[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D3Q08YAX7RK7DW3Z702TX3":3,"skill-same:01M6D3Q08YAX7RK7DW3Z702TX3":72},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6D3Q08YAX7RK7DW3Z702TX3","codebase-status",null,"Report what a repository is, what recent conversation history says about it, current application status, and outstanding work","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbase\u002Fcodex\u002Fcodebase-status\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"status","codebase status","report","repository","analysis","history","work","repo","v0","conversation","application","focus","2026-11-10 10:12:30",false,"---\nname: codebase-status\ndescription: Report what a repository is, what recent conversation history says about it, current application status, and outstanding work\ntype: analysis\nversion: v0.12\nargument-hint: \"[optional repo path, focus, or --no-history]\"\n---\n\n# Codebase Status\n\nInvoke as `$codebase-status`.\n\nUse this skill when the user asks what a repo or application is, where work was left, what is outstanding, whether it is ready\u002Fstable, or wants a detailed status report that combines codebase evidence with local Claude\u002FCodex conversation history.\n\nThis is read-only status synthesis. It does not replace `$roadmap`: `roadmap` maintains the task pipeline and priority queue; `codebase-status` explains the actual current state of the repo and relevant prior conversations.\n\n## Process\n\n1. Resolve target repo:\n   - Default to the current working directory.\n   - If the user provides a path, use that repo.\n   - Confirm it is a git worktree when possible; if not, continue with filesystem evidence and report that git evidence is unavailable.\n2. Read project orientation:\n   - `README.md`, `AGENTS.md`, `CLAUDE.md`, `.agents\u002Fproject.json`, package\u002Fworkspace files, app entrypoints, and high-signal docs.\n   - Identify project type, main apps\u002Fpackages, runtime, tests, and likely user-facing or developer-facing purpose.\n3. Read planning and status docs when present:\n   - `tasks\u002Froadmap.md`, `tasks\u002Ftodo.md`, `tasks\u002Fmanual-todo.md`, `tasks\u002Frecord-todo.md`, `tasks\u002Frecurring-todo.md`, `tasks\u002Fhistory.md`, `tasks\u002Flessons.md`, `tasks\u002Fphases\u002F`, `specs\u002F`, `spec.md`, and `research\u002F`.\n   - Distinguish checked-off work, active work, manual blockers, advisory work, stale docs, and missing docs.\n4. Read routing evidence for product, research, or spec repos:\n   - When `research\u002F`, `specs\u002F`, `spec.md`, product docs, or prototype artifacts exist, read `docs\u002Fpack-workflow-matrix.md` and `docs\u002Fskill-next-step-contracts.md` if present.\n   - Identify the last completed relevant research\u002Fproduct skill from artifacts, task history, or conversation history. Before recommending another research\u002Fproduct skill, consult that skill's active `SKILL.md` `## Next Steps` contract and any `## Next Steps` section in its output artifact.\n   - Treat those route contracts as stronger evidence than a generic status impression. If docs disagree, report the contradiction and prefer the newest active skill contract or route matrix with file evidence.\n   - For pack-local recommendations, check `.agents\u002Fproject.json` `enabled_packs` first. If the target skill's pack is not enabled, recommend `npx skillpacks install \u003Cpack-name>` from the project shell, before the skill.\n5. Inspect git evidence:\n   - `git status --short`\n   - current branch and upstream status\n   - last 20 commits\n   - unpushed commits when an upstream exists\n   - changed files in the working tree\n6. Inspect codebase health signals:\n   - Project structure and primary modules.\n   - Test\u002Fbuild\u002Flint scripts from package manifests or equivalent tool files.\n   - Obvious TODO\u002FFIXME markers, failing-test notes, disabled tests, and local quality scripts.\n   - Do not run expensive commands by default. Run cheap read-only inspections freely; ask or state assumptions before long builds, network installs, destructive commands, or mutation.\n7. Find related conversation history unless `--no-history` is passed:\n   - Read full available local prompt history, not a sample:\n     - `~\u002F.claude\u002Fhistory.jsonl`\n     - `~\u002F.codex\u002Fhistory.jsonl`\n     - `~\u002F.codex\u002Fsessions\u002F**\u002F*.jsonl` for Codex session metadata only when needed to map session IDs to cwd.\n   - Filter to records whose project\u002Fcwd matches the target repo or whose text mentions the absolute path, repo directory name, package\u002Fapp name, or repository URL.\n   - Exclude system, developer, tool output, injected skill payloads, and base instruction text from examples.\n   - Use line-by-line parsing for scale and deduplicate Codex prompt records when compact and rich histories overlap.\n   - Extract recent user goals, repeated requests, unresolved questions, blockers, and prior recommendations.\n8. Synthesize status:\n   - What this repo\u002Fapp is.\n   - What has happened recently.\n   - Current implementation status by major area.\n   - Outstanding work, grouped as blocking, next execution, advisory, manual\u002Fhuman-only, and uncertain.\n   - Mismatches between conversation history, task docs, git history, and code reality.\n   - Confidence level for each major conclusion: high, medium, or low, with evidence.\n9. Recommend next route:\n   - Use phase-aware routing before naming a command:\n     - If `tasks\u002Ftodo.md` or active phase docs contain actionable implementation work, recommend the approved task artifact route. Do not route back to research merely because advisory gaps exist.\n     - If finished work is dirty, unpushed, unvalidated, or needs packaging\u002Freview before handoff, recommend `$ship`.\n     - If user-facing product research\u002Fprototype artifacts are missing and no implementation\u002Fshipping queue is active, follow the canonical AFPS route from the routing evidence: `customer-discovery -> competitive-analysis -> journey-map -> positioning -> user-flow-map -> ux-variations [specific-user-flow] -> ui-interview [specific-ux-variation] -> prototype -> uat --variant-evaluation -> consolidate-prototypes -> research-roadmap --post-prototype -> spec-interview -> research-roadmap --post-spec -> roadmap`. Use `$ui-interview --requirements-only` and `$ux-variations --layout-mode` only when the user explicitly needs a fixed content\u002Fdata\u002Faction contract and layout-only alternatives.\n     - If `research\u002Ficp.md` and `research\u002Fcompetitive-analysis.md` exist but `research\u002Fjourney-map.md` is missing, check `customer-lifecycle` availability. If it is not enabled, recommend `npx skillpacks install customer-lifecycle` from the project shell, before `$journey-map`; if enabled, recommend `$journey-map`.\n     - Treat `value-prop-canvas` and `lean-canvas` as optional risk-driven detours only. Before recommending either, check `business-research` availability; if it is not enabled, recommend `npx skillpacks install business-research` from the project shell, before `$value-prop-canvas` or `$lean-canvas`. Recommend `$value-prop-canvas` only for contested solution-fit evidence, and `$lean-canvas` only for material business-model risk; do not make either a default blocker before `journey-map`, `positioning`, `user-flow-map`, or layout-mode UX variations.\n     - If no research, spec, task, implementation, validation, dirty, or unpushed work remains, recommend `$brainstorm` to discover new AFPS work.\n   - Approved task artifact route when the next task is already clear and executable.\n   - `$roadmap` when specs exist but sequencing or task queue health needs updating.\n   - `$feature-interview` when the next idea\u002Fdirection is not yet represented in specs or tasks.\n   - `$reconcile-dev-docs audit` or `$reconcile-dev-docs fix tasks` when task docs contradict git\u002Fcode reality.\n   - `$spec-drift` when specs and code appear out of sync.\n   - `$guide` only for human-only external blockers.\n   - `$brainstorm` when the repo is complete\u002Fcurrent and the next step is discovering a new phase.\n\n## Output\n\nProduce a structured report with:\n\n- **Overview:** repo path, project purpose, project type, primary apps\u002Fpackages, branch, dirty\u002Funpushed status.\n- **History Signal:** number of Claude\u002FCodex prompt records scanned, number matched to this repo, date range, and 3-8 concise real examples.\n- **Recent Work:** last commits and task\u002Fhistory evidence.\n- **Current Status:** major areas and whether each appears complete, in progress, blocked, stale, or unknown.\n- **Outstanding Work:** prioritized list with evidence and recommended owner\u002Fskill.\n- **Risks And Drift:** contradictions, stale docs, missing tests, manual blockers, or uncertain claims.\n- **Recommended Next Step:** one concrete next work item and one command.\n\nEnd with exactly:\n\n```md\n**Next work:** \u003Cspecific task, blocker, discovery task, or \"none\">\n**Recommended next command:** \u003Cone command or route>\n```\n\n## Constraints\n\n- Read-only by default. Do not modify files, create commits, run installs, or execute long test suites unless the user explicitly asks.\n- Do not include private conversation history unrelated to the target repo.\n- Quote only short prompt excerpts. Prefer paraphrase plus timestamp\u002Fsource\u002Fproject.\n- Do not treat `tasks\u002Frecord-todo.md` or `tasks\u002Frecurring-todo.md` as execution queues unless an item has clearly become concrete work.\n- Do not put agent-executable work in `tasks\u002Fmanual-todo.md` or route it to `$guide`.\n- Do not recommend `$roadmap` if the finding is only \"tell me the status\"; use `$roadmap` only when the task pipeline itself needs queue maintenance or roadmap extension.\n- When recommending a pack skill, first check `.agents\u002Fproject.json` for `enabled_packs`. If the target skill's pack is not enabled, include `npx skillpacks install \u003Cpack-name>` from the project shell, as a prerequisite in the recommendation.\n- Do not create or modify GitHub Actions workflows.\n\n## Default Shipping Contract\n\n- **Default next-step routing:** when reporting completion, include either `Recommended next skill: \u003Ccommand>` or the two-line pair `**Next work:** \u003Cspecific task or \"none\">` and `**Recommended next command:** \u003Cone command or route>` so the next caller has a concrete handoff.\n- Normally read-only and should not create or modify tracked repository files.\n- If the user explicitly asks this skill to create or modify tracked files, follow `docs\u002Fgithub-delivery-contract.md` and finish with an issue-backed non-primary branch plus ready pull request; do not merge it.\n- This contract does not override stricter safety rules about secrets, destructive history changes, release publication\u002Ftag confirmation, production deploy confirmation, paid actions, or public visibility changes.\n","# Codebase Status\n\nInvoke as `$codebase-status`.\n\nUse this skill when the user asks what a repo or application is, where work was left, what is outstanding, whether it is ready\u002Fstable, or wants a detailed status report that combines codebase evidence with local Claude\u002FCodex conversation history.\n\nThis is read-only status synthesis. It does not replace `$roadmap`: `roadmap` maintains the task pipeline and priority queue; `codebase-status` explains the actual current state of the repo and relevant prior conversations.\n\n## Process\n\n1. Resolve target repo:\n   - Default to the current working directory.\n   - If the user provides a path, use that repo.\n   - Confirm it is a git worktree when possible; if not, continue with filesystem evidence and report that git evidence is unavailable.\n2. Read project orientation:\n   - `README.md`, `AGENTS.md`, `CLAUDE.md`, `.agents\u002Fproject.json`, package\u002Fworkspace files, app entrypoints, and high-signal docs.\n   - Identify project type, main apps\u002Fpackages, runtime, tests, and likely user-facing or developer-facing purpose.\n3. Read planning and status docs when present:\n   - `tasks\u002Froadmap.md`, `tasks\u002Ftodo.md`, `tasks\u002Fmanual-todo.md`, `tasks\u002Frecord-todo.md`, `tasks\u002Frecurring-todo.md`, `tasks\u002Fhistory.md`, `tasks\u002Flessons.md`, `tasks\u002Fphases\u002F`, `specs\u002F`, `spec.md`, and `research\u002F`.\n   - Distinguish checked-off work, active work, manual blockers, advisory work, stale docs, and missing docs.\n4. Read routing evidence for product, research, or spec repos:\n   - When `research\u002F`, `specs\u002F`, `spec.md`, product docs, or prototype artifacts exist, read `docs\u002Fpack-workflow-matrix.md` and `docs\u002Fskill-next-step-contracts.md` if present.\n   - Identify the last completed relevant research\u002Fproduct skill from artifacts, task history, or conversation history. Before recommending another research\u002Fproduct skill, consult that skill's active `SKILL.md` `## Next Steps` contract and any `## Next Steps` section in its output artifact.\n   - Treat those route contracts as stronger evidence than a generic status impression. If docs disagree, report the contradiction and prefer the newest active skill contract or route matrix with file evidence.\n   - For pack-local recommendations, check `.agents\u002Fproject.json` `enabled_packs` first. If the target skill's pack is not enabled, recommend `npx skillpacks install \u003Cpack-name>` from the project shell, before the skill.\n5. Inspect git evidence:\n   - `git status --short`\n   - current branch and upstream status\n   - last 20 commits\n   - unpushed commits when an upstream exists\n   - changed files in the working tree\n6. Inspect codebase health signals:\n   - Project structure and primary modules.\n   - Test\u002Fbuild\u002Flint scripts from package manifests or equivalent tool files.\n   - Obvious TODO\u002FFIXME markers, failing-test notes, disabled tests, and local quality scripts.\n   - Do not run expensive commands by default. Run cheap read-only inspections freely; ask or state assumptions before long builds, network installs, destructive commands, or mutation.\n7. Find related conversation history unless `--no-history` is passed:\n   - Read full available local prompt history, not a sample:\n     - `~\u002F.claude\u002Fhistory.jsonl`\n     - `~\u002F.codex\u002Fhistory.jsonl`\n     - `~\u002F.codex\u002Fsessions\u002F**\u002F*.jsonl` for Codex session metadata only when needed to map session IDs to cwd.\n   - Filter to records whose project\u002Fcwd matches the target repo or whose text mentions the absolute path, repo directory name, package\u002Fapp name, or repository URL.\n   - Exclude system, developer, tool output, injected skill payloads, and base instruction text from examples.\n   - Use line-by-line parsing for scale and deduplicate Codex prompt records when compact and rich histories overlap.\n   - Extract recent user goals, repeated requests, unresolved questions, blockers, and prior recommendations.\n8. Synthesize status:\n   - What this repo\u002Fapp is.\n   - What has happened recently.\n   - Current implementation status by major area.\n   - Outstanding work, grouped as blocking, next execution, advisory, manual\u002Fhuman-only, and uncertain.\n   - Mismatches between conversation history, task docs, git history, and code reality.\n   - Confidence level for each major conclusion: high, medium, or low, with evidence.\n9. Recommend next route:\n   - Use phase-aware routing before naming a command:\n     - If `tasks\u002Ftodo.md` or active phase docs contain actionable implementation work, recommend the approved task artifact route. Do not route back to research merely because advisory gaps exist.\n     - If finished work is dirty, unpushed, unvalidated, or needs packaging\u002Freview before handoff, recommend `$ship`.\n     - If user-facing product research\u002Fprototype artifacts are missing and no implementation\u002Fshipping queue is active, follow the canonical AFPS route from the routing evidence: `customer-discovery -> competitive-analysis -> journey-map -> positioning -> user-flow-map -> ux-variations [specific-user-flow] -> ui-interview [specific-ux-variation] -> prototype -> uat --variant-evaluation -> consolidate-prototypes -> research-roadmap --post-prototype -> spec-interview -> research-roadmap --post-spec -> roadmap`. Use `$ui-interview --requirements-only` and `$ux-variations --layout-mode` only when the user explicitly needs a fixed content\u002Fdata\u002Faction contract and layout-only alternatives.\n     - If `research\u002Ficp.md` and `research\u002Fcompetitive-analysis.md` exist but `research\u002Fjourney-map.md` is missing, check `customer-lifecycle` availability. If it is not enabled, recommend `npx skillpacks install customer-lifecycle` from the project shell, before `$journey-map`; if enabled, recommend `$journey-map`.\n     - Treat `value-prop-canvas` and `lean-canvas` as optional risk-driven detours only. Before recommending either, check `business-research` availability; if it is not enabled, recommend `npx skillpacks install business-research` from the project shell, before `$value-prop-canvas` or `$lean-canvas`. Recommend `$value-prop-canvas` only for contested solution-fit evidence, and `$lean-canvas` only for material business-model risk; do not make either a default blocker before `journey-map`, `positioning`, `user-flow-map`, or layout-mode UX variations.\n     - If no research, spec, task, implementation, validation, dirty, or unpushed work remains, recommend `$brainstorm` to discover new AFPS work.\n   - Approved task artifact route when the next task is already clear and executable.\n   - `$roadmap` when specs exist but sequencing or task queue health needs updating.\n   - `$feature-interview` when the next idea\u002Fdirection is not yet represented in specs or tasks.\n   - `$reconcile-dev-docs audit` or `$reconcile-dev-docs fix tasks` when task docs contradict git\u002Fcode reality.\n   - `$spec-drift` when specs and code appear out of sync.\n   - `$guide` only for human-only external blockers.\n   - `$brainstorm` when the repo is complete\u002Fcurrent and the next step is discovering a new phase.\n\n## Output\n\nProduce a structured report with:\n\n- **Overview:** repo path, project purpose, project type, primary apps\u002Fpackages, branch, dirty\u002Funpushed status.\n- **History Signal:** number of Claude\u002FCodex prompt records scanned, number matched to this repo, date range, and 3-8 concise real examples.\n- **Recent Work:** last commits and task\u002Fhistory evidence.\n- **Current Status:** major areas and whether each appears complete, in progress, blocked, stale, or unknown.\n- **Outstanding Work:** prioritized list with evidence and recommended owner\u002Fskill.\n- **Risks And Drift:** contradictions, stale docs, missing tests, manual blockers, or uncertain claims.\n- **Recommended Next Step:** one concrete next work item and one command.\n\nEnd with exactly:\n\n```md\n**Next work:** \u003Cspecific task, blocker, discovery task, or \"none\">\n**Recommended next command:** \u003Cone command or route>\n```\n\n## Constraints\n\n- Read-only by default. Do not modify files, create commits, run installs, or execute long test suites unless the user explicitly asks.\n- Do not include private conversation history unrelated to the target repo.\n- Quote only short prompt excerpts. Prefer paraphrase plus timestamp\u002Fsource\u002Fproject.\n- Do not treat `tasks\u002Frecord-todo.md` or `tasks\u002Frecurring-todo.md` as execution queues unless an item has clearly become concrete work.\n- Do not put agent-executable work in `tasks\u002Fmanual-todo.md` or route it to `$guide`.\n- Do not recommend `$roadmap` if the finding is only \"tell me the status\"; use `$roadmap` only when the task pipeline itself needs queue maintenance or roadmap extension.\n- When recommending a pack skill, first check `.agents\u002Fproject.json` for `enabled_packs`. If the target skill's pack is not enabled, include `npx skillpacks install \u003Cpack-name>` from the project shell, as a prerequisite in the recommendation.\n- Do not create or modify GitHub Actions workflows.\n\n## Default Shipping Contract\n\n- **Default next-step routing:** when reporting completion, include either `Recommended next skill: \u003Ccommand>` or the two-line pair `**Next work:** \u003Cspecific task or \"none\">` and `**Recommended next command:** \u003Cone command or route>` so the next caller has a concrete handoff.\n- Normally read-only and should not create or modify tracked repository files.\n- If the user explicitly asks this skill to create or modify tracked files, follow `docs\u002Fgithub-delivery-contract.md` and finish with an issue-backed non-primary branch plus ready pull request; do not merge it.\n- This contract does not override stricter safety rules about secrets, destructive history changes, release publication\u002Ftag confirmation, production deploy confirmation, paid actions, or public visibility changes.\n",{"name":5,"type":23,"version":36,"description":7,"argument-hint":37},"v0.12","[optional repo path, focus, or --no-history]","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fbase\u002Fcodex\u002Fcodebase-status",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill codebase-status",{"tool":54,"command":55},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill codebase-status",{"tool":57,"command":58},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill codebase-status","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbase\u002Fcodex\u002Fcodebase-status\u002FSKILL.md",true,[62,68],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"agents\u002Fopenai.yaml","REFERENCE","参考文档",371,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbase\u002Fcodex\u002Fcodebase-status\u002Fagents\u002Fopenai.yaml",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"CHANGELOG.md",2302,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fbase\u002Fcodex\u002Fcodebase-status\u002FCHANGELOG.md",[73,85,95,107,122,133],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":31},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[80,81,82,83,27,84],"source checkout allowed","checkout","fixture","only","valid",{"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":31},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[92,93,94,84,82,27],"deck install valid","deck","install",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":31},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[102,103,104,84,105,106,82,27],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":31},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[119,120,84,105,27,121,82],"codex missing skill valid","missing","fallback",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":31},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[128],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},[84,105,121,130,131,132,27,82],"base skill","codex base skill fallback valid","base",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":31},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[84,104,103,140,106,27,82],"claude pack guard valid"]