[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AD4WF3TVXDFD725XC227P8":3,"skill-same:01M6AD4WF3TVXDFD725XC227P8":117},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6AD4WF3TVXDFD725XC227P8","agent-skill-stack",null,"Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit, safety, and overlap. Do not use for locating one known or common Skill; use the generic find-skills workflow.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41081,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,9,37,38,39,40,41,42,43],"agent skill stack","stack","agent skill","goal","common skill","when","which","natural-language","opencli","skill audit","end","project","local","assemble","common","SET","audit","search","workflow","ai agent","2026-11-10 10:12:30",false,"---\nname: agent-skill-stack\ndescription: 'Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit, safety, and overlap. Do not use for locating one known or common Skill; use the generic find-skills workflow.'\n---\n\n# Build an Agent Skill Stack\n\nBuild the smallest useful stack for the user's actual outcome. Never force a domain example or a fixed lifecycle onto a different request.\n\n## 1. Choose the user-facing depth\n\nDefault to **plain-language mode**. Assume the user does not need to understand paths, revisions, hashes, manifests, static analysis, or runtime details.\n\nIn plain-language mode, show:\n\n- what the user is trying to accomplish;\n- the steps in everyday language;\n- which capabilities are already available;\n- which Skills are recommended, optional, overlapping, or unsuitable;\n- how widely each candidate is used;\n- whether it passed an installation safety check and a safe trial;\n- what account access or external actions it may require.\n\nKeep source paths, revisions, file fingerprints, raw scores, audit evidence, and dependency details in the internal record. Show them only when the user asks for technical details or when a specific technical fact is necessary for informed consent.\n\n## 2. Derive the workflow dynamically\n\nRead [references\u002Fworkflow-model.md](references\u002Fworkflow-model.md). Begin with the final result the user wants, not the domain words in the request.\n\nAsk only questions whose answers materially change the result, access boundary, cost, or stack. Derive the workflow backward from success, then validate it forward from the available starting point.\n\nDo not reuse a previous numbered flow. Do not assume that every request needs research, content creation, publishing, analytics, storage, or automation. Add a step only when the user's outcome requires it.\n\nStop decomposing when a step has one understandable action, one main result, one access boundary, and one observable success condition. Keep the technical capability cards internal; show the user a short plain-language flow.\n\n## 3. Search the local index first\n\nRead [references\u002Flocal-index-and-profiles.md](references\u002Flocal-index-and-profiles.md).\n\nIf a current local Skill index exists, search it before the filesystem or internet. If it is missing or stale, rebuild it from the relevant Skill roots:\n\n```bash\npython3 scripts\u002Fskill_index.py build \\\n  --root ~\u002F.codex\u002Fskills \\\n  --root ~\u002F.codex\u002Fplugins\u002Fcache \\\n  --root .codex\u002Fskills \\\n  --root ~\u002F.agents\u002Fskills \\\n  --root ~\u002F.hermes\u002Fskills \\\n  --output ~\u002F.codex\u002Fskill-index.json\n```\n\nThe index stores names, summaries, aliases, scope, capability terms, update time, and internal file fingerprints. It never executes a Skill and stores no usage history.\n\nIf the current project has `.codex\u002Fskill-stack.json`, treat its active Skills and routing rules as the first-choice stack. Search outside the profile only for an uncovered capability or when the user asks for alternatives. Treat same-name entries from different local roots as a review item; do not silently merge them.\n\n## 4. Map capabilities, including indirect helpers\n\nFor every necessary step, record internally:\n\n- required input, action, and output;\n- constraints, frequency, and scale;\n- local\u002Fread-external\u002Fwrite-external boundary;\n- account, permission, and approval needs;\n- success condition and fallback;\n- predecessor and successor steps.\n\nThen consider cross-cutting needs only where relevant: quality\u002Fstyle, accuracy, compliance, privacy, localization, data quality, orchestration, and observability.\n\nMatch Skills by `input -> operation -> output`, not by title similarity. This allows a Humanizer to match a natural-writing requirement even when the user's domain never appears in its name.\n\nDo not force one Skill per step. A Skill may cover several steps; a step may need a tool, MCP, connector, or general agent capability rather than another Skill.\n\n## 5. Search with four lenses\n\nRead [references\u002Fdiscovery-ranking.md](references\u002Fdiscovery-ranking.md). Search each uncovered capability through:\n\n1. **Direct need**: the user's domain and action.\n2. **Underlying operation**: the actual transformation or data task.\n3. **Supporting outcome**: quality, safety, style, compliance, evaluation, and monitoring.\n4. **Connection method**: CLI, MCP, API, connector, browser automation, storage, and handoff.\n\nExpand Chinese\u002FEnglish aliases, verbs, nouns, outputs, and adjacent terminology. Search titles, descriptions, headings, and full `SKILL.md` content when possible.\n\nUse multiple sources because no registry is complete:\n\n- the local Skill index and installed inventory;\n- GitHub connector or GitHub file\u002Frepository search;\n- `npx skills find \u003Cquery>` and skills.sh;\n- agentskill.sh or another registry when available;\n- OpenCLI for broad web discovery and platform-specific research.\n\nRun browser-backed OpenCLI searches sequentially. Do not log in, add credentials, or enable a connector without user approval.\n\n## 6. Verify and rank candidates\n\nTreat every search hit as a candidate, not a recommendation. Identify the canonical repository and exact Skill path. Read the full Skill and every executable file that installation would make reachable.\n\nReject or quarantine a candidate when:\n\n- its source or claimed capability cannot be verified;\n- its structure cannot be installed;\n- mandatory dependencies are incompatible or unavailable;\n- critical credential access, data upload, prompt injection, destructive action, or obfuscation remains unexplained;\n- its only possible test would publish, send, purchase, delete, or change a real account;\n- license or platform terms make the intended use materially uncertain.\n\nRank candidates that pass these gates with the rubric in [references\u002Fdiscovery-ranking.md](references\u002Fdiscovery-ranking.md). Real-world adoption and community evidence account for 25% of the score. Preserve unknown values as unknown.\n\nPrefer the smallest stack that meets all required success conditions. Classify candidates as:\n\n- **Required**: needed to complete the outcome.\n- **Helpful**: improves quality, safety, or efficiency.\n- **Alternative**: mutually exclusive substitute.\n- **Not recommended**: blocked, redundant, incompatible, or too uncertain.\n\n## 7. Analyze conflicts and scope\n\nRead [references\u002Fsecurity-installation.md](references\u002Fsecurity-installation.md). Check identity, activation, instruction, resource, dependency, data-format, permission, and compliance conflicts.\n\nResolve overlap by selecting one primary Skill, defining a narrow handoff to helpers, keeping alternatives mutually exclusive, or not installing the redundant candidate.\n\nPrefer project-local Skills and a project Skill Stack Profile for task-specific capabilities. Use global installation only for capabilities that should be available broadly.\n\n## 8. Present recommendations in plain language\n\nDefault output:\n\n1. **What you want to achieve**: one short restatement.\n2. **How the work breaks down**: a short numbered flow derived for this request.\n3. **What you already have**: existing useful Skills and uncovered gaps.\n4. **Recommended combination**: Required, Helpful, Alternative, and Not recommended.\n5. **Why these were chosen**: fit, adoption, safety check, safe trial, and conflicts in everyday language.\n6. **What needs your decision**: account access, paid services, external publishing, or installation selection.\n\nUse labels such as `已具备`, `推荐`, `可选`, `不建议`, `安全检查通过`, `安全试跑通过`, and `最近确认可用`. Do not show a hash or local path in the default response.\n\nOffer `查看技术详情` when useful. The technical view may include canonical source, revision, file fingerprint, exact destination, raw evidence, dependencies, permissions, and rollback details.\n\nWhen the user wants a reusable artifact, create a shareable recommendation card from structured JSON:\n\n```bash\npython3 scripts\u002Frender_stack_card.py \\\n  --input \u002Fpath\u002Fto\u002Fstack-card.json \\\n  --output \u002Fpath\u002Fto\u002Fstack-card.svg\n```\n\nKeep the card understandable without technical paths or raw hashes. Include the goal, selected Skills, each role and status, safety boundary, and verification date.\n\n## 9. Install only after consent\n\nRecommendation does not authorize installation. Follow [references\u002Fsecurity-installation.md](references\u002Fsecurity-installation.md) after the user chooses.\n\nDefault to staged installation. Allow a one-click batch only when every selected Skill passed the hard gates, has an exact pinned identity, has no unresolved conflict, will not overwrite an existing destination, and the user explicitly approves the batch.\n\nFor already downloaded and checked Skill directories, preview first:\n\n```bash\npython3 scripts\u002Fstage_install.py \\\n  --source \u002Fpath\u002Fto\u002Fskill-a \\\n  --dest ~\u002F.codex\u002Fskills \\\n  --manifest .\u002Fskill-stack-lock.json\n```\n\nRepeat with `--apply` only after approval. Never silently add credentials, accept new permissions, overwrite an installed Skill, or publish\u002Fsend\u002Fdelete external data.\n\nAfter the user selects the stack, offer to create a project profile in dry-run mode:\n\n```bash\npython3 scripts\u002Fproject_profile.py \\\n  --project \u002Fpath\u002Fto\u002Fproject \\\n  --name project-stack \\\n  --skill skill-a \\\n  --skill skill-b\n```\n\nUse `--apply` only after the user confirms the profile.\n\n## 10. Run a recall check\n\nAfter installation or profile changes, run a **recall check**, not a performance benchmark:\n\n1. a direct request that names the task;\n2. a natural paraphrase that uses different words;\n3. a supporting request that should bring in a helper such as writing quality, fact checking, or compliance.\n\nConfirm that the correct primary and supporting Skills are selected and unrelated Skills stay out. Report a simple result such as `3\u002F3 种说法都能正确识别`; keep raw prompts and routing details in the technical view.\n\nDo not collect or store user prompt history, hit\u002Fmiss logs, or routing feedback.\n","# Build an Agent Skill Stack\n\nBuild the smallest useful stack for the user's actual outcome. Never force a domain example or a fixed lifecycle onto a different request.\n\n## 1. Choose the user-facing depth\n\nDefault to **plain-language mode**. Assume the user does not need to understand paths, revisions, hashes, manifests, static analysis, or runtime details.\n\nIn plain-language mode, show:\n\n- what the user is trying to accomplish;\n- the steps in everyday language;\n- which capabilities are already available;\n- which Skills are recommended, optional, overlapping, or unsuitable;\n- how widely each candidate is used;\n- whether it passed an installation safety check and a safe trial;\n- what account access or external actions it may require.\n\nKeep source paths, revisions, file fingerprints, raw scores, audit evidence, and dependency details in the internal record. Show them only when the user asks for technical details or when a specific technical fact is necessary for informed consent.\n\n## 2. Derive the workflow dynamically\n\nRead [references\u002Fworkflow-model.md](references\u002Fworkflow-model.md). Begin with the final result the user wants, not the domain words in the request.\n\nAsk only questions whose answers materially change the result, access boundary, cost, or stack. Derive the workflow backward from success, then validate it forward from the available starting point.\n\nDo not reuse a previous numbered flow. Do not assume that every request needs research, content creation, publishing, analytics, storage, or automation. Add a step only when the user's outcome requires it.\n\nStop decomposing when a step has one understandable action, one main result, one access boundary, and one observable success condition. Keep the technical capability cards internal; show the user a short plain-language flow.\n\n## 3. Search the local index first\n\nRead [references\u002Flocal-index-and-profiles.md](references\u002Flocal-index-and-profiles.md).\n\nIf a current local Skill index exists, search it before the filesystem or internet. If it is missing or stale, rebuild it from the relevant Skill roots:\n\n```bash\npython3 scripts\u002Fskill_index.py build \\\n  --root ~\u002F.codex\u002Fskills \\\n  --root ~\u002F.codex\u002Fplugins\u002Fcache \\\n  --root .codex\u002Fskills \\\n  --root ~\u002F.agents\u002Fskills \\\n  --root ~\u002F.hermes\u002Fskills \\\n  --output ~\u002F.codex\u002Fskill-index.json\n```\n\nThe index stores names, summaries, aliases, scope, capability terms, update time, and internal file fingerprints. It never executes a Skill and stores no usage history.\n\nIf the current project has `.codex\u002Fskill-stack.json`, treat its active Skills and routing rules as the first-choice stack. Search outside the profile only for an uncovered capability or when the user asks for alternatives. Treat same-name entries from different local roots as a review item; do not silently merge them.\n\n## 4. Map capabilities, including indirect helpers\n\nFor every necessary step, record internally:\n\n- required input, action, and output;\n- constraints, frequency, and scale;\n- local\u002Fread-external\u002Fwrite-external boundary;\n- account, permission, and approval needs;\n- success condition and fallback;\n- predecessor and successor steps.\n\nThen consider cross-cutting needs only where relevant: quality\u002Fstyle, accuracy, compliance, privacy, localization, data quality, orchestration, and observability.\n\nMatch Skills by `input -> operation -> output`, not by title similarity. This allows a Humanizer to match a natural-writing requirement even when the user's domain never appears in its name.\n\nDo not force one Skill per step. A Skill may cover several steps; a step may need a tool, MCP, connector, or general agent capability rather than another Skill.\n\n## 5. Search with four lenses\n\nRead [references\u002Fdiscovery-ranking.md](references\u002Fdiscovery-ranking.md). Search each uncovered capability through:\n\n1. **Direct need**: the user's domain and action.\n2. **Underlying operation**: the actual transformation or data task.\n3. **Supporting outcome**: quality, safety, style, compliance, evaluation, and monitoring.\n4. **Connection method**: CLI, MCP, API, connector, browser automation, storage, and handoff.\n\nExpand Chinese\u002FEnglish aliases, verbs, nouns, outputs, and adjacent terminology. Search titles, descriptions, headings, and full `SKILL.md` content when possible.\n\nUse multiple sources because no registry is complete:\n\n- the local Skill index and installed inventory;\n- GitHub connector or GitHub file\u002Frepository search;\n- `npx skills find \u003Cquery>` and skills.sh;\n- agentskill.sh or another registry when available;\n- OpenCLI for broad web discovery and platform-specific research.\n\nRun browser-backed OpenCLI searches sequentially. Do not log in, add credentials, or enable a connector without user approval.\n\n## 6. Verify and rank candidates\n\nTreat every search hit as a candidate, not a recommendation. Identify the canonical repository and exact Skill path. Read the full Skill and every executable file that installation would make reachable.\n\nReject or quarantine a candidate when:\n\n- its source or claimed capability cannot be verified;\n- its structure cannot be installed;\n- mandatory dependencies are incompatible or unavailable;\n- critical credential access, data upload, prompt injection, destructive action, or obfuscation remains unexplained;\n- its only possible test would publish, send, purchase, delete, or change a real account;\n- license or platform terms make the intended use materially uncertain.\n\nRank candidates that pass these gates with the rubric in [references\u002Fdiscovery-ranking.md](references\u002Fdiscovery-ranking.md). Real-world adoption and community evidence account for 25% of the score. Preserve unknown values as unknown.\n\nPrefer the smallest stack that meets all required success conditions. Classify candidates as:\n\n- **Required**: needed to complete the outcome.\n- **Helpful**: improves quality, safety, or efficiency.\n- **Alternative**: mutually exclusive substitute.\n- **Not recommended**: blocked, redundant, incompatible, or too uncertain.\n\n## 7. Analyze conflicts and scope\n\nRead [references\u002Fsecurity-installation.md](references\u002Fsecurity-installation.md). Check identity, activation, instruction, resource, dependency, data-format, permission, and compliance conflicts.\n\nResolve overlap by selecting one primary Skill, defining a narrow handoff to helpers, keeping alternatives mutually exclusive, or not installing the redundant candidate.\n\nPrefer project-local Skills and a project Skill Stack Profile for task-specific capabilities. Use global installation only for capabilities that should be available broadly.\n\n## 8. Present recommendations in plain language\n\nDefault output:\n\n1. **What you want to achieve**: one short restatement.\n2. **How the work breaks down**: a short numbered flow derived for this request.\n3. **What you already have**: existing useful Skills and uncovered gaps.\n4. **Recommended combination**: Required, Helpful, Alternative, and Not recommended.\n5. **Why these were chosen**: fit, adoption, safety check, safe trial, and conflicts in everyday language.\n6. **What needs your decision**: account access, paid services, external publishing, or installation selection.\n\nUse labels such as `已具备`, `推荐`, `可选`, `不建议`, `安全检查通过`, `安全试跑通过`, and `最近确认可用`. Do not show a hash or local path in the default response.\n\nOffer `查看技术详情` when useful. The technical view may include canonical source, revision, file fingerprint, exact destination, raw evidence, dependencies, permissions, and rollback details.\n\nWhen the user wants a reusable artifact, create a shareable recommendation card from structured JSON:\n\n```bash\npython3 scripts\u002Frender_stack_card.py \\\n  --input \u002Fpath\u002Fto\u002Fstack-card.json \\\n  --output \u002Fpath\u002Fto\u002Fstack-card.svg\n```\n\nKeep the card understandable without technical paths or raw hashes. Include the goal, selected Skills, each role and status, safety boundary, and verification date.\n\n## 9. Install only after consent\n\nRecommendation does not authorize installation. Follow [references\u002Fsecurity-installation.md](references\u002Fsecurity-installation.md) after the user chooses.\n\nDefault to staged installation. Allow a one-click batch only when every selected Skill passed the hard gates, has an exact pinned identity, has no unresolved conflict, will not overwrite an existing destination, and the user explicitly approves the batch.\n\nFor already downloaded and checked Skill directories, preview first:\n\n```bash\npython3 scripts\u002Fstage_install.py \\\n  --source \u002Fpath\u002Fto\u002Fskill-a \\\n  --dest ~\u002F.codex\u002Fskills \\\n  --manifest .\u002Fskill-stack-lock.json\n```\n\nRepeat with `--apply` only after approval. Never silently add credentials, accept new permissions, overwrite an installed Skill, or publish\u002Fsend\u002Fdelete external data.\n\nAfter the user selects the stack, offer to create a project profile in dry-run mode:\n\n```bash\npython3 scripts\u002Fproject_profile.py \\\n  --project \u002Fpath\u002Fto\u002Fproject \\\n  --name project-stack \\\n  --skill skill-a \\\n  --skill skill-b\n```\n\nUse `--apply` only after the user confirms the profile.\n\n## 10. Run a recall check\n\nAfter installation or profile changes, run a **recall check**, not a performance benchmark:\n\n1. a direct request that names the task;\n2. a natural paraphrase that uses different words;\n3. a supporting request that should bring in a helper such as writing quality, fact checking, or compliance.\n\nConfirm that the correct primary and supporting Skills are selected and unrelated Skills stay out. Report a simple result such as `3\u002F3 种说法都能正确识别`; keep raw prompts and routing details in the technical view.\n\nDo not collect or store user prompt history, hit\u002Fmiss logs, or routing feedback.\n",{"name":5,"description":7},"main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd","skills\u002Fagent-skill-stack",5344,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","https:\u002F\u002Fawesome-copilot.github.com\u002F","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-13 02:05:36",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add github\u002Fawesome-copilot --skill agent-skill-stack",{"tool":65,"command":66},"bunx","bunx skills add github\u002Fawesome-copilot --skill agent-skill-stack",{"tool":68,"command":69},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill agent-skill-stack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002FSKILL.md",true,[73,79,83,87,91,95,101,105,109,113],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"agents\u002Fopenai.yaml","REFERENCE","参考文档",276,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Fagents\u002Fopenai.yaml",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fdiscovery-ranking.md",4923,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Freferences\u002Fdiscovery-ranking.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Flocal-index-and-profiles.md",3008,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Freferences\u002Flocal-index-and-profiles.md",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fsecurity-installation.md",5432,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Freferences\u002Fsecurity-installation.md",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fworkflow-model.md",4487,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Freferences\u002Fworkflow-model.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Finventory_skills.py","SCRIPT","脚本",10796,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Fscripts\u002Finventory_skills.py",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Fproject_profile.py",4438,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Fscripts\u002Fproject_profile.py",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Frender_stack_card.py",6465,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Fscripts\u002Frender_stack_card.py",{"path":110,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fskill_index.py",10783,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Fscripts\u002Fskill_index.py",{"path":114,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fstage_install.py",7194,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fagent-skill-stack\u002Fscripts\u002Fstage_install.py",[118,147,173,202,235,252],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":128,"publishedAt":44},"01M70KXZNX9ES38N2A8M58ZZMZ","supabase-rls-policies","Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsupabase-rls-policies\u002FSKILL.md",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[129,130,131,132,35,29,133,134,135,136,137,138,139,140,141,142,143,144,145,146],"supabase","rls","supabase rls","supabase rls policies","review","change","read","write","security","isolation","tables","as","tests","prove","use","users","functions","with",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":154,"publishedAt":44},"01M70KWA5YWXDV6V8DZ19E3T2Y","skill-distribution-audit","Audit a skill collection before release or investigate installer omissions, archived\u002Ftemplate leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fskill-distribution-audit\u002FSKILL.md",[153],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[155,156,40,39,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172],"distribution","skill distribution audit","deterministic","installer","for","discovery","comparison","helper","manifest","version","collection","drift","output","investigate","duplicate","template","release","reconcile",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":177,"sourceHtmlUrl":178,"categories":179,"keywords":185,"publishedAt":44},"01M70KCJPFVW7PPQ49CC5R8JGK","logicapps-custom-code-net10-migration","Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project\u002Fpackage configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FSKILL.md",[180],{"categoryNo":181,"categoryName":182,"taxonomyType":183,"taxonomyTypeDesc":184},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[186,187,188,189,190,191,159,35,192,193,36,194,195,196,197,143,198,199,200,201],"custom","code","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"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":206,"sourceHtmlUrl":207,"categories":208,"keywords":213,"publishedAt":44},"01M6AEBN37RQMXJ3298PEY7PG1","winmd-api-search","Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI\u002FML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FSKILL.md",[209,212],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":181,"categoryName":182,"taxonomyType":183,"taxonomyTypeDesc":184},[214,41,215,216,217,218,219,220,221,222,223,224,225,226,227,29,228,229,230,231,232,159,233,234],"winmd api search","api","windows","desktop","file access","enumeration","ui","ml","file","networking","capabilities","notifications","explore","access","features","full","camera","events","platform","methods","controls",{"skillNo":236,"name":237,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":239,"licenseFileUrl":240,"sourceHtmlUrl":241,"categories":242,"keywords":248,"publishedAt":44},"01M6AE571R3SC1ZGE202B3NB5S","resemble-detect","Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FSKILL.md",[243,244,247],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":245,"categoryName":246,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[249,39,222,250,251],"resemble detect","https","identity",{"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":239,"licenseFileUrl":256,"sourceHtmlUrl":257,"categories":258,"keywords":263,"publishedAt":44},"01M6AE30BSK2HCY4TQQ22Z8JRD","quality-playbook","Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FSKILL.md",[259,262],{"categoryNo":260,"categoryName":261,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[264,265,266,267,187,133,9,40,268,269,250,270,271,272,273,274,275,276,277,278,279,280,141,281,282,283,284],"playbook","quality playbook","quality","code review","tdd","run","report","spec","bug report","council","engineering","functional","spec audit","bug","verified","multi-model","three","coverage","model","regression","structural"]