[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CWKEK6CVPQW8EMCNSDPHBJ":3,"skill-same:01M6CWKEK6CVPQW8EMCNSDPHBJ":182},{"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":23,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6CWKEK6CVPQW8EMCNSDPHBJ","spec-write-skill",null,"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。","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\u002Fspec-write-skill\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33],"spec","write skill","write","spec write skill","review","workflow","package","audit","翻译","generated","2026-11-10 10:12:30",false,"---\nname: spec-write-skill\ndescription: 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。\n---\n\n# Spec Write Skill\n\n把可复用目标转成 portable、source-first 的 Skill patch，或在零写入模式下报告 package readiness；交付正确分支的结果、匹配证据与 residual risks，不把 source bytes、fixture pass 或模型自述当成语义改善。\n\n## Scenario Capability\n\nFollows `docs\u002Fcontracts\u002Fworkflows\u002Fscenario-capability-matrix.md` (default).\nOverrides: none\n\n## Workflow Contract Summary\n\n- **Input \u002F output:** 用户目标、一个 target repo\u002FSkill root、现有 package、项目规则、相邻 Skill、已接受 findings 和必要只读参考，产生 near-neighbor route、`validate-only` report、preview 后的单 repo source patch 或 source-resolution blocker；每个结果带验证状态与 residual risks。\n- `base_operation=create|revise` 只区分新建 package 与处理现有 package；`effect=apply|validate-only` 决定副作用，只有 `effect=apply` 才允许修改已确认的 canonical source，`effect=validate-only` 即使面对现有或外部 package 也保持零写入。`modifier=migrate|audit-remediation|none` 只补充输入分析，不形成新 workflow\u002Feffect。\n- `layer_result` 是 runtime 输出合同：`near-neighbor-route|refuse-generated-runtime-patch|portable-core-only|portable-core-with-behavior-contract|portable-readiness-report|trust-preflight-blocked|blocked-source-owner|spec-first-project-profile`。新增值必须同步更新 source、consumer 和 tests，不能只写入 maintainer fixture。\n\n## Branch Contract\n\n先根据用户请求和已确认事实选择一个 disposition；只读取会改变该 disposition 判断的 reference，并在下列 done signal 达成后停止。\n\n| Disposition | Entry signal and result | Required action \u002F evidence | Done signal and failure behavior |\n| --- | --- | --- | --- |\n| Near-neighbor | 非 authoring\u002Freadiness，或只请求 audit-only quality review、纯安装、runtime mirror。已接受 finding 的 remediation 不属于本分支。输出 `base_operation=null`、`effect=not-entered`、`modifier=none`；结果为 `near-neighbor-route` 或 `refuse-generated-runtime-patch`。 | 只给 owning route \u002F next action；安装交给 `skill-installer`，mirror 交给 `runtime-maintenance`。 | 路由后停止；不得 inventory、validator、preview 或 mutation。 |\n| Owner blocked | create\u002Frevise 的 owner 不唯一、跨 repo、repo-external、generated-only 或 containment 未确认。保留 `base_operation=create|revise` 与 `effect=apply`，结果为 `blocked-source-owner`。 | 读 [Authoring Method](references\u002Fauthoring-method.md)，给 candidate-only preview、空 would-change\u002Fcommand list 和唯一下一步。 | 未绑定单一 canonical source 时零 mutation；不得降格为 `not-entered` 或猜测 owner。 |\n| Validate-only | 用户明确检查现有\u002F外部 package；现有 package 使用 `base_operation=revise` + `effect=validate-only`，结果为 `portable-readiness-report` 或 `trust-preflight-blocked`。 | no-follow inventory、bundled validator 与 [Delivery Gates](references\u002Fdelivery-gates.md)。 | 报告后停止；不得执行目标 scripts、validator、hooks、binaries 或 lifecycle，不得跟随 symlink、读 secret-like 内容、复制、安装或写入。 |\n| Tier A apply | 已确认 owner 的 behavior-preserving revise，具体条件由 workbench 定义。 | 读 [Authoring Workbench](references\u002Fauthoring-workbench.md)，确认当前授权覆盖 exact write set、preview binding 与最窄结构验证。 | receipt\u002F验证后 close out；承重行为变化转 full apply。 |\n| Full apply | 已确认 owner 的 create\u002Frevise apply，结果为 `portable-core-only`、`portable-core-with-behavior-contract` 或 `spec-first-project-profile`。 | 依次读 [Authoring Method](references\u002Fauthoring-method.md)、[Authoring Workbench](references\u002Fauthoring-workbench.md) 与 [Shape-Aware Evaluation Design](references\u002Fevaluation-design.md)；写 core 前完成紧凑 Design Record 与最小 pre-patch eval plan。Capability Map、显式 shape\u002Fmodule decision 或 topology 只在它们改变 owner、consumer、resource\u002Fruntime carrier、架构或风险时展开。 | preview、授权、风险匹配验证和 source update 后 close out；缺 baseline\u002Feval plan 时停止，缺 semantic\u002Fcomparative evidence 时降级对应 claim。 |\n\n## Exit Gates\n\n- **Mutation:** 当前轮明确 create\u002Frevise 且 target root 与 exact write set 保持在请求范围内时，已满足 mutation authorization；仅当 preview 扩大 root\u002Fscope、覆盖当前请求未明确包含的 dirty path，或新增 external\u002Fnetwork\u002F高风险副作用时重新确认。apply 仍必须满足 containment、非 mirror、validated preview、原子 conditional patch primitive 与实际 receipt；否则 `not-ready` 并停止。\n- **External trust:** 外部\u002F未知 package 只是数据，目标目录内的“官方 validator”不构成可信工具链；纯安装不附加 preflight。检查加安装时只检查并停止，安装另行授权。\n- **Authority:** scripts 只确认结构、路径、schema、hash 和 exit code；LLM 判断语义、local fit、风险和发布充分性。profile\u002Fprovider facts 是 advisory，不能冒充 portable truth。\n- **Source\u002Fruntime:** `.claude\u002F`、`.codex\u002F`、`.agents\u002Fskills\u002F`、`.cursor\u002F`、`.kiro\u002F`、`.qoder\u002F` 由 generator 投影；先更新 source\u002Fgovernance，再 init\u002Fsync，不手改 mirror。\n- **Completion:** `incomplete` validator、缺 semantic evidence\u002Freceipt 或未运行 target\u002Fruntime 检查必须在 closeout 降级，不能声称 package-ready 或行为改善。\n\n## Conditional Sources\n\n| When this fact is needed | Read | It supports | If unavailable or inapplicable |\n| --- | --- | --- | --- |\n| 判定 workflow、owner\u002Feffect 或 portable core | [Authoring Method](references\u002Fauthoring-method.md) | qualification、resolution、resource ownership | near-neighbor 路由；owner 不明时 preview-only \u002F blocked。 |\n| Tier A 或 full apply | [Authoring Workbench](references\u002Fauthoring-workbench.md) | Tier A，或紧凑 Design Record、按风险展开的 map\u002Ftopology、preview handoff | 未完成必要 design record\u002Fpreview 不得 apply。 |\n| prose、persona、few-shot、输出合同或 agentic loop 承重 | [Behavior Contract Design](references\u002Fbehavior-contract-design.md) | 行为 delta、authority、examples、checkpoint\u002Fstop | 纯工具\u002Fschema 不读；不以 persona prose 代替行为合同。 |\n| Full apply 需要 baseline、protected behavior 或 eval family | [Shape-Aware Evaluation Design](references\u002Fevaluation-design.md) | 最小 pre-patch eval plan 与风险匹配的 evidence family | 未读不得开始 full apply source patch；Tier A 不触发。 |\n| measurable optimization 或 field feedback 改变 disposition | [Optimization And Feedback Handoff](references\u002Foptimization-and-lifecycle.md) | optimization handoff、feedback-to-regression | optimization 主意图路由 `spec-optimize`；未复现 feedback 保持 observation。 |\n| package\u002F写前\u002Fcloseout 验证或风险信号 | [Delivery Gates](references\u002Fdelivery-gates.md) | validator、preview、risk checks、五轴 readiness | 记录 `not-run` \u002F degraded，不伪造 gate。 |\n| target metadata\u002Finvocation 或本地治理\u002Fcatalog\u002Fgenerator 改变 patch | [Target Profiles](references\u002Ftarget-profiles.md) 或 [Project Profiles](references\u002Fproject-profiles.md) | target\u002Fproject facts 和 projection | portable-only 不读 profile；owner 不明不 apply。 |\n\n## Source Update and Closeout\n\napply 先更新 canonical source、必要 tests\u002Fdocs\u002FChangelog；catalog 由 generator 重建，runtime 由项目 init\u002Fsync 重建。\ncloseout 固定报告 `base_operation`、`effect`、`modifier`、`layer_result`、target\u002Fsource owner、changed surfaces、deterministic\u002Fsemantic evidence、portable\u002Ftarget\u002Fproject\u002Fsemantic\u002Fmutation 五轴 readiness、runtime 状态、not-run reason 和 residual risks。\n\n`agents\u002Fopenai.yaml` 仅是 Codex target metadata；`evals\u002F` 仅是维护者证据，二者都不是 portable 行为真相源。\n","# Spec Write Skill\n\n把可复用目标转成 portable、source-first 的 Skill patch，或在零写入模式下报告 package readiness；交付正确分支的结果、匹配证据与 residual risks，不把 source bytes、fixture pass 或模型自述当成语义改善。\n\n## Scenario Capability\n\nFollows `docs\u002Fcontracts\u002Fworkflows\u002Fscenario-capability-matrix.md` (default).\nOverrides: none\n\n## Workflow Contract Summary\n\n- **Input \u002F output:** 用户目标、一个 target repo\u002FSkill root、现有 package、项目规则、相邻 Skill、已接受 findings 和必要只读参考，产生 near-neighbor route、`validate-only` report、preview 后的单 repo source patch 或 source-resolution blocker；每个结果带验证状态与 residual risks。\n- `base_operation=create|revise` 只区分新建 package 与处理现有 package；`effect=apply|validate-only` 决定副作用，只有 `effect=apply` 才允许修改已确认的 canonical source，`effect=validate-only` 即使面对现有或外部 package 也保持零写入。`modifier=migrate|audit-remediation|none` 只补充输入分析，不形成新 workflow\u002Feffect。\n- `layer_result` 是 runtime 输出合同：`near-neighbor-route|refuse-generated-runtime-patch|portable-core-only|portable-core-with-behavior-contract|portable-readiness-report|trust-preflight-blocked|blocked-source-owner|spec-first-project-profile`。新增值必须同步更新 source、consumer 和 tests，不能只写入 maintainer fixture。\n\n## Branch Contract\n\n先根据用户请求和已确认事实选择一个 disposition；只读取会改变该 disposition 判断的 reference，并在下列 done signal 达成后停止。\n\n| Disposition | Entry signal and result | Required action \u002F evidence | Done signal and failure behavior |\n| --- | --- | --- | --- |\n| Near-neighbor | 非 authoring\u002Freadiness，或只请求 audit-only quality review、纯安装、runtime mirror。已接受 finding 的 remediation 不属于本分支。输出 `base_operation=null`、`effect=not-entered`、`modifier=none`；结果为 `near-neighbor-route` 或 `refuse-generated-runtime-patch`。 | 只给 owning route \u002F next action；安装交给 `skill-installer`，mirror 交给 `runtime-maintenance`。 | 路由后停止；不得 inventory、validator、preview 或 mutation。 |\n| Owner blocked | create\u002Frevise 的 owner 不唯一、跨 repo、repo-external、generated-only 或 containment 未确认。保留 `base_operation=create|revise` 与 `effect=apply`，结果为 `blocked-source-owner`。 | 读 [Authoring Method](references\u002Fauthoring-method.md)，给 candidate-only preview、空 would-change\u002Fcommand list 和唯一下一步。 | 未绑定单一 canonical source 时零 mutation；不得降格为 `not-entered` 或猜测 owner。 |\n| Validate-only | 用户明确检查现有\u002F外部 package；现有 package 使用 `base_operation=revise` + `effect=validate-only`，结果为 `portable-readiness-report` 或 `trust-preflight-blocked`。 | no-follow inventory、bundled validator 与 [Delivery Gates](references\u002Fdelivery-gates.md)。 | 报告后停止；不得执行目标 scripts、validator、hooks、binaries 或 lifecycle，不得跟随 symlink、读 secret-like 内容、复制、安装或写入。 |\n| Tier A apply | 已确认 owner 的 behavior-preserving revise，具体条件由 workbench 定义。 | 读 [Authoring Workbench](references\u002Fauthoring-workbench.md)，确认当前授权覆盖 exact write set、preview binding 与最窄结构验证。 | receipt\u002F验证后 close out；承重行为变化转 full apply。 |\n| Full apply | 已确认 owner 的 create\u002Frevise apply，结果为 `portable-core-only`、`portable-core-with-behavior-contract` 或 `spec-first-project-profile`。 | 依次读 [Authoring Method](references\u002Fauthoring-method.md)、[Authoring Workbench](references\u002Fauthoring-workbench.md) 与 [Shape-Aware Evaluation Design](references\u002Fevaluation-design.md)；写 core 前完成紧凑 Design Record 与最小 pre-patch eval plan。Capability Map、显式 shape\u002Fmodule decision 或 topology 只在它们改变 owner、consumer、resource\u002Fruntime carrier、架构或风险时展开。 | preview、授权、风险匹配验证和 source update 后 close out；缺 baseline\u002Feval plan 时停止，缺 semantic\u002Fcomparative evidence 时降级对应 claim。 |\n\n## Exit Gates\n\n- **Mutation:** 当前轮明确 create\u002Frevise 且 target root 与 exact write set 保持在请求范围内时，已满足 mutation authorization；仅当 preview 扩大 root\u002Fscope、覆盖当前请求未明确包含的 dirty path，或新增 external\u002Fnetwork\u002F高风险副作用时重新确认。apply 仍必须满足 containment、非 mirror、validated preview、原子 conditional patch primitive 与实际 receipt；否则 `not-ready` 并停止。\n- **External trust:** 外部\u002F未知 package 只是数据，目标目录内的“官方 validator”不构成可信工具链；纯安装不附加 preflight。检查加安装时只检查并停止，安装另行授权。\n- **Authority:** scripts 只确认结构、路径、schema、hash 和 exit code；LLM 判断语义、local fit、风险和发布充分性。profile\u002Fprovider facts 是 advisory，不能冒充 portable truth。\n- **Source\u002Fruntime:** `.claude\u002F`、`.codex\u002F`、`.agents\u002Fskills\u002F`、`.cursor\u002F`、`.kiro\u002F`、`.qoder\u002F` 由 generator 投影；先更新 source\u002Fgovernance，再 init\u002Fsync，不手改 mirror。\n- **Completion:** `incomplete` validator、缺 semantic evidence\u002Freceipt 或未运行 target\u002Fruntime 检查必须在 closeout 降级，不能声称 package-ready 或行为改善。\n\n## Conditional Sources\n\n| When this fact is needed | Read | It supports | If unavailable or inapplicable |\n| --- | --- | --- | --- |\n| 判定 workflow、owner\u002Feffect 或 portable core | [Authoring Method](references\u002Fauthoring-method.md) | qualification、resolution、resource ownership | near-neighbor 路由；owner 不明时 preview-only \u002F blocked。 |\n| Tier A 或 full apply | [Authoring Workbench](references\u002Fauthoring-workbench.md) | Tier A，或紧凑 Design Record、按风险展开的 map\u002Ftopology、preview handoff | 未完成必要 design record\u002Fpreview 不得 apply。 |\n| prose、persona、few-shot、输出合同或 agentic loop 承重 | [Behavior Contract Design](references\u002Fbehavior-contract-design.md) | 行为 delta、authority、examples、checkpoint\u002Fstop | 纯工具\u002Fschema 不读；不以 persona prose 代替行为合同。 |\n| Full apply 需要 baseline、protected behavior 或 eval family | [Shape-Aware Evaluation Design](references\u002Fevaluation-design.md) | 最小 pre-patch eval plan 与风险匹配的 evidence family | 未读不得开始 full apply source patch；Tier A 不触发。 |\n| measurable optimization 或 field feedback 改变 disposition | [Optimization And Feedback Handoff](references\u002Foptimization-and-lifecycle.md) | optimization handoff、feedback-to-regression | optimization 主意图路由 `spec-optimize`；未复现 feedback 保持 observation。 |\n| package\u002F写前\u002Fcloseout 验证或风险信号 | [Delivery Gates](references\u002Fdelivery-gates.md) | validator、preview、risk checks、五轴 readiness | 记录 `not-run` \u002F degraded，不伪造 gate。 |\n| target metadata\u002Finvocation 或本地治理\u002Fcatalog\u002Fgenerator 改变 patch | [Target Profiles](references\u002Ftarget-profiles.md) 或 [Project Profiles](references\u002Fproject-profiles.md) | target\u002Fproject facts 和 projection | portable-only 不读 profile；owner 不明不 apply。 |\n\n## Source Update and Closeout\n\napply 先更新 canonical source、必要 tests\u002Fdocs\u002FChangelog；catalog 由 generator 重建，runtime 由项目 init\u002Fsync 重建。\ncloseout 固定报告 `base_operation`、`effect`、`modifier`、`layer_result`、target\u002Fsource owner、changed surfaces、deterministic\u002Fsemantic evidence、portable\u002Ftarget\u002Fproject\u002Fsemantic\u002Fmutation 五轴 readiness、runtime 状态、not-run reason 和 residual risks。\n\n`agents\u002Fopenai.yaml` 仅是 Codex target metadata；`evals\u002F` 仅是维护者证据，二者都不是 portable 行为真相源。\n",{"name":5,"description":7},"master","74655dc86b1270bb52239e0f8bc9517de7a7071c","skills\u002Fspec-write-skill",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。","2026-11-12 18:28:30",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add leo-kuang-ai\u002Fspec-first --skill spec-write-skill",{"tool":54,"command":55},"bunx","bunx skills add leo-kuang-ai\u002Fspec-first --skill spec-write-skill",{"tool":57,"command":58},"pnpm","pnpm dlx skills add leo-kuang-ai\u002Fspec-first --skill spec-write-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002FSKILL.md",true,[62,68,72,76,80,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158,162,166,170,174,178],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"agents\u002Fopenai.yaml","REFERENCE","参考文档",991,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fagents\u002Fopenai.yaml",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"CouncilMembers.md",3531,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv5.0.0\u002F.claude\u002Fskills\u002FCouncil\u002FCouncilMembers.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"evals\u002Fcases\u002Fmirror-patch-refused.yaml",749,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Fcases\u002Fmirror-patch-refused.yaml",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"evals\u002Feval.yaml",306,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Feval.yaml",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"evals\u002Fexport-trigger-evals.cjs","SCRIPT","脚本",2268,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Fexport-trigger-evals.cjs",{"path":87,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":88,"sourceHtmlUrl":89},"evals\u002Ffixtures\u002Frepos\u002Fmini-ledger\u002Fpackage.json",96,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Ffixtures\u002Frepos\u002Fmini-ledger\u002Fpackage.json",{"path":91,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":92,"sourceHtmlUrl":93},"evals\u002Ffixtures\u002Frepos\u002Fmini-ledger\u002FREADME.md",365,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Ffixtures\u002Frepos\u002Fmini-ledger\u002FREADME.md",{"path":95,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":96,"sourceHtmlUrl":97},"evals\u002Ffixtures\u002Frepos\u002Fmini-ledger\u002Fsrc\u002Fserver.js",665,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Ffixtures\u002Frepos\u002Fmini-ledger\u002Fsrc\u002Fserver.js",{"path":99,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":100,"sourceHtmlUrl":101},"evals\u002Ffixtures\u002Fscripts\u002Fasks-a-question.sh",1232,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Ffixtures\u002Fscripts\u002Fasks-a-question.sh",{"path":103,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":104,"sourceHtmlUrl":105},"evals\u002Ffixtures\u002Fscripts\u002Fcheck-mirror-refused.sh",604,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Ffixtures\u002Fscripts\u002Fcheck-mirror-refused.sh",{"path":107,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":108,"sourceHtmlUrl":109},"evals\u002FREADME.md",4988,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002FREADME.md",{"path":111,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":112,"sourceHtmlUrl":113},"evals\u002Ftrigger-cases.json",16431,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Ftrigger-cases.json",{"path":115,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":116,"sourceHtmlUrl":117},"evals\u002Fvalidate-promotion-evidence.cjs",31920,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fevals\u002Fvalidate-promotion-evidence.cjs",{"path":119,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":120,"sourceHtmlUrl":121},"OutputFormat.md",2062,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv5.0.0\u002F.claude\u002Fskills\u002FCouncil\u002FOutputFormat.md",{"path":123,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fauthoring-method.md",10331,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Fauthoring-method.md",{"path":127,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fauthoring-workbench.md",5830,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Fauthoring-workbench.md",{"path":131,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Fbehavior-contract-design.md",6002,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Fbehavior-contract-design.md",{"path":135,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fdelivery-gates.md",6344,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Fdelivery-gates.md",{"path":139,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Fevaluation-design.md",3268,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Fevaluation-design.md",{"path":143,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Foptimization-and-lifecycle.md",1763,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Foptimization-and-lifecycle.md",{"path":147,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":148,"sourceHtmlUrl":149},"references\u002Fproject-profiles.md",1877,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Fproject-profiles.md",{"path":151,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":152,"sourceHtmlUrl":153},"references\u002Ftarget-profiles.md",3500,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Freferences\u002Ftarget-profiles.md",{"path":155,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":156,"sourceHtmlUrl":157},"RoundStructure.md",1557,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv5.0.0\u002F.claude\u002Fskills\u002FCouncil\u002FRoundStructure.md",{"path":159,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":160,"sourceHtmlUrl":161},"scripts\u002Finspect-context.cjs",7354,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fscripts\u002Finspect-context.cjs",{"path":163,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":164,"sourceHtmlUrl":165},"scripts\u002Flib\u002Fpackage-inspection.cjs",13757,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fscripts\u002Flib\u002Fpackage-inspection.cjs",{"path":167,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":168,"sourceHtmlUrl":169},"scripts\u002Fvalidate-authoring-preview.cjs",21442,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fscripts\u002Fvalidate-authoring-preview.cjs",{"path":171,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":172,"sourceHtmlUrl":173},"scripts\u002Fvalidate-skill.cjs",18863,"https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fspec-write-skill\u002Fscripts\u002Fvalidate-skill.cjs",{"path":175,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":176,"sourceHtmlUrl":177},"Workflows\u002FDebate.md",5420,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv5.0.0\u002F.claude\u002Fskills\u002FCouncil\u002FWorkflows\u002FDebate.md",{"path":179,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":180,"sourceHtmlUrl":181},"Workflows\u002FQuick.md",2369,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv5.0.0\u002F.claude\u002Fskills\u002FCouncil\u002FWorkflows\u002FQuick.md",[183,214,234,248,268,288],{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":195,"publishedAt":34},"01M6CWKQCYJXDCW4MEF3FSJE26","using-spec-first","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.","https:\u002F\u002Fgithub.com\u002Fleo-kuang-ai\u002Fspec-first\u002Fblob\u002Fmaster\u002Fskills\u002Fusing-spec-first\u002FSKILL.md",[189,190],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[196,197,24,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,29,213],"using spec first","first","active","do","use","context","command","repo","work","choose","direct","next","risk","lane","run","cleanup","workflows","terminal",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":34},"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",[220],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[222,26,223,24,224,225,199,226,227,200,33,204,228,229,208,230,231,232,233,29],"spec write tasks","tasks","plan","task","complexity","plan authoring","local","doc","execution","compile","state","validate",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":240,"publishedAt":34},"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",[],[24,241,242,243,204,244,245,246,247],"spec worktree","worktree","dogfood","git worktree","Bash","intake","git",{"skillNo":249,"name":250,"nameZh":6,"description":251,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":252,"categories":253,"keywords":255,"publishedAt":34},"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",[254],{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},[256,204,24,224,257,229,258,259,260,261,28,262,263,225,264,265,266,267,200,203],"spec work","open","pr","debug","to spec","github","feedback","route","github pr","stop","implementation","auto",{"skillNo":269,"name":270,"nameZh":6,"description":271,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":272,"categories":273,"keywords":279,"publishedAt":34},"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",[274,277,278],{"categoryNo":275,"categoryName":276,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},[280,281,24,282,283,200,284,285,286,258,287],"spec test xcode","test","build","default","behavior","ios","code","build and test",{"skillNo":289,"name":290,"nameZh":6,"description":291,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":292,"categories":293,"keywords":296,"publishedAt":34},"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",[294,295],{"categoryNo":275,"categoryName":276,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},[24,297,298,281,299,259,258,286,260,300,200,301,263,210,28,302,303],"spec test browser","browser","test browser","merge","branch","verification","pipeline"]