[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EFDFCY4V0JMQHSEE34A2JS":3,"skill-same:01M7EFDFCY4V0JMQHSEE34A2JS":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7EFDFCY4V0JMQHSEE34A2JS","using-agent-skills",null,"Use when starting a new session, switching tasks, or unsure which arthurpower skill applies. Routes incoming work to the matching skill via flowchart before invoking. Activates on phrases like \"which skill should I use\", \"skill check\", \"pre-task skill check\", \"how to start\", \"router\", \"skill routing\", or when multiple competing skills could apply. Does not auto-invoke user-invoked authoring skills (skill-authoring, self-evolving-rules).","winter6205\u002Farthurpower","winter6205","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F136674824?v=4","01M7EF9EWNYDKHX9MR3AG5QV7A","01M7EF9EXCC1CNFXQNV6PS3M8B",2,"MIT","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: using-agent-skills\ndescription: Use when starting a new session, switching tasks, or unsure which arthurpower skill applies. Routes incoming work to the matching skill via flowchart before invoking. Activates on phrases like \"which skill should I use\", \"skill check\", \"pre-task skill check\", \"how to start\", \"router\", \"skill routing\", or when multiple competing skills could apply. Does not auto-invoke user-invoked authoring skills (skill-authoring, self-evolving-rules).\nbucket: engineering\ntype: discipline\n---\n\n# Using Agent Skills\n\nSkill router for the arthurpower collection. It names the **task class** and the **current slot** in any documented sequence, then invokes that one skill. It does not do the downstream work.\n\nUser-invoked only (`disable-model-invocation: true` on the target): `skill-authoring`, `self-evolving-rules`. The operator must name them. Other skills, including `dispatching-parallel-agents`, are model-invoked playbooks the current agent may run when their triggers match.\n\n## When to use\n\n- A new session whose first task is unclassified\n- The user asks which skill \u002F how to start \u002F skill check \u002F routing\n- Several skills could match (ambiguous routing)\n- Switching task class mid-session (planning → implementing → verifying)\n\nSkip when the task already maps to one skill, the user already named a skill, the edit is trivial, or the work is outside this graph.\n\n## Procedure\n\n1. **Classify.** Match the task to one branch in [`references\u002Fflowchart.md`](references\u002Fflowchart.md) (Defining \u002F Planning \u002F Implementing \u002F Verifying \u002F Reviewing \u002F Committing \u002F Meta). Scale (single vs multi-session) selects a **sequence**, not a pile of skills in one turn. Completion: one branch label, and if scale applies, the sequence named.\n\n2. **User-invoked gate.** If the match is `skill-authoring` or `self-evolving-rules` and the user did not name it, stop and ask. Completion: either a different skill, or the user named that skill.\n\n3. **Current slot.** Documented sequences (SPECIFY → `architecture-change-reviewer` → persist → `writing-plans`; `code-review` → `review-report-repair` when `GATE: BLOCKED`) are ordered gates. Invoke **this slot only**; do not stack the whole sequence. Competing skills for the same slot (e.g. ACR and `code-review` as \"the review\") are not a sequence — pick one. Completion: the slot's skill name.\n\n4. **Invoke.** State the routing decision in one sentence, then invoke that skill. CONTEXT \u002F ADR writes go through `domain-modeling` when a persist list exists. Completion: the chosen skill started.\n\nPromoted skill add \u002F rename \u002F remove \u002F flow-placement updates this file and [`references\u002Fquick-reference.md`](references\u002Fquick-reference.md) in the same change. Default landing sequence: [`references\u002Flanding.md`](references\u002Flanding.md). Details: [`references\u002Frouter-maintenance.md`](references\u002Frouter-maintenance.md).\n\n## Registered skills (hook mirror)\n\n`hooks\u002Fpre-release-validate.ts` greps this `SKILL.md` for each sibling directory basename. Keep every promoted skill named below. Phase \u002F trigger tables live in [`references\u002Fquick-reference.md`](references\u002Fquick-reference.md), not here.\n\n- architecture-change-reviewer\n- boundary-testing\n- bounded-context-guardian\n- code-review\n- review-report-repair\n- complexity-anti-drift\n- input-contract-tests\n- dispatching-parallel-agents\n- domain-modeling\n- error-handling-enforcer\n- logicsync\n- minimal-change-verifier\n- self-evolving-rules\n- session-handoff\n- setup-arthurpower\n- skill-authoring\n- spec-driven-development\n- systematic-debugging\n- test-driven-development\n- verification-before-completion\n- wayfinder\n- writing-plans\n\n## Acceptance\n\n- [ ] Flowchart branch chosen before any skill invoke\n- [ ] One task class; if a sequence, only the current slot invoked\n- [ ] User-invoked authoring skills not auto-started\n- [ ] Routing stated in one sentence\n- [ ] No catch-all meta skill when a focused skill matches\n\n## References\n\n- [`references\u002Fflowchart.md`](references\u002Fflowchart.md) — branches including scale sequences\n- [`references\u002Fquick-reference.md`](references\u002Fquick-reference.md) — phase \u002F trigger \u002F user-invoked vs model-invoked\n- [`references\u002Frouter-maintenance.md`](references\u002Frouter-maintenance.md) — add \u002F rename \u002F remove \u002F flow-placement\n- [`references\u002Fbehaviors.md`](references\u002Fbehaviors.md) — optional operating habits (not routing)\n","# Using Agent Skills\n\nSkill router for the arthurpower collection. It names the **task class** and the **current slot** in any documented sequence, then invokes that one skill. It does not do the downstream work.\n\nUser-invoked only (`disable-model-invocation: true` on the target): `skill-authoring`, `self-evolving-rules`. The operator must name them. Other skills, including `dispatching-parallel-agents`, are model-invoked playbooks the current agent may run when their triggers match.\n\n## When to use\n\n- A new session whose first task is unclassified\n- The user asks which skill \u002F how to start \u002F skill check \u002F routing\n- Several skills could match (ambiguous routing)\n- Switching task class mid-session (planning → implementing → verifying)\n\nSkip when the task already maps to one skill, the user already named a skill, the edit is trivial, or the work is outside this graph.\n\n## Procedure\n\n1. **Classify.** Match the task to one branch in [`references\u002Fflowchart.md`](references\u002Fflowchart.md) (Defining \u002F Planning \u002F Implementing \u002F Verifying \u002F Reviewing \u002F Committing \u002F Meta). Scale (single vs multi-session) selects a **sequence**, not a pile of skills in one turn. Completion: one branch label, and if scale applies, the sequence named.\n\n2. **User-invoked gate.** If the match is `skill-authoring` or `self-evolving-rules` and the user did not name it, stop and ask. Completion: either a different skill, or the user named that skill.\n\n3. **Current slot.** Documented sequences (SPECIFY → `architecture-change-reviewer` → persist → `writing-plans`; `code-review` → `review-report-repair` when `GATE: BLOCKED`) are ordered gates. Invoke **this slot only**; do not stack the whole sequence. Competing skills for the same slot (e.g. ACR and `code-review` as \"the review\") are not a sequence — pick one. Completion: the slot's skill name.\n\n4. **Invoke.** State the routing decision in one sentence, then invoke that skill. CONTEXT \u002F ADR writes go through `domain-modeling` when a persist list exists. Completion: the chosen skill started.\n\nPromoted skill add \u002F rename \u002F remove \u002F flow-placement updates this file and [`references\u002Fquick-reference.md`](references\u002Fquick-reference.md) in the same change. Default landing sequence: [`references\u002Flanding.md`](references\u002Flanding.md). Details: [`references\u002Frouter-maintenance.md`](references\u002Frouter-maintenance.md).\n\n## Registered skills (hook mirror)\n\n`hooks\u002Fpre-release-validate.ts` greps this `SKILL.md` for each sibling directory basename. Keep every promoted skill named below. Phase \u002F trigger tables live in [`references\u002Fquick-reference.md`](references\u002Fquick-reference.md), not here.\n\n- architecture-change-reviewer\n- boundary-testing\n- bounded-context-guardian\n- code-review\n- review-report-repair\n- complexity-anti-drift\n- input-contract-tests\n- dispatching-parallel-agents\n- domain-modeling\n- error-handling-enforcer\n- logicsync\n- minimal-change-verifier\n- self-evolving-rules\n- session-handoff\n- setup-arthurpower\n- skill-authoring\n- spec-driven-development\n- systematic-debugging\n- test-driven-development\n- verification-before-completion\n- wayfinder\n- writing-plans\n\n## Acceptance\n\n- [ ] Flowchart branch chosen before any skill invoke\n- [ ] One task class; if a sequence, only the current slot invoked\n- [ ] User-invoked authoring skills not auto-started\n- [ ] Routing stated in one sentence\n- [ ] No catch-all meta skill when a focused skill matches\n\n## References\n\n- [`references\u002Fflowchart.md`](references\u002Fflowchart.md) — branches including scale sequences\n- [`references\u002Fquick-reference.md`](references\u002Fquick-reference.md) — phase \u002F trigger \u002F user-invoked vs model-invoked\n- [`references\u002Frouter-maintenance.md`](references\u002Frouter-maintenance.md) — add \u002F rename \u002F remove \u002F flow-placement\n- [`references\u002Fbehaviors.md`](references\u002Fbehaviors.md) — optional operating habits (not routing)\n",{"name":5,"type":23,"bucket":24,"description":7},"discipline","engineering","master","1a067ffc9024631d22ca8bf2b47ad81369f28056","arthurpower\u002Fskills\u002Fusing-agent-skills",0,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower","https:\u002F\u002Fgithub.com\u002Fwinter6205","2026-10-28 23:46:38",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add winter6205\u002Farthurpower --skill using-agent-skills",{"tool":38,"command":39},"bunx","bunx skills add winter6205\u002Farthurpower --skill using-agent-skills",{"tool":41,"command":42},"pnpm","pnpm dlx skills add winter6205\u002Farthurpower --skill using-agent-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",true,[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fbehaviors.md","REFERENCE","参考文档",1578,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002Freferences\u002Fbehaviors.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fflowchart.md",3176,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002Freferences\u002Fflowchart.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fgit-workflow.md",7543,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002Freferences\u002Fgit-workflow.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Flanding.md",867,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002Freferences\u002Flanding.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fquick-reference.md",3075,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002Freferences\u002Fquick-reference.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Frouter-maintenance.md",795,"https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fusing-agent-skills\u002Freferences\u002Frouter-maintenance.md",[73,80,87,94,101,108],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7EFDX3VT33HSHDA17T9N9JJ","writing-plans","Use when turning a buildable spec into ordered tracer bullets after architecture-change-reviewer. Covers vertical slicing, dependency order, and headroom for the implementer. Triggers on 写计划, 拆任务, 任务分解, 制定方案, 跨文件改动, 计划.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7EFDQV6SGJWDK634DWPFR35","wayfinder","Use when a chunk of work is more than one agent session can hold — plan it 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\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7EFDM9Y55GKYFGY96088BYB","verification-before-completion","This skill should be used when claiming \"完成\" \u002F \"done\" \u002F \"fixed\" \u002F \"passing\" \u002F \"ready to ship\", before trusting a subagent success report, or when checking \"对照计划\" \u002F \"对照 spec\" — whether this run's delivery matches its basis.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M7EFDB70ATNQASXP4BKDYGA6","test-driven-development","Use when implementing logic, fixing a bug, or changing behavior — write the failing test first (RED), then minimal code (GREEN), then refactor. Triggers on \"write the failing test first\", \"Prove-It\", or a bug that needs a reproduction test before the fix.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M7EFD6NPWFG5WSXT0DF07XH1","systematic-debugging","Use when debugging a test failure, build break, unexpected runtime error, flaky test, or hanging process. Triggers on phrases like \"fix this bug\", \"getting an error\", \"failing test\", \"flaky\", \"hanging\", \"halfway through debugging\", \"this used to work\", \"intermittent failure\", \"stack trace shows X\", or any case where behavior does not match expectations. Prevents shotgun debugging.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":18},"01M7EFD2BSFHQYRCNX49CBB9AK","spec-driven-development","Use when the work isn't a spec yet — a one-line ask, multi-file change, ambiguous scope, or architectural decision on the table. Spec-driven-development captures what to build, why, and how to know it's done before any plan or commit. Skip for single-line fixes or bounded bug fixes.","https:\u002F\u002Fgithub.com\u002Fwinter6205\u002Farthurpower\u002Fblob\u002Fmaster\u002Farthurpower\u002Fskills\u002Fspec-driven-development\u002FSKILL.md",[],[]]