[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WZWFSXT73KQAGV4535VG8Z":3,"skill-same:01M6WZWFSXT73KQAGV4535VG8Z":75},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6WZWFSXT73KQAGV4535VG8Z","squad-help",null,"How to use the Squad coordinator agent and the separate squad menu skill, with host-dependent discovery and slash-command support.","microsoft\u002Fwaza","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6WZT4PAP160SPCF851532KH",1508,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsquad-help\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"squad help","squad","help","use","waza","managed","for","high","with","coordinator","how to","host","project","sdk","command","how","discovery","onboarding","support","2026-11-10 10:12:30",false,"---\nname: \"squad-help\"\ndescription: \"How to use the Squad coordinator agent and the separate squad menu skill, with host-dependent discovery and slash-command support.\"\nallowedTools: []\nconfidence: high\ndomain: squad-onboarding\nsource: \"Squad SDK managed help with a Waza project correction for host-dependent menu invocation.\"\n---\n\n# Skill: squad-help\n\n> **Quick reference.** If you're reading this because a user said \"use squad\" or \"squad\" or \"set up a squad\", you're in the right place — read on for the correct invocation paths.\n\n---\n\n## Squad coordinator and squad menu skill\n\nThe Squad framework registers a **custom Copilot CLI agent** at `.github\u002Fagents\u002Fsquad.agent.md`. The agent is named **`Squad`** and its description is *\"Your AI team. Describe what you're building, get a team of specialists that live in your repo.\"*\n\nCopilot CLI agents and skills are different things:\n\n| Thing | How to invoke | Example |\n|---|---|---|\n| **Menu skill** | Host skill tool, natural-language match, or exposed skill command | `skill(squad)` when available |\n| **Agent** | `task` tool with `agent_type=\u003Cname>` | `task(name=\"...\", agent_type=\"Squad\", prompt=\"...\")` |\n| **Slash command** | Host-dependent built-in command or exposed user-invocable skill | `\u002Fsquad` when the host exposes the installed menu |\n\nThe `Squad` agent performs coordination; the separate `squad` menu skill lives at\n`.github\u002Fskills\u002Fsquad\u002FSKILL.md` and declares `user-invocable: true`. They are not\ninterchangeable. Slash-command availability is **host-dependent**: use `\u002Fsquad` only\nwhere the host exposes that skill as a command. Otherwise use its natural-language\ntriggers or the host's skill picker\u002Ftool, when available; invoke the coordinator agent\nfor actual orchestration.\n\n---\n\n## How to actually use Squad\n\nPick the path that matches the user's intent:\n\n### A) Invoke the Squad coordinator agent (most common)\n\nThe Squad coordinator orchestrates a team of specialists. It routes work to the right agent, scaffolds a team if none exists, and enforces handoffs.\n\n```text\ntask(\n  name=\"\u003Cshort-task-name>\",\n  agent_type=\"Squad\",\n  prompt=\"\u003Cwhat you want the team to do>\"\n)\n```\n\nUse this when the user says things like:\n- *\"Use Squad to build X\"*\n- *\"Set up an AI team for this project\"*\n- *\"Have the Squad coordinator design Y\"*\n- *\"Spawn Squad\"* \u002F *\"Squad, help me with ...\"*\n\n### B) See what Squad commands exist\n\nThe `squad` skill is a categorized catalog of common Squad operations. The coordinator presents it as an interactive menu.\n\nTrigger by natural-language match: `\"squad commands\"`, `\"what can squad do\"`, `\"show me squad options\"`, `\"slash commands\"`, `\"what commands are available\"`.\n\nUse this when the user says things like:\n- *\"What can Squad do?\"*\n- *\"Show me the squad commands\"*\n- *\"squad help\"*\n\n### C) Initialize Squad in a fresh project\n\n`squad init` is a **shell command**, not a tool call. The user runs it in their terminal in a project that has no `.squad\u002F` directory yet.\n\n```bash\nsquad init\n```\n\nDo **not** try to invoke this from inside an existing Copilot session — `.squad\u002F` is already initialized if you're reading this file.\n\n---\n\n## What NOT to do\n\n- ❌ Do not use the menu skill as a substitute for the `Squad` coordinator agent.\n- ❌ Do not assume `\u002Fsquad` is exposed by every host, or universally unsupported; check host discovery and use the natural-language menu fallback.\n- ❌ Do not call `task(agent_type=\"Squad\", …)` for tiny tasks the current agent can handle directly. Squad is for work that needs orchestration; trivial edits do not.\n\n---\n\n## How this skill was discovered\n\nThis repository installs managed help at `.github\u002Fskills\u002Fsquad-help\u002FSKILL.md`.\nDiscovery in a picker, tool or command menu depends on the host's repository-skill\nsupport and settings. This narrow Waza correction is not pristine upstream text;\npreserve its coordinator\u002Fmenu distinction and source-contract regression on upgrade.\n\nIf you removed this skill on purpose, the model will fall back to its own reasoning and may make the lookup mistakes described above.\n\n---\n\n## See also\n\n- `.github\u002Fagents\u002Fsquad.agent.md` — the actual Squad coordinator agent\n- `.github\u002Fskills\u002Fsquad\u002FSKILL.md` — the separate command catalog and interactive menu\n","# Skill: squad-help\n\n> **Quick reference.** If you're reading this because a user said \"use squad\" or \"squad\" or \"set up a squad\", you're in the right place — read on for the correct invocation paths.\n\n---\n\n## Squad coordinator and squad menu skill\n\nThe Squad framework registers a **custom Copilot CLI agent** at `.github\u002Fagents\u002Fsquad.agent.md`. The agent is named **`Squad`** and its description is *\"Your AI team. Describe what you're building, get a team of specialists that live in your repo.\"*\n\nCopilot CLI agents and skills are different things:\n\n| Thing | How to invoke | Example |\n|---|---|---|\n| **Menu skill** | Host skill tool, natural-language match, or exposed skill command | `skill(squad)` when available |\n| **Agent** | `task` tool with `agent_type=\u003Cname>` | `task(name=\"...\", agent_type=\"Squad\", prompt=\"...\")` |\n| **Slash command** | Host-dependent built-in command or exposed user-invocable skill | `\u002Fsquad` when the host exposes the installed menu |\n\nThe `Squad` agent performs coordination; the separate `squad` menu skill lives at\n`.github\u002Fskills\u002Fsquad\u002FSKILL.md` and declares `user-invocable: true`. They are not\ninterchangeable. Slash-command availability is **host-dependent**: use `\u002Fsquad` only\nwhere the host exposes that skill as a command. Otherwise use its natural-language\ntriggers or the host's skill picker\u002Ftool, when available; invoke the coordinator agent\nfor actual orchestration.\n\n---\n\n## How to actually use Squad\n\nPick the path that matches the user's intent:\n\n### A) Invoke the Squad coordinator agent (most common)\n\nThe Squad coordinator orchestrates a team of specialists. It routes work to the right agent, scaffolds a team if none exists, and enforces handoffs.\n\n```text\ntask(\n  name=\"\u003Cshort-task-name>\",\n  agent_type=\"Squad\",\n  prompt=\"\u003Cwhat you want the team to do>\"\n)\n```\n\nUse this when the user says things like:\n- *\"Use Squad to build X\"*\n- *\"Set up an AI team for this project\"*\n- *\"Have the Squad coordinator design Y\"*\n- *\"Spawn Squad\"* \u002F *\"Squad, help me with ...\"*\n\n### B) See what Squad commands exist\n\nThe `squad` skill is a categorized catalog of common Squad operations. The coordinator presents it as an interactive menu.\n\nTrigger by natural-language match: `\"squad commands\"`, `\"what can squad do\"`, `\"show me squad options\"`, `\"slash commands\"`, `\"what commands are available\"`.\n\nUse this when the user says things like:\n- *\"What can Squad do?\"*\n- *\"Show me the squad commands\"*\n- *\"squad help\"*\n\n### C) Initialize Squad in a fresh project\n\n`squad init` is a **shell command**, not a tool call. The user runs it in their terminal in a project that has no `.squad\u002F` directory yet.\n\n```bash\nsquad init\n```\n\nDo **not** try to invoke this from inside an existing Copilot session — `.squad\u002F` is already initialized if you're reading this file.\n\n---\n\n## What NOT to do\n\n- ❌ Do not use the menu skill as a substitute for the `Squad` coordinator agent.\n- ❌ Do not assume `\u002Fsquad` is exposed by every host, or universally unsupported; check host discovery and use the natural-language menu fallback.\n- ❌ Do not call `task(agent_type=\"Squad\", …)` for tiny tasks the current agent can handle directly. Squad is for work that needs orchestration; trivial edits do not.\n\n---\n\n## How this skill was discovered\n\nThis repository installs managed help at `.github\u002Fskills\u002Fsquad-help\u002FSKILL.md`.\nDiscovery in a picker, tool or command menu depends on the host's repository-skill\nsupport and settings. This narrow Waza correction is not pristine upstream text;\npreserve its coordinator\u002Fmenu distinction and source-contract regression on upgrade.\n\nIf you removed this skill on purpose, the model will fall back to its own reasoning and may make the lookup mistakes described above.\n\n---\n\n## See also\n\n- `.github\u002Fagents\u002Fsquad.agent.md` — the actual Squad coordinator agent\n- `.github\u002Fskills\u002Fsquad\u002FSKILL.md` — the separate command catalog and interactive menu\n",{"name":5,"domain":48,"source":49,"confidence":31,"description":7,"allowedTools":50},"squad-onboarding","Squad SDK managed help with a Waza project correction for host-dependent menu invocation.",[],"main","116214a33b5e07766539f64c0ea21521467829bf",".github\u002Fskills\u002Fsquad-help",101,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza","https:\u002F\u002Fmicrosoft.github.io\u002Fwaza\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-13 03:34:47",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add microsoft\u002Fwaza --skill squad-help",{"tool":67,"command":68},"bunx","bunx skills add microsoft\u002Fwaza --skill squad-help",{"tool":70,"command":71},"pnpm","pnpm dlx skills add microsoft\u002Fwaza --skill squad-help","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsquad-help\u002FSKILL.md",true,[],[76,106,132,160,180,193],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":86,"publishedAt":43},"01M6X00A438VG96V20V1VMDHCM","waza-runner","Run evaluations on Agent Skills to measure their effectiveness. \nUSE FOR: \"run skill evals\", \"evaluate my skill\", \"test skill quality\", \n\"check skill triggers\", \"skill compliance check\", \"measure skill performance\",\n\"run evals on [skill-name]\", \"grade skill execution\".\nDO NOT USE FOR: writing skills (use skill-authoring), improving frontmatter \n(use sensei), or general testing unrelated to skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fwaza-runner\u002FSKILL.md",[82,85],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[87,88,28,89,90,91,92,93,94,30,95,96,97,98,99,100,101,102,103,104,105],"waza runner","runner","frontmatter","run","triggers","do","my","general","evals","unrelated","writing skills","my skill","sensei","Test Skill","run evals","performance","writing","testing","authoring",{"skillNo":107,"name":28,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":113,"publishedAt":43},"01M6X003ZZKY5WQ5SWPAQ3MJMS","**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), creating new skills from scratch (use skill-creator), token counting or budget checks (use waza tokens). INVOKES: Copilot SDK executor, mock engine, code\u002Fregex validators. FOR SINGLE OPERATIONS: use waza run directly for a single benchmark.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fskills\u002Fwaza\u002FSKILL.md",[111,112],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[28,90,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,104,129,130,131],"workflow skill","executor","fixture","eval","compare results","model","Evaluation","evaluate skill","code","eval suite","generate","copilot","init","workflow","ai agent","counting","new","skill-creator",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":147,"publishedAt":43},"01M6WZZZHCTPZ8YF9564J3QJVT","waza-interactive","Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fskills\u002Fwaza-interactive\u002FSKILL.md",[138,139,144],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":140,"categoryName":141,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":145,"categoryName":146,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000036","内容创作者",[148,28,149,150,103,104,128,27,151,123,30,105,92,94,95,152,153,154,117,155,156,98,90,157,158,99,159,127],"waza interactive","interactive","tests","general coding","ready","only","failing","work","improve","create","debug","create eval",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":167,"publishedAt":43},"01M6WZZTQR955SVJ02J33DGQYK","code-explainer","Explains code snippets in plain English, breaking down what the code does step by step. Perfect for learning, code reviews, or documentation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fskills\u002Fcode-explainer\u002FSKILL.md",[166],{"categoryNo":140,"categoryName":141,"taxonomyType":142,"taxonomyTypeDesc":143},[168,169,122,170,171,172,30,173,174,175,176,177,178,179],"code explainer","explainer","learning","plain","down","reviews","step by step","english","snippets","what the","plain english","documentation",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":43},"01M6WZZR27J4RE4J10M38ECM26","compatibility-skill","Read fixture status and report whether it is ready.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Finternal\u002Ftestdata\u002Fcompatibility\u002Fv1\u002FSKILL.md",[],[187,188,189,116,152,190,191,192],"compatibility skill","compatibility","it","read","report","status",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":199,"publishedAt":43},"01M6WZZMYWAKWE36WD4PHQK8V2","evidence-judge","Read a supplied report and summarize its recorded status and numeric items.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fexamples\u002Fevidence-judge\u002FSKILL.md",[],[200,201,202,190,191,192,203],"evidence","evidence judge","judge","summarize"]