[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AD9E543VTCR5JND17BK4P9":3,"skill-same:01M6AD9E543VTCR5JND17BK4P9":91},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":70,"repositoryHtmlUrl":71,"repositoryHomepageUrl":72,"ownerHtmlUrl":73,"ownerBlogUrl":74,"ownerDescription":75,"updatedAt":76,"install":77,"resources":90},"01M6AD9E543VTCR5JND17BK4P9","cross-squad",null,"Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says 'squad' (the product) vs casual English 'group of agents'.","github\u002Fgh-aw","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3VCZ4WKQSFSRTPN7N9DN",5636,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fcross-squad\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"cross squad","squad","work","when","which","you","english","discover","across","instances","up","ask","delegate","review","SET","repository","product","delegation","capabilities","create","orchestration","2026-11-10 10:12:30",false,"---\nname: \"cross-squad\"\ndescription: \"Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says 'squad' (the product) vs casual English 'group of agents'.\"\ndomain: \"orchestration\"\nconfidence: \"medium\"\nsource: \"manual\"\ntriggers:\n  - \"spawn N squads\"\n  - \"spawn a squad\"\n  - \"another squad\"\n  - \"two squads of\"\n  - \"second squad\"\n  - \"fan out to squads\"\n  - \"delegate to a squad\"\n  - \"set up squads for\"\n  - \"create a squad to review\"\n  - \"ask the other squad\"\ntools:\n  - name: \"squad-discover\"\n    description: \"List known squads and their capabilities\"\n    when: \"When you need to find which squad can handle a task\"\n  - name: \"squad-delegate\"\n    description: \"Create work in another squad's repository\"\n    when: \"When a task belongs to another squad's domain\"\n---\n\n## Context\n\n> **Read this FIRST any time the user says \"squad\" as a thing to spawn, delegate to, address, or fan out to** — e.g., *\"spawn two squads of designers and devs\"*, *\"ask the other squad\"*, *\"delegate to a squad\"*. In Squad-PRODUCT vocabulary, \"squad\" is a **peer** (an independent installation with its own `.squad\u002F`, `team.md`, MCP server, and agents) — NOT a generic English synonym for \"team\" or \"group\". Do not fan out raw `task` agents inside your own coordinator context when the user means \"another squad\". Use the discovery and communication patterns below (and the companion `cross-squad-communication` skill for the actual protocols).\n\nWhen an organization runs multiple Squad instances (e.g., platform-squad, frontend-squad, data-squad), those squads need to discover each other, share context, and hand off work across repository boundaries. This skill teaches agents how to coordinate across squads without creating tight coupling.\n\n> **Companion skill — for protocol details:** `cross-squad-communication\u002FSKILL.md` covers the four communication patterns (synchronous CLI, read-only knowledge query, git-based async, and GitHub-issue-based delegation) once a peer squad is discovered via the registry below. This skill answers \"who?\" — the companion answers \"how?\".\n\nCross-squad orchestration applies when:\n- A task requires capabilities owned by another squad\n- An architectural decision affects multiple squads\n- A feature spans multiple repositories with different squads\n- A squad needs to request infrastructure, tooling, or support from another squad\n\n## Disambiguation: \"squad\" vs ad-hoc agents\n\nWhen the user uses the word **\"squad\" \u002F \"squads\"** or asks to **\"spawn a team\"**, the coordinator MUST treat it as a literal reference to a Squad install (a `.squad\u002F` directory with its own roster, casting, and coordinator) — NOT as a casual synonym for \"a group of sub-agents\".\n\n### Default behaviour (apply unless explicitly told otherwise)\n\n| User says | Coordinator does |\n|---|---|\n| *\"spawn two squads of X and Y\"* \u002F *\"set up squads for X, Y, Z\"* | Bootstrap N **real** Squad installs — separate folder + `git init` + `squad init` per squad — then use the cross-squad patterns below (`.squad\u002Fmanifest.json`, `squad registry add`, `squad delegate`) and the protocols in the `cross-squad-communication` skill |\n| *\"ask the other squad about X\"* \u002F *\"delegate to the data squad\"* | Discover the peer via `squad registry list` (or by reading a known `.squad\u002Fmanifest.json`), then use `cross-squad-communication` Pattern 0 \u002F 1 \u002F 2 \u002F 3 — never re-implement the protocol with `task` |\n| *\"spawn a few agents to do X\"* \u002F *\"have some agents review X\"* \u002F *\"in parallel, get sub-agents to...\"* | Ad-hoc `task` fan-out is fine — no `.squad\u002F` bootstrap needed. This is the only path where raw `task` is appropriate when the user mentioned a multi-agent activity |\n\n### Ambiguous? `ask_user`, never silently downgrade\n\nIf the request **could** be either interpretation AND bootstrapping real squads is non-trivial (more than one or two `squad init` runs), you MUST use the `ask_user` tool with a 2-choice prompt before proceeding:\n\n```\nquestion: \"Should I create separate Squad installs or just dispatch ad-hoc agents?\"\nchoices:\n  - \"Real squads — separate .squad\u002F per squad (heavier, persistent, can be re-engaged later)\"\n  - \"Ad-hoc agents — one-shot `task` dispatch (lighter, ephemeral, no .squad\u002F created)\"\n```\n\nThe cost of asking is one `ask_user`. The cost of getting it wrong is the user has to redo the work. **Never silently pick the cheaper option just because it feels disproportionate for the task size — surface the trade-off and let the user pick.**\n\n### Anti-patterns (every one of these is a real failure mode observed in production)\n\n- **Calling `task` sub-agents \"squad-alpha\" \u002F \"squad-beta\"** and treating them as squads. Naming something a squad doesn't make it one — a squad has its own `.squad\u002F`, `team.md`, MCP server, and coordinator. If those aren't there, it's not a squad.\n- **Matching a prior session's ad-hoc pattern without re-checking current intent.** If you see existing `reviews\u002Fsquad-alpha\u002F` folders from a previous run, that's a hint, NOT a contract — the user may have meant something different this time. Re-evaluate from scratch.\n- **Silently choosing the cheaper interpretation because \"bootstrapping two real squads for a 30-line app feels disproportionate\".** That's a judgment call for the USER to make, not the coordinator. Use `ask_user`.\n- **Loading the `cross-squad` skill, reading it, then doing `task` fan-out anyway** because the eager-execution \u002F parallel-fan-out doctrine pulled you back. The disambiguation rule on this page OVERRIDES the generic fan-out doctrine when \"squad\" was the trigger.\n\n## Patterns\n\n### Discovery via Manifest\nEach squad publishes a `.squad\u002Fmanifest.json` declaring its name, capabilities, and contact information. Squads discover each other through two mechanisms:\n\n1. **`.squad\u002Fsquad-registry.json`** — **discovery-only.** Peer squads are findable via `squad discover` and addressable via `squad delegate`, but their skills\u002Fdecisions\u002Fwisdom are NOT loaded into your coordinator. Manage with `squad registry add\u002Flist\u002Fremove`.\n2. **`.squad\u002Fupstream.json`** — **discovery + inheritance.** Squads listed here are also discoverable, AND your coordinator inherits their skills\u002Fdecisions\u002Fwisdom\u002Frouting at session start. Manage with `squad upstream add\u002Flist\u002Fremove\u002Fsync`.\n\nBoth forms read the peer's manifest via the same code path. The `path` field is the **repository root** (e.g. `..\u002Ffriend-repo`), and Squad appends `.squad\u002Fmanifest.json` internally. Pointing at the `.squad\u002F` directory works too — Squad accepts both forms (`readManifest` strips a trailing `.squad` if present).\n\n```json\n{\n  \"name\": \"platform-squad\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Platform infrastructure team\",\n  \"capabilities\": [\"kubernetes\", \"helm\", \"monitoring\", \"ci-cd\"],\n  \"contact\": {\n    \"repo\": \"org\u002Fplatform\",\n    \"labels\": [\"squad:platform\"]\n  },\n  \"accepts\": [\"issues\", \"prs\"],\n  \"skills\": [\"helm-developer\", \"operator-developer\", \"pipeline-engineer\"]\n}\n```\n\n### Context Sharing\nWhen delegating work, share only what the target squad needs:\n- **Capability list**: What this squad can do (from manifest)\n- **Relevant decisions**: Only decisions that affect the target squad\n- **Handoff context**: A concise description of why this work is being delegated\n\nDo NOT share:\n- Internal team state (casting history, session logs)\n- Full decision archives (send only relevant excerpts)\n- Authentication credentials or secrets\n\n### Work Handoff Protocol\n1. **Check manifest**: Verify the target squad accepts the work type (issues, PRs)\n2. **Create issue**: Use `gh issue create` in the target repo with:\n   - Title: `[cross-squad] \u003Cdescription>`\n   - Label: `squad:cross-squad` (or the squad's configured label)\n   - Body: Context, acceptance criteria, and link back to originating issue\n3. **Track**: Record the cross-squad issue URL in the originating squad's orchestration log\n4. **Poll**: Periodically check if the delegated issue is closed\u002Fcompleted\n\n### Feedback Loop\nTrack delegated work completion:\n- Poll target issue status via `gh issue view`\n- Update originating issue with status changes\n- Close the feedback loop when delegated work merges\n\n## Examples\n\n### Registering a peer squad (no inheritance)\n```bash\n# Friend's repo is checked out at ..\u002Ffriend-platform\u002F\nsquad registry add platform-squad ..\u002Ffriend-platform\n\n# Verify\nsquad registry list\nsquad discover\n```\n\n### Discovering squads\n```bash\n# List all squads discoverable from registry + upstreams\nsquad discover\n\n# Output:\n#   platform-squad  →  org\u002Fplatform  (kubernetes, helm, monitoring)\n#   frontend-squad  →  org\u002Ffrontend  (react, nextjs, storybook)\n#   data-squad      →  org\u002Fdata      (spark, airflow, dbt)\n```\n\n### Delegating work\n```bash\n# Delegate a task to the platform squad\nsquad delegate platform-squad \"Add Prometheus metrics endpoint for the auth service\"\n\n# Creates issue in org\u002Fplatform with cross-squad label and context\n```\n\n### Manifest in squad.config.ts\n```typescript\nexport default defineSquad({\n  manifest: {\n    name: 'platform-squad',\n    capabilities: ['kubernetes', 'helm'],\n    contact: { repo: 'org\u002Fplatform', labels: ['squad:platform'] },\n    accepts: ['issues', 'prs'],\n    skills: ['helm-developer', 'operator-developer'],\n  },\n});\n```\n\n## Anti-Patterns\n- **Direct file writes across repos** — Never modify another squad's `.squad\u002F` directory. Use issues and PRs as the communication protocol.\n- **Tight coupling** — Don't depend on another squad's internal structure. Use the manifest as the public API contract.\n- **Unbounded delegation** — Always include acceptance criteria and a timeout. Don't create open-ended requests.\n- **Skipping discovery** — Don't hardcode squad locations. Use manifests and the discovery protocol.\n- **Sharing secrets** — Never include credentials, tokens, or internal URLs in cross-squad issues.\n- **Circular delegation** — Track delegation chains. If squad A delegates to B which delegates back to A, something is wrong.\n","## Context\n\n> **Read this FIRST any time the user says \"squad\" as a thing to spawn, delegate to, address, or fan out to** — e.g., *\"spawn two squads of designers and devs\"*, *\"ask the other squad\"*, *\"delegate to a squad\"*. In Squad-PRODUCT vocabulary, \"squad\" is a **peer** (an independent installation with its own `.squad\u002F`, `team.md`, MCP server, and agents) — NOT a generic English synonym for \"team\" or \"group\". Do not fan out raw `task` agents inside your own coordinator context when the user means \"another squad\". Use the discovery and communication patterns below (and the companion `cross-squad-communication` skill for the actual protocols).\n\nWhen an organization runs multiple Squad instances (e.g., platform-squad, frontend-squad, data-squad), those squads need to discover each other, share context, and hand off work across repository boundaries. This skill teaches agents how to coordinate across squads without creating tight coupling.\n\n> **Companion skill — for protocol details:** `cross-squad-communication\u002FSKILL.md` covers the four communication patterns (synchronous CLI, read-only knowledge query, git-based async, and GitHub-issue-based delegation) once a peer squad is discovered via the registry below. This skill answers \"who?\" — the companion answers \"how?\".\n\nCross-squad orchestration applies when:\n- A task requires capabilities owned by another squad\n- An architectural decision affects multiple squads\n- A feature spans multiple repositories with different squads\n- A squad needs to request infrastructure, tooling, or support from another squad\n\n## Disambiguation: \"squad\" vs ad-hoc agents\n\nWhen the user uses the word **\"squad\" \u002F \"squads\"** or asks to **\"spawn a team\"**, the coordinator MUST treat it as a literal reference to a Squad install (a `.squad\u002F` directory with its own roster, casting, and coordinator) — NOT as a casual synonym for \"a group of sub-agents\".\n\n### Default behaviour (apply unless explicitly told otherwise)\n\n| User says | Coordinator does |\n|---|---|\n| *\"spawn two squads of X and Y\"* \u002F *\"set up squads for X, Y, Z\"* | Bootstrap N **real** Squad installs — separate folder + `git init` + `squad init` per squad — then use the cross-squad patterns below (`.squad\u002Fmanifest.json`, `squad registry add`, `squad delegate`) and the protocols in the `cross-squad-communication` skill |\n| *\"ask the other squad about X\"* \u002F *\"delegate to the data squad\"* | Discover the peer via `squad registry list` (or by reading a known `.squad\u002Fmanifest.json`), then use `cross-squad-communication` Pattern 0 \u002F 1 \u002F 2 \u002F 3 — never re-implement the protocol with `task` |\n| *\"spawn a few agents to do X\"* \u002F *\"have some agents review X\"* \u002F *\"in parallel, get sub-agents to...\"* | Ad-hoc `task` fan-out is fine — no `.squad\u002F` bootstrap needed. This is the only path where raw `task` is appropriate when the user mentioned a multi-agent activity |\n\n### Ambiguous? `ask_user`, never silently downgrade\n\nIf the request **could** be either interpretation AND bootstrapping real squads is non-trivial (more than one or two `squad init` runs), you MUST use the `ask_user` tool with a 2-choice prompt before proceeding:\n\n```\nquestion: \"Should I create separate Squad installs or just dispatch ad-hoc agents?\"\nchoices:\n  - \"Real squads — separate .squad\u002F per squad (heavier, persistent, can be re-engaged later)\"\n  - \"Ad-hoc agents — one-shot `task` dispatch (lighter, ephemeral, no .squad\u002F created)\"\n```\n\nThe cost of asking is one `ask_user`. The cost of getting it wrong is the user has to redo the work. **Never silently pick the cheaper option just because it feels disproportionate for the task size — surface the trade-off and let the user pick.**\n\n### Anti-patterns (every one of these is a real failure mode observed in production)\n\n- **Calling `task` sub-agents \"squad-alpha\" \u002F \"squad-beta\"** and treating them as squads. Naming something a squad doesn't make it one — a squad has its own `.squad\u002F`, `team.md`, MCP server, and coordinator. If those aren't there, it's not a squad.\n- **Matching a prior session's ad-hoc pattern without re-checking current intent.** If you see existing `reviews\u002Fsquad-alpha\u002F` folders from a previous run, that's a hint, NOT a contract — the user may have meant something different this time. Re-evaluate from scratch.\n- **Silently choosing the cheaper interpretation because \"bootstrapping two real squads for a 30-line app feels disproportionate\".** That's a judgment call for the USER to make, not the coordinator. Use `ask_user`.\n- **Loading the `cross-squad` skill, reading it, then doing `task` fan-out anyway** because the eager-execution \u002F parallel-fan-out doctrine pulled you back. The disambiguation rule on this page OVERRIDES the generic fan-out doctrine when \"squad\" was the trigger.\n\n## Patterns\n\n### Discovery via Manifest\nEach squad publishes a `.squad\u002Fmanifest.json` declaring its name, capabilities, and contact information. Squads discover each other through two mechanisms:\n\n1. **`.squad\u002Fsquad-registry.json`** — **discovery-only.** Peer squads are findable via `squad discover` and addressable via `squad delegate`, but their skills\u002Fdecisions\u002Fwisdom are NOT loaded into your coordinator. Manage with `squad registry add\u002Flist\u002Fremove`.\n2. **`.squad\u002Fupstream.json`** — **discovery + inheritance.** Squads listed here are also discoverable, AND your coordinator inherits their skills\u002Fdecisions\u002Fwisdom\u002Frouting at session start. Manage with `squad upstream add\u002Flist\u002Fremove\u002Fsync`.\n\nBoth forms read the peer's manifest via the same code path. The `path` field is the **repository root** (e.g. `..\u002Ffriend-repo`), and Squad appends `.squad\u002Fmanifest.json` internally. Pointing at the `.squad\u002F` directory works too — Squad accepts both forms (`readManifest` strips a trailing `.squad` if present).\n\n```json\n{\n  \"name\": \"platform-squad\",\n  \"version\": \"1.0.0\",\n  \"description\": \"Platform infrastructure team\",\n  \"capabilities\": [\"kubernetes\", \"helm\", \"monitoring\", \"ci-cd\"],\n  \"contact\": {\n    \"repo\": \"org\u002Fplatform\",\n    \"labels\": [\"squad:platform\"]\n  },\n  \"accepts\": [\"issues\", \"prs\"],\n  \"skills\": [\"helm-developer\", \"operator-developer\", \"pipeline-engineer\"]\n}\n```\n\n### Context Sharing\nWhen delegating work, share only what the target squad needs:\n- **Capability list**: What this squad can do (from manifest)\n- **Relevant decisions**: Only decisions that affect the target squad\n- **Handoff context**: A concise description of why this work is being delegated\n\nDo NOT share:\n- Internal team state (casting history, session logs)\n- Full decision archives (send only relevant excerpts)\n- Authentication credentials or secrets\n\n### Work Handoff Protocol\n1. **Check manifest**: Verify the target squad accepts the work type (issues, PRs)\n2. **Create issue**: Use `gh issue create` in the target repo with:\n   - Title: `[cross-squad] \u003Cdescription>`\n   - Label: `squad:cross-squad` (or the squad's configured label)\n   - Body: Context, acceptance criteria, and link back to originating issue\n3. **Track**: Record the cross-squad issue URL in the originating squad's orchestration log\n4. **Poll**: Periodically check if the delegated issue is closed\u002Fcompleted\n\n### Feedback Loop\nTrack delegated work completion:\n- Poll target issue status via `gh issue view`\n- Update originating issue with status changes\n- Close the feedback loop when delegated work merges\n\n## Examples\n\n### Registering a peer squad (no inheritance)\n```bash\n# Friend's repo is checked out at ..\u002Ffriend-platform\u002F\nsquad registry add platform-squad ..\u002Ffriend-platform\n\n# Verify\nsquad registry list\nsquad discover\n```\n\n### Discovering squads\n```bash\n# List all squads discoverable from registry + upstreams\nsquad discover\n\n# Output:\n#   platform-squad  →  org\u002Fplatform  (kubernetes, helm, monitoring)\n#   frontend-squad  →  org\u002Ffrontend  (react, nextjs, storybook)\n#   data-squad      →  org\u002Fdata      (spark, airflow, dbt)\n```\n\n### Delegating work\n```bash\n# Delegate a task to the platform squad\nsquad delegate platform-squad \"Add Prometheus metrics endpoint for the auth service\"\n\n# Creates issue in org\u002Fplatform with cross-squad label and context\n```\n\n### Manifest in squad.config.ts\n```typescript\nexport default defineSquad({\n  manifest: {\n    name: 'platform-squad',\n    capabilities: ['kubernetes', 'helm'],\n    contact: { repo: 'org\u002Fplatform', labels: ['squad:platform'] },\n    accepts: ['issues', 'prs'],\n    skills: ['helm-developer', 'operator-developer'],\n  },\n});\n```\n\n## Anti-Patterns\n- **Direct file writes across repos** — Never modify another squad's `.squad\u002F` directory. Use issues and PRs as the communication protocol.\n- **Tight coupling** — Don't depend on another squad's internal structure. Use the manifest as the public API contract.\n- **Unbounded delegation** — Always include acceptance criteria and a timeout. Don't create open-ended requests.\n- **Skipping discovery** — Don't hardcode squad locations. Use manifests and the discovery protocol.\n- **Sharing secrets** — Never include credentials, tokens, or internal URLs in cross-squad issues.\n- **Circular delegation** — Track delegation chains. If squad A delegates to B which delegates back to A, something is wrong.\n",{"name":5,"tools":45,"domain":39,"source":54,"triggers":55,"confidence":66,"description":7},[46,50],{"name":47,"when":48,"description":49},"squad-discover","When you need to find which squad can handle a task","List known squads and their capabilities",{"name":51,"when":52,"description":53},"squad-delegate","When a task belongs to another squad's domain","Create work in another squad's repository","manual",[56,57,58,59,60,61,62,63,64,65],"spawn N squads","spawn a squad","another squad","two squads of","second squad","fan out to squads","delegate to a squad","set up squads for","create a squad to review","ask the other squad","medium","main","8541229759617347888641eba917d3b0ad66a984",".squad\u002Ftemplates\u002Fskills\u002Fcross-squad",626,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw","https:\u002F\u002Fgh.io\u002Fgh-aw","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-15 06:45:15",{"source":8,"skillName":5,"commands":78,"prompt":88,"zipAvailable":89},[79,82,85],{"tool":80,"command":81},"npx","npx skills add github\u002Fgh-aw --skill cross-squad",{"tool":83,"command":84},"bunx","bunx skills add github\u002Fgh-aw --skill cross-squad",{"tool":86,"command":87},"pnpm","pnpm dlx skills add github\u002Fgh-aw --skill cross-squad","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fcross-squad\u002FSKILL.md",true,[],[92,100,108,137,155,179],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":99},"01M7DQYVZ9W9DDXKQ9452SNP8J","cracktro","Edit, preview, and verify the standalone interactive talk deck in docs\u002Fpublic\u002Fcracktro (slides, SVG diagrams, transitions, WebAudio sound).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcracktro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":107},"01M7612HQ4378TK8QZ5HPAF4KR","create-connector","Create or extend a declaration-only third-party connector, with narrow reads, separate safe outputs, optional protected triggers, and offline conformance evidence.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcreate-connector\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":122,"publishedAt":40},"01M6ADC942STTXHFV410J4DH0X","GitHub Agentic Workflows","GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension for writing Agentic Workflows in markdown and compiling them to GitHub Actions.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002FSKILL.md",[114,119],{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":120,"categoryName":121,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000023","Skill与智能体开发",[9,123,124,125,126,127,128,129,130,131,132,133,134,135,136],"github agentic workflows","agentic workflows","workflows","agentic","extension","markdown","github cli","cli","gh","for","compiling","writing","github actions","actions",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":40},"01M6ADC6ZXSA46N9XD6VNAP1MS","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[144,145,146,147,148,149,150,151,152,153,154],"windows","windows compatibility","compatibility","command","git","bugs","platform","high","patterns","cross-platform","path",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":40},"01M6ADC44957SVQF96R5YY247P","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[162,163,164,165,166,130,167,168,169,170,171,172,173,20,132,174,175,176,177,178],"versioning","policy","versioning policy","gate","implementation","workspace","pr","sdk","release","ci","npm","semver","incident","incidents","Rules","version","resolution",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":189,"publishedAt":40},"01M6ADC1PHMEAEVR87F8PDR89X","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[185,188],{"categoryNo":186,"categoryName":187,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":120,"categoryName":121,"taxonomyType":117,"taxonomyTypeDesc":118},[190,191,192,193,194,195,196,197,198,199,200,201,202,132,203,204],"tiered memory","memory","performance","design","agent memory","proposal","cold","model","wiki","spawn","memory-management","context","three","runtime","management"]