code location with\none consumer; update the count for a second, and propose extraction in its\nown ticket for a third or a cross-repository consumer.\n\n## Designing for testability\n\nGood interfaces make testing natural:\n\n1. **Accept dependencies, don't create them.**\n\n   ```typescript\n   \u002F\u002F Testable\n   function processOrder(order, paymentGateway) {}\n\n   \u002F\u002F Hard to test\n   function processOrder(order) {\n     const gateway = new StripeGateway();\n   }\n   ```\n\n2. **Return results, don't produce side effects.**\n\n   ```typescript\n   \u002F\u002F Testable\n   function calculateDiscount(cart): Discount {}\n\n   \u002F\u002F Hard to test\n   function applyDiscount(cart): void {\n     cart.total -= discount;\n   }\n   ```\n\n3. **Small surface area.** Fewer methods = fewer tests needed. Fewer params = simpler test setup.\n\n## Relationships\n\n- A **Module** has exactly one **Interface** (the surface it presents to callers and tests).\n- **Depth** is a property of a **Module**, measured against its **Interface**.\n- A **Seam** is where a **Module**'s **Interface** lives.\n- An **Adapter** sits at a **Seam** and satisfies the **Interface**.\n- **Depth** produces **Leverage** for callers and **Locality** for maintainers.\n\n## Rejected framings\n\n- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-leverage instead.\n- **\"Interface\" as the TypeScript `interface` keyword or a class's public methods**: too narrow: interface here includes every fact a caller must know.\n- **\"Boundary\"**: overloaded with DDD's bounded context. Say **seam** or **interface**.\n\n## Going deeper\n\n- **Deepening a cluster given its dependencies**, see [DEEPENING.md](DEEPENING.md): dependency categories, seam discipline, and replace-don't-layer testing.\n- **Exploring alternative interfaces**, see [DESIGN-IT-TWICE.md](DESIGN-IT-TWICE.md): spin up parallel sub-agents to design the interface several radically different ways, then compare on depth, locality, and seam placement.\n\n## Reads\n\nPaths are relative to the repository root.\n\n- `GLOSSARY.md`: the project's domain language for ownership and Design It\n  Twice. When it is missing, use this skill's vocabulary.\n- `CONTRIBUTING.md`: Findings and owner-question routes. When it is missing,\n  use the ownership section's question and finding handoff above.\n",{"name":5,"description":7},"main","f5a3e334f7bc0fce1854f224a8e78c53f8ea75b9",".agents\u002Fskills\u002Fcodebase-design",0,"https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon","https:\u002F\u002Frepo-standards.com\u002Fsources\u002Flutzseverino\u002Frepo-canon\u002F","https:\u002F\u002Fgithub.com\u002Flutzseverino","If Codex could write profile bios, you wouldn't be reading this. Or would you?","2026-11-15 06:12:31",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lutzseverino\u002Frepo-canon --skill codebase-design",{"tool":39,"command":40},"bunx","bunx skills add lutzseverino\u002Frepo-canon --skill codebase-design",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lutzseverino\u002Frepo-canon --skill codebase-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodebase-design\u002FSKILL.md",true,[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",102,"https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodebase-design\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"CREDITS.md",2161,"https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodebase-design\u002FCREDITS.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"DEEPENING.md",2553,"https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodebase-design\u002FDEEPENING.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"DESIGN-IT-TWICE.md",2665,"https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcodebase-design\u002FDESIGN-IT-TWICE.md",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7CP829W88YVACQ3ZFS4KYAK","repository-standards","Look up installed rules before any work in a disposable planning exercise, including tracker work and file changes.","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002Fscripts\u002Fsupport\u002Frepository-standards\u002FSKILL.md",[],[],{"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":19},"01M7CP7Y70KNBJBVDNGSQ6RGG4","triage","Move issues and external PRs through a state machine of triage roles, sort each request by where its uncertainty lies, and bring its agent brief to acceptance through research and independent review, or through a grilling session with the owner.","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.repo-standards\u002Finputs\u002Fsource\u002F.agents\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7CP7TWX07ST84HT5XNEYS1J","orchestrate","Turn the owner's feature or problem into an approved plan across tickets, keep its state in the workbench, and run it to an announced close.","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.repo-standards\u002Finputs\u002Fsource\u002F.agents\u002Fskills\u002Forchestrate\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7CP7QE6M9W0E24BV0VZV1RS","babysit","Babysit an opened pull request through checks and review to merge or its prescribed handoff. Use right after opening a pull request, or when asked to babysit or land one.","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.repo-standards\u002Finputs\u002Fsource\u002F.agents\u002Fskills\u002Fbabysit\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7CP7N4VMT6C4THVN2RBRB5Q","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7CP7GN4YYS18YS91N0AN0PK","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Flutzseverino\u002Frepo-canon\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]