[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CTH1EHZR660ANDXJV2KA19":3,"skill-same:01M7CTH1EHZR660ANDXJV2KA19":51},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CTH1EHZR660ANDXJV2KA19","capture-subsystem",null,"Capture a stable subsystem's mental model, invariants, and key files as a reusable skill after deep research. Use for durable subsystem knowledge; use artifact-logging for ephemeral findings.","xiaden\u002FSkyScow","xiaden","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3605480?v=4","01M7CTGKNTD1XNQE710J977HVD","Lucian Hardy","01M7CTGKPVQ3XRNXNRJ3A6E31F",1,"MIT","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fcapture-subsystem\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: capture-subsystem\ndescription: Capture a stable subsystem's mental model, invariants, and key files as a reusable skill after deep research. Use for durable subsystem knowledge; use artifact-logging for ephemeral findings.\n---\n\n# Capture Subsystem\n\nYou have just done expensive research on a stable subsystem. Capture the mental model now — once — rather than rediscovering it every session.\n\n## Check Before Creating\n\n**Before creating a new skill, check if one already exists** for this subsystem. Skills live in `{project_skills_dir}` and `{tooling_skills_dir}`. If a skill exists:\n- **Extend it** with what you just learned — do not create a duplicate\n- Update the `## Coverage` section\n- If you learned something that contradicts the skill, fix the skill and note the change\n\nA partial skill that labels its gaps is always preferable to no skill. A partial skill with *unlabeled* gaps causes confident wrong reasoning — worse than no skill.\n\n## What Belongs\n\nA subsystem skill answers: **\"What does a competent engineer need to know before touching this area?\"**\n\n**Include:**\n- The intended mental model — why this architecture, not just what it does\n- Process\u002Fthread\u002FIPC topology (who owns what, how parts communicate)\n- Key invariants an agent must not violate\n- Which files are canonical owners of each concern\n- How the subsystem connects to the rest of the system (entry\u002Fexit points)\n- Citations to the governing decisions (from the `architecture-decisions` skill) and prior design docs that motivated the design\n\n**Do not include:**\n- Implementation details that change with normal refactors (method signatures, variable names)\n- Information already obvious from reading one file\n- Anything the model already knows (Python stdlib, FastAPI patterns, etc.)\n- Episodic history (\"we tried X and it failed\") — that belongs in logs\u002Fprocess history\n\n## The Test\n\nIf an agent reads all the files in the subsystem but still doesn't know *why* it's structured this way or *what would break* if they changed it naively — the gap belongs in a skill.\n\n## Structure\n\nPlace project-specific subsystem skills in `{project_skills_dir}\u002F{subsystem-name}\u002FSKILL.md`.\nPlace generic\u002Ftooling skills in `{tooling_skills_dir}\u002F{skill-name}\u002FSKILL.md`.\n\n```\n{project_skills_dir}\u002Fmy-subsystem\u002F\n├── SKILL.md                  ← frontmatter + mental model + key files table + invariants\n└── references\u002F               ← optional: full topology, schema, edge cases if large\n    └── architecture.md\n```\n\nKeep `SKILL.md` scannable — the body should contain what every invocation needs. Move detailed examples, topology diagrams, and edge cases to `references\u002F` and link them.\n\n## Required Sections\n\nEvery subsystem orientation skill must include these sections, in order:\n\n1. **One-paragraph mental model** — the \"explain it to a new hire in 60 seconds\" summary\n2. **Coverage** — formal declaration of what this skill documents and what it does not\n3. **Key Files table** — area → canonical file, no descriptions, just the map\n4. **Critical Invariants** — the things an agent must never break, stated as constraints\n5. **Common Task Patterns** (optional) — if there are 2-3 stereotyped tasks that are easy to get wrong\n\n## Coverage Section Format\n\nEvery subsystem skill **must** include a `## Coverage` section immediately after the mental model. This is the staleness and incompleteness signal for future agents.\n\n```markdown\n## Coverage\n\n**Documented:** \u003Ccomma-separated list of concerns this skill covers>\n\n**Not yet documented:** \u003Ccomma-separated list of known gaps, or \"none known\">\n\n**Last extended:** YYYY-MM-DD\n```\n\nRules:\n- `Documented` lists specific concerns — not the subsystem name, the *concerns*\n- `Not yet documented` lists known gaps — areas that exist in the subsystem but weren't researched yet\n- `Last extended` is the ISO date the skill was last written or extended\n- When extending a skill, move items from `Not yet documented` to `Documented`, and add new gaps discovered\n- If `Not yet documented` is empty, write `none known` — do not omit the field\n\n## Frontmatter Discipline\n\nThe `description` field is the trigger selector. It must:\n- Name the subsystem explicitly (agents match on nouns)\n- List the *tasks* that should load it, not just the domain\n- Be specific enough that it doesn't load for every session\n\nSee [`references\u002Fexamples.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fcapture-subsystem\u002Freferences\u002Fexamples.md) for good and bad description examples with explanations, plus a full annotated example of a well-structured subsystem skill.\n\n## Source Citations\n\nEvery skill must cite its authoritative sources. Include at the bottom:\n\n```\n## Sources\n- ADR-NNN: Title\n- DD: slug (artifacts\u002Fdesigns\u002F...)\n```\n\nIf no governing decision or prior design doc exists for the design decision, that's a gap worth noting — the skill can serve as informal documentation until a proper record is committed through the `artifact-logging` workflow.\n\n## Staleness Contract\n\nA skill is a *view* over governing decisions and design docs. When the underlying design changes:\n- The governance-record supersession and the skill update must be in the same commit\n- If the skill becomes stale, it causes confident wrong reasoning — worse than no skill\n- Always include a `## Sources` section so future maintainers know which governance records to check\n\n## References\n\n- [`references\u002Fexamples.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fcapture-subsystem\u002Freferences\u002Fexamples.md) — Full annotated example, good\u002Fbad description patterns, and when NOT to create a skill\n- Related skills: `making-editing-skills` (skill structure conventions), `artifact-logging` (logging conventions)\n\nBase directory for this skill: \u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fcapture-subsystem\n","# Capture Subsystem\n\nYou have just done expensive research on a stable subsystem. Capture the mental model now — once — rather than rediscovering it every session.\n\n## Check Before Creating\n\n**Before creating a new skill, check if one already exists** for this subsystem. Skills live in `{project_skills_dir}` and `{tooling_skills_dir}`. If a skill exists:\n- **Extend it** with what you just learned — do not create a duplicate\n- Update the `## Coverage` section\n- If you learned something that contradicts the skill, fix the skill and note the change\n\nA partial skill that labels its gaps is always preferable to no skill. A partial skill with *unlabeled* gaps causes confident wrong reasoning — worse than no skill.\n\n## What Belongs\n\nA subsystem skill answers: **\"What does a competent engineer need to know before touching this area?\"**\n\n**Include:**\n- The intended mental model — why this architecture, not just what it does\n- Process\u002Fthread\u002FIPC topology (who owns what, how parts communicate)\n- Key invariants an agent must not violate\n- Which files are canonical owners of each concern\n- How the subsystem connects to the rest of the system (entry\u002Fexit points)\n- Citations to the governing decisions (from the `architecture-decisions` skill) and prior design docs that motivated the design\n\n**Do not include:**\n- Implementation details that change with normal refactors (method signatures, variable names)\n- Information already obvious from reading one file\n- Anything the model already knows (Python stdlib, FastAPI patterns, etc.)\n- Episodic history (\"we tried X and it failed\") — that belongs in logs\u002Fprocess history\n\n## The Test\n\nIf an agent reads all the files in the subsystem but still doesn't know *why* it's structured this way or *what would break* if they changed it naively — the gap belongs in a skill.\n\n## Structure\n\nPlace project-specific subsystem skills in `{project_skills_dir}\u002F{subsystem-name}\u002FSKILL.md`.\nPlace generic\u002Ftooling skills in `{tooling_skills_dir}\u002F{skill-name}\u002FSKILL.md`.\n\n```\n{project_skills_dir}\u002Fmy-subsystem\u002F\n├── SKILL.md                  ← frontmatter + mental model + key files table + invariants\n└── references\u002F               ← optional: full topology, schema, edge cases if large\n    └── architecture.md\n```\n\nKeep `SKILL.md` scannable — the body should contain what every invocation needs. Move detailed examples, topology diagrams, and edge cases to `references\u002F` and link them.\n\n## Required Sections\n\nEvery subsystem orientation skill must include these sections, in order:\n\n1. **One-paragraph mental model** — the \"explain it to a new hire in 60 seconds\" summary\n2. **Coverage** — formal declaration of what this skill documents and what it does not\n3. **Key Files table** — area → canonical file, no descriptions, just the map\n4. **Critical Invariants** — the things an agent must never break, stated as constraints\n5. **Common Task Patterns** (optional) — if there are 2-3 stereotyped tasks that are easy to get wrong\n\n## Coverage Section Format\n\nEvery subsystem skill **must** include a `## Coverage` section immediately after the mental model. This is the staleness and incompleteness signal for future agents.\n\n```markdown\n## Coverage\n\n**Documented:** \u003Ccomma-separated list of concerns this skill covers>\n\n**Not yet documented:** \u003Ccomma-separated list of known gaps, or \"none known\">\n\n**Last extended:** YYYY-MM-DD\n```\n\nRules:\n- `Documented` lists specific concerns — not the subsystem name, the *concerns*\n- `Not yet documented` lists known gaps — areas that exist in the subsystem but weren't researched yet\n- `Last extended` is the ISO date the skill was last written or extended\n- When extending a skill, move items from `Not yet documented` to `Documented`, and add new gaps discovered\n- If `Not yet documented` is empty, write `none known` — do not omit the field\n\n## Frontmatter Discipline\n\nThe `description` field is the trigger selector. It must:\n- Name the subsystem explicitly (agents match on nouns)\n- List the *tasks* that should load it, not just the domain\n- Be specific enough that it doesn't load for every session\n\nSee [`references\u002Fexamples.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fcapture-subsystem\u002Freferences\u002Fexamples.md) for good and bad description examples with explanations, plus a full annotated example of a well-structured subsystem skill.\n\n## Source Citations\n\nEvery skill must cite its authoritative sources. Include at the bottom:\n\n```\n## Sources\n- ADR-NNN: Title\n- DD: slug (artifacts\u002Fdesigns\u002F...)\n```\n\nIf no governing decision or prior design doc exists for the design decision, that's a gap worth noting — the skill can serve as informal documentation until a proper record is committed through the `artifact-logging` workflow.\n\n## Staleness Contract\n\nA skill is a *view* over governing decisions and design docs. When the underlying design changes:\n- The governance-record supersession and the skill update must be in the same commit\n- If the skill becomes stale, it causes confident wrong reasoning — worse than no skill\n- Always include a `## Sources` section so future maintainers know which governance records to check\n\n## References\n\n- [`references\u002Fexamples.md`](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fcapture-subsystem\u002Freferences\u002Fexamples.md) — Full annotated example, good\u002Fbad description patterns, and when NOT to create a skill\n- Related skills: `making-editing-skills` (skill structure conventions), `artifact-logging` (logging conventions)\n\nBase directory for this skill: \u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fcapture-subsystem\n",{"name":5,"description":7},"main","8f95d6b7cbf4ec39161b4e6c8bc5e1493e58003c","config\u002Fskills\u002Fcapture-subsystem",0,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow","https:\u002F\u002Fgithub.com\u002Fxiaden","2026-09-30 22:33:49",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add xiaden\u002FSkyScow --skill capture-subsystem",{"tool":37,"command":38},"bunx","bunx skills add xiaden\u002FSkyScow --skill capture-subsystem",{"tool":40,"command":41},"pnpm","pnpm dlx skills add xiaden\u002FSkyScow --skill capture-subsystem","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fcapture-subsystem\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fexamples.md","REFERENCE","参考文档",6513,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fcapture-subsystem\u002Freferences\u002Fexamples.md",[52,58,65,71,78,85],{"skillNo":53,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7CTNJ49PJ794TEFBCNYYKQM","unquoted-colon","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Funquoted-colon\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7CTNENFBZPEX63HNSRBCW4T","quoted-description","Use when a plain scalar contains a colon: like this one.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Fquoted-description\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CTNBBPKA6GMCVEM3GPB59F","block-description","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Fblock-description\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CTN4M0SR4Z4TPJMHWC3A3B","work-routing","Canonical authority for who owns the next unit of work — direct work versus delegation, task tiers, bounded localization, the Change DAG size threshold, R&D evaluation routing, progressive research escalation, researcher scope signals, and QA\u002Fsupport owner selection. Use before choosing execution, investigation, design, or QA ownership; do not use to construct dispatch prompts, handoff schemas, or Change DAG\u002FDD tool operation.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fwork-routing\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CTMY5AY3NSNHGQJA0M7VP9","update-docs","Update project documentation to match code changes — generate codemaps, refresh READMEs, detect doc\u002Fcode drift using AST analysis. Use when updating documentation after code changes, generating codemaps, verifying doc accuracy, or detecting stale documentation. Do NOT use for writing API reference docs from scratch (use doc-coauthoring) or for creating new skill files (use making-editing-skills).","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fupdate-docs\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CTMSQD82CPD53C6F07J0R9","skill-loading-system","Explain or troubleshoot OpenCode skill discovery, loading, permissions, availability, or prompt injection.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fskill-loading-system\u002FSKILL.md",[],[]]