[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CWKQCYJXDCW4MEF3FSJE26":3,"skill-same:01M6CWKQCYJXDCW4MEF3FSJE26":201},{"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":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6CWKQCYJXDCW4MEF3FSJE26","using-spec-first",null,"Standalone entry governor for spec-first. Use before substantial work in a spec-first repo or when the user asks what to run next; choose one public `spec-*` workflow, standalone skill, terminal command, or Direct Lane. Do not use to reroute active public workflows or bounded workers, or for lightweight facts, current-context explanations, narrow lookups, user-supplied single-document cleanup, or clearly scoped low-risk edits.","leo-kuang-ai\u002Fspec-first","leo-kuang-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F8476392?v=4","01M6CWDM2YRT5M8C3G3QC3YGR5","leokuang","01M6CWDM6X46EFBXT1M1GDB5XC",111,"MIT","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"using spec first","first","spec","choose","active","next","do","use","context","command","repo","work","direct","risk","lane","run","cleanup","workflows","workflow","terminal","2026-11-10 10:12:30",false,"---\nname: using-spec-first\ndescription: Standalone entry governor for spec-first. Use before substantial work in a spec-first repo or when the user asks what to run next; choose one public `spec-*` workflow, standalone skill, terminal command, or Direct Lane. Do not use to reroute active public workflows or bounded workers, or for lightweight facts, current-context explanations, narrow lookups, user-supplied single-document cleanup, or clearly scoped low-risk edits.\n---\n\n# Using Spec-First\n\n`using-spec-first` is a standalone entry governor, not a command-backed workflow. It selects one next entrypoint and yields control; it creates no workflow artifact. It is a semantic map, not a rigid state machine.\n\n## Workflow Contract Summary\n\n- **输入：** 当前用户意图、已有 workflow 状态、artifact 类型、失败\u002F环境信号与项目级路由规则。\n- **输出：** 恰好一个 public `spec-*` workflow、standalone skill、terminal command 或 Direct Lane 入口；进入后立即把控制权交给该 owner。\n- **硬出口：** 入口选择不授权 mutation、verification claim、runtime maintenance、handoff、knowledge promotion、commit 或 landing；低置信且会改变 route 时最多询问一个问题。\n- **权威：** 用户意图与项目 source rules 决定 route；本 skill 只做语义路由，不创建 workflow state 或执行下游工作。\n- **消费者：** 当前用户、所有 public workflow、standalone skill 与 host runtime entrypoint。\n\n## Fast Paths\n\n- Continue an active public workflow or bounded worker; do not restart routing.\n- Use the Direct Lane only for current-context explanations, lightweight facts, one-off how-to explanations, command-output explanations, narrow lookups, one user-supplied document, or a single low-risk edit whose target, change, and root cause are already clear.\n- Do **not** use the Direct Lane when the request includes document review\u002Fcritique, a failure\u002Ferror\u002Fstack trace, environment\u002Fsetup\u002Fruntime concerns, an explicit workflow name, handoff\u002Fcontext reset, knowledge promotion, or an unresolved build goal, target user, success\u002Facceptance criterion, or mutually exclusive implementation direction. If a Direct Lane task expands to multi-file behavior, architecture, governance, runtime, an unknown root cause, or a sensitive surface, stop and route again.\n\n## Route Selection\n\nFor every request outside the fast paths, and to validate an explicit public route or answer “what next?”, read [Public Route Map](references\u002Fpublic-route-map.md). Select exactly one entrypoint; do not automatically chain the flow. Prefer readiness, failure, or review routes when they match; otherwise use immediate intent and artifact type. **Checkpoint — ask:** at low confidence, ask at most one route-changing question, then stop and wait for the answer before routing further.\n\nFor active work, announce one localized line equivalent to `Entering \u003Centrypoint>: \u003Cone concrete reason>`, then follow the selected route. If a standalone skill is user-invoked only, recommend it and wait. For recommendation-only requests, return exactly one recommendation and wait:\n\n```text\nRecommended entrypoint: \u003Cspec-*, standalone skill, or terminal command>\nReason: \u003Cone concrete reason>\nNext action: \u003Cone action the user can take now>\n```\n\nUse the repository's configured user language. **Checkpoint — wait:** after any recommendation, stop and yield; enter the recommended entrypoint only after the user asks to continue.\n\n## Exit Boundaries\n\nHard exit gates cover mutation, verification claims, source\u002Fruntime, handoff\u002Fcontext reset, and knowledge promotion. A route match never authorizes an exit. Never claim verification or completion without traceable evidence, and never fabricate tests, refreshes, evals, or routing evidence. Modify source-of-truth surfaces, never generated host runtime; scripts\u002Ftools prepare deterministic facts while LLMs judge semantic adequacy.\n\nBefore runtime maintenance, scenario-fingerprint interpretation, worker dispatch, the Codex startup reminder, ordinary-context exclusions, handoff\u002Fcontext reset, knowledge promotion, or any parent multi-repo write, test, autofix, or commit, read [Conditional Routing Boundaries](references\u002Fconditional-routing-boundaries.md) and apply the matching section.\n","# Using Spec-First\n\n`using-spec-first` is a standalone entry governor, not a command-backed workflow. It selects one next entrypoint and yields control; it creates no workflow artifact. It is a semantic map, not a rigid state machine.\n\n## Workflow Contract Summary\n\n- **输入：** 当前用户意图、已有 workflow 状态、artifact 类型、失败\u002F环境信号与项目级路由规则。\n- **输出：** 恰好一个 public `spec-*` workflow、standalone skill、terminal command 或 Direct Lane 入口；进入后立即把控制权交给该 owner。\n- **硬出口：** 入口选择不授权 mutation、verification claim、runtime maintenance、handoff、knowledge promotion、commit 或 landing；低置信且会改变 route 时最多询问一个问题。\n- **权威：** 用户意图与项目 source rules 决定 route；本 skill 只做语义路由，不创建 workflow state 或执行下游工作。\n- **消费者：** 当前用户、所有 public workflow、standalone skill 与 host runtime entrypoint。\n\n## Fast Paths\n\n- Continue an active public workflow or bounded worker; do not restart routing.\n- Use the Direct Lane only for current-context explanations, lightweight facts, one-off how-to explanations, command-output explanations, narrow lookups, one user-supplied document, or a single low-risk edit whose target, change, and root cause are already clear.\n- Do **not** use the Direct Lane when the request includes document review\u002Fcritique, a failure\u002Ferror\u002Fstack trace, environment\u002Fsetup\u002Fruntime concerns, an explicit workflow name, handoff\u002Fcontext reset, knowledge promotion, or an unresolved build goal, target user, success\u002Facceptance criterion, or mutually exclusive implementation direction. If a Direct Lane task expands to multi-file behavior, architecture, governance, runtime, an unknown root cause, or a sensitive surface, stop and route again.\n\n## Route Selection\n\nFor every request outside the fast paths, and to validate an explicit public route or answer “what next?”, read [Public Route Map](references\u002Fpublic-route-map.md). Select exactly one entrypoint; do not automatically chain the flow. Prefer readiness, failure, or review routes when they match; otherwise use immediate intent and artifact type. **Checkpoint — ask:** at low confidence, ask at most one route-changing question, then stop and wait for the answer before routing further.\n\nFor active work, announce one localized line equivalent to `Entering \u003Centrypoint>: \u003Cone concrete reason>`, then follow the selected route. If a standalone skill is user-invoked only, recommend it and wait. For recommendation-only requests, return exactly one recommendation and wait:\n\n```text\nRecommended entrypoint: \u003Cspec-*, standalone skill, or terminal command>\nReason: \u003Cone concrete reason>\nNext action: \u003Cone action the user can take now>\n```\n\nUse the repository's configured user language. **Checkpoint — wait:** after any recommendation, stop and yield; enter the recommended entrypoint only after the user asks to continue.\n\n## Exit Boundaries\n\nHard exit gates cover mutation, verification claims, source\u002Fruntime, handoff\u002Fcontext reset, and knowledge promotion. A route match never authorizes an exit. Never claim verification or completion without traceable evidence, and never fabricate tests, refreshes, evals, or routing evidence. Modify source-of-truth surfaces, never generated host runtime; scripts\u002Ftools prepare deterministic facts while LLMs judge semantic adequacy.\n\nBefore runtime maintenance, scenario-fingerprint interpretation, worker dispatch, the Codex startup reminder, ordinary-context exclusions, handoff\u002Fcontext reset, knowledge promotion, or any parent multi-repo write, test, autofix, or commit, read [Conditional Routing Boundaries](references\u002Fconditional-routing-boundaries.md) and apply the matching section.\n",{"name":5,"description":7},"master","74655dc86b1270bb52239e0f8bc9517de7a7071c","skills\u002Fusing-spec-first",13,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first","http:\u002F\u002Fspec-first.cn\u002F","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai","作为一个初学者或者进阶者，这并没有什么错。当一个有能力的程序员而不是领导者，这也没有什么错。真正的错误是，当你知道应该如何去提高时仍然选择做一名初学者。","2026-11-05 13:30:55",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add leo-kuang-ai\u002Fspec-first --skill using-spec-first",{"tool":69,"command":70},"bunx","bunx skills add leo-kuang-ai\u002Fspec-first --skill using-spec-first",{"tool":72,"command":73},"pnpm","pnpm dlx skills add leo-kuang-ai\u002Fspec-first --skill using-spec-first","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002FSKILL.md",true,[77,83,87,91,95,99,103,107,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Fcases\u002Fdirect-lane-simple-howto.yaml","REFERENCE","参考文档",735,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Fcases\u002Fdirect-lane-simple-howto.yaml",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Fcases\u002Ffailure-priority-single-entry.yaml",1212,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Fcases\u002Ffailure-priority-single-entry.yaml",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"evals\u002Fcases\u002Fr2-low-confidence-one-question.yaml",700,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Fcases\u002Fr2-low-confidence-one-question.yaml",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"evals\u002Fcases\u002Frecommendation-only-format.yaml",1106,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Fcases\u002Frecommendation-only-format.yaml",{"path":96,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":97,"sourceHtmlUrl":98},"evals\u002Fcases\u002Froute-failure-to-spec-debug.yaml",1214,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Fcases\u002Froute-failure-to-spec-debug.yaml",{"path":100,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":101,"sourceHtmlUrl":102},"evals\u002Fcases\u002Froute-vague-idea-to-spec-brainstorm.yaml",1166,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Fcases\u002Froute-vague-idea-to-spec-brainstorm.yaml",{"path":104,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":105,"sourceHtmlUrl":106},"evals\u002Feval.yaml",587,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Feval.yaml",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"evals\u002Ffixtures\u002Fscripts\u002Fcheck-r2-asks.sh","SCRIPT","脚本",394,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Fevals\u002Ffixtures\u002Fscripts\u002Fcheck-r2-asks.sh",{"path":114,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":115,"sourceHtmlUrl":116},"payloads\u002FREADME.md",1088,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Fpayloads\u002FREADME.md",{"path":118,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Fai-pentest-agents.md",6171,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fai-pentest-agents.md",{"path":122,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Fai-pentesting-landscape-2026.md",3503,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fai-pentesting-landscape-2026.md",{"path":126,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Fautomation-loop-pattern.md",5346,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fautomation-loop-pattern.md",{"path":130,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Fawesome-pentest-digest.md",6090,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fawesome-pentest-digest.md",{"path":134,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":135,"sourceHtmlUrl":136},"references\u002Fburpsuite-mcp-guide.md",23673,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fburpsuite-mcp-guide.md",{"path":138,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":139,"sourceHtmlUrl":140},"references\u002Fclient-side-lab-playbook.md",4936,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fclient-side-lab-playbook.md",{"path":142,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Fconditional-routing-boundaries.md",4273,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Freferences\u002Fconditional-routing-boundaries.md",{"path":146,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":147,"sourceHtmlUrl":148},"references\u002Fkali-mcp-ecosystem.md",4527,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fkali-mcp-ecosystem.md",{"path":150,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002Fmsf-protocol.md",6042,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fmsf-protocol.md",{"path":154,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":155,"sourceHtmlUrl":156},"references\u002Fnetwork-attack-defense.md",10119,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fnetwork-attack-defense.md",{"path":158,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":159,"sourceHtmlUrl":160},"references\u002Fnuclei-guide-2026.md",4070,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fnuclei-guide-2026.md",{"path":162,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":163,"sourceHtmlUrl":164},"references\u002Fpentest-ai-agents-matrix.md",5074,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fpentest-ai-agents-matrix.md",{"path":166,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":167,"sourceHtmlUrl":168},"references\u002Fpentest-loop.md",6719,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fpentest-loop.md",{"path":170,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":171,"sourceHtmlUrl":172},"references\u002Fpublic-route-map.md",4896,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002Freferences\u002Fpublic-route-map.md",{"path":174,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":175,"sourceHtmlUrl":176},"references\u002Frecon-pipeline.md",5793,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Frecon-pipeline.md",{"path":178,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":179,"sourceHtmlUrl":180},"references\u002Fweb-attack-cheatsheet.md",7700,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Freferences\u002Fweb-attack-cheatsheet.md",{"path":182,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":183,"sourceHtmlUrl":184},"templates\u002Ffindings.md",328,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Ftemplates\u002Ffindings.md",{"path":186,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":187,"sourceHtmlUrl":188},"templates\u002Fprogress.md",242,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Ftemplates\u002Fprogress.md",{"path":190,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":191,"sourceHtmlUrl":192},"templates\u002Frules.md",722,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Ftemplates\u002Frules.md",{"path":194,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":195,"sourceHtmlUrl":196},"templates\u002Fscope.md",422,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Ftemplates\u002Fscope.md",{"path":198,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":199,"sourceHtmlUrl":200},"templates\u002Ftask_plan.md",543,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FSecurity-and-Compliance\u002Fpentest-tools\u002Ftemplates\u002Ftask_plan.md",[202,224,238,252,272,292],{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":209,"publishedAt":49},"01M6CWKK43ZJKQXKVJB3BWWPR1","spec-write-tasks","Public workflow entrypoint (spec-write-tasks): compile a settled local spec-plan into an optional derived task pack for spec-work, or validate an existing local task pack before execution. Use for explicit plan-splitting\u002Ftask-doc requests or high-complexity work suitability; do not use for plan authoring, implementation execution, unresolved scope, small low-risk plans, progress\u002Fapproval state, remote\u002Fgeneric task lists, or generated runtime mirror edits. Keep the plan as single source of truth; tasks are derived and optional.","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-tasks\u002FSKILL.md",[208],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[31,210,211,212,47,213,214,215,35,216,217,36,218,219,40,220,221,42,222,223],"tasks","write","spec write tasks","state","local","task","complexity","plan authoring","generated","validate","plan","doc","execution","compile",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":231,"publishedAt":49},"01M6CWKEK6CVPQW8EMCNSDPHBJ","spec-write-skill","公开 workflow：创建、修改或迁移项目拥有的 Agent Skill package，或对现有\u002F外部 package 做用户明确要求、零执行的只读验证与 readiness 报告时使用；也用于按已接受的 audit finding 修复 source skill。不要用于一次性回答、解释\u002F总结\u002F翻译、普通代码 review、第三方 Skill 纯安装或导入、跨仓批量修改，或直接修补 generated runtime mirrors。","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002FSKILL.md",[230],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[31,232,211,233,234,218,235,236,47,237],"write skill","spec write skill","audit","翻译","package","review",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":244,"publishedAt":49},"01M6CWKBDEZ7QFF1ZH3DP52SHA","spec-worktree","Internal helper for caller-owned git worktree isolation. Governed callers are spec-dogfood and spec-work; every caller must provide the forward invocation and intake contract.","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-worktree\u002FSKILL.md",[],[31,245,246,247,40,248,249,250,251],"worktree","spec worktree","dogfood","Bash","git worktree","git","intake",{"skillNo":253,"name":254,"nameZh":6,"description":255,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":256,"categories":257,"keywords":259,"publishedAt":49},"01M6CWK5W4VREMNXGQQKXXSQ3N","spec-work","Execute a settled plan, validated task pack, spec path, or concrete implementation request end-to-end. Use spec-debug for open-ended bugs; stop when target repo, scope, source ownership, or required authorization is unresolved. Not for explicitly requested GitHub PR-review-feedback handling — route those to spec-resolve-pr-feedback.","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-work\u002FSKILL.md",[258],{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[31,40,260,261,221,262,263,264,265,237,220,266,39,36,267,268,269,270,215,271],"spec work","open","pr","debug","to spec","github","feedback","auto","implementation","stop","github pr","route",{"skillNo":273,"name":274,"nameZh":6,"description":275,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":276,"categories":277,"keywords":283,"publishedAt":49},"01M6CWK1MFTSNV9MYD4C8WGB8B","spec-test-xcode","Build and test iOS apps on simulator using XcodeBuildMCP. Use after making iOS code changes, before creating a PR, or when verifying app behavior and checking for crashes on simulator.","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-test-xcode\u002FSKILL.md",[278,281,282],{"categoryNo":279,"categoryName":280,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[284,285,31,286,287,36,288,289,290,262,291],"test","spec test xcode","build","default","behavior","ios","code","build and test",{"skillNo":293,"name":294,"nameZh":6,"description":295,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":296,"categories":297,"keywords":300,"publishedAt":49},"01M6CWJXMAXKVRW5MA4E9EJJQW","spec-test-browser","Run browser tests on pages affected by current PR or branch. Use after code changes when browser verification is requested before review or merge. Not for diagnosing failures those runs uncover — route defects to spec-debug.","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-test-browser\u002FSKILL.md",[298,299],{"categoryNo":279,"categoryName":280,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[31,284,301,302,303,304,263,262,44,290,264,237,271,36,305,306,307],"spec test browser","browser","test browser","merge","branch","pipeline","verification"]