[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WZWT02YPB3A4RNW1DHKCJ3":3,"skill-same:01M6WZWT02YPB3A4RNW1DHKCJ3":68},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":67},"01M6WZWT02YPB3A4RNW1DHKCJ3","squad",null,"Squad's command catalog and interactive menu. Invoke via \u002Fsquad where the host exposes user-invocable skills as commands, or natural language (\"squad commands\", \"what can squad do\", \"show me squad options\"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.","microsoft\u002Fwaza","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6WZT4PAP160SPCF851532KH",1511,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsquad\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"invoke","cli","coordinator","host","as","commands","upgrade","options","me","natural language","do","show","install","command","model","team","show me","issues","squad commands","2026-11-10 10:12:30",false,"---\nname: squad\ndescription: >-\n  Squad's command catalog and interactive menu. Invoke via \u002Fsquad where the host exposes user-invocable skills as commands, or natural language (\"squad commands\", \"what can squad do\", \"show me squad options\"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.\nuser-invocable: true\nallowedTools: []\n---\n\n## Menu Presentation Rules\n\n**Host-dependent invocation:** `user-invocable: true` declares menu intent, not a guarantee\nthat every host exposes `\u002Fsquad`. Use natural-language triggers or the host skill picker\u002Ftool\nwhen slash invocation is unavailable. This menu is separate from the `Squad` coordinator agent.\n\nWhen the user triggers this skill (via `\u002Fsquad` slash command, \"squad commands\", \"help\", \"what can squad do\", etc.):\n\n1. **Category-level menu first.** Present category names as an `ask_user` choice list:\n   ```\n   ? Squad Commands — pick a category:\n   1. Install & Upgrade\n   2. Team Management\n   3. Issues & PRs\n   4. Plugins & Skills\n   5. Model & Cost\n   6. Sessions & State\n   ```\n2. **Drill-down.** After selection, show operation titles in that category as a second `ask_user` list.\n3. **Direct match skips the menu.** If the user says \"how do I upgrade with state backend,\" match to the specific entry and go straight to argument collection.\n4. **Compact fallback.** If `ask_user` is unavailable, render as a markdown table instead.\n5. **Back \u002F Cancel.** Include \"← Back to categories\" in sub-menus. Include \"Cancel\" in confirmation prompts. Respect \"never mind\" \u002F \"cancel\" at any point.\n\n**Argument collection:** For entries with `args`, iterate the list sequentially. Use `ask_user` with choices when `choices` is provided; free-text prompt otherwise. If the user says \"just do it\" or \"defaults are fine,\" skip remaining args and use their defaults.\n\n**Confirmation template:**\n```\n⚠️ This will {action-description}.\n{what will change}\nProceed? (yes \u002F no)\n```\n\n---\n\n## Install & Upgrade\n\n### Upgrade Squad CLI\n\n- **intent:** upgrade squad, update squad, install latest version, get new version\n- **summary:** Upgrade Squad CLI to the latest version for your channel\n- **action:** shell\n- **command:** squad upgrade\n- **args:**\n  - `state-backend`: Which state backend? | choices: {worktree, git-notes, orphan, two-layer} | default: (keep current)\n- **confirm:** false\n- **platform_caveats:** Requires terminal. In VS Code, open the integrated terminal and run the command directly.\n\n### Initialize Squad\n\n- **intent:** set up squad, initialize squad, create team, start squad in this project\n- **summary:** Scaffold Squad in the current directory (idempotent)\n- **action:** shell\n- **command:** squad init\n- **args:** (none)\n- **confirm:** false\n- **platform_caveats:** Requires terminal. Recommend a standalone terminal for best results.\n\n### Switch State Backend\n\n- **intent:** switch state backend, change state storage, use git-notes, use orphan branch\n- **summary:** Change where Squad stores mutable state (config.json)\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → stateBackend\n- **args:**\n  - `stateBackend`: Which state backend? | choices: {worktree, git-notes, orphan, two-layer} | default: (keep current)\n- **confirm:** true\n- **platform_caveats:** May require migration if switching away from worktree. Show current value and new value before confirming.\n\n---\n\n## Team Management\n\n### Add Team Member\n\n- **intent:** add team member, hire agent, add agent, add developer, recruit\n- **summary:** Add a new agent to the team roster\n- **action:** coordinator\n- **command:** Add Team Member flow (Init Mode \u002F Team Mode)\n- **args:**\n  - `role`: What role should this agent fill? (e.g., Frontend Dev, Backend Dev, QA Engineer)\n  - `name`: Preferred name or casting universe? | default: (auto-cast from active universe)\n- **confirm:** false\n\n### Remove Team Member\n\n- **intent:** remove team member, fire agent, delete agent, remove developer\n- **summary:** Remove an agent and delete their charter and history files\n- **action:** coordinator\n- **command:** Remove Team Member flow\n- **args:**\n  - `member`: Which team member to remove? (name or role)\n- **confirm:** true\n\n### Reassign Roles\n\n- **intent:** reassign role, change role, swap roles, update team member role\n- **summary:** Update a team member's role in team.md and their charter\n- **action:** coordinator\n- **command:** Update team.md roster + charter.md\n- **args:**\n  - `member`: Which team member?\n  - `newRole`: New role?\n- **confirm:** false\n\n### Show Roster\n\n- **intent:** show roster, who is on the team, list team members, show team, capability profile\n- **summary:** Display the current team roster and capability profile\n- **action:** coordinator\n- **command:** Direct Mode — read team.md, answer\n- **args:** (none)\n- **confirm:** false\n\n---\n\n## Issues & PRs\n\n### Connect GitHub Repo\n\n- **intent:** connect github, enable issues, set up issues, link repository, github issues mode\n- **summary:** Connect this project to GitHub Issues via gh auth\n- **action:** coordinator\n- **command:** GitHub Issues Mode (connection flow)\n- **args:** (none)\n- **confirm:** false\n- **platform_caveats:** Requires `gh auth login` to have been run in the terminal.\n\n### Triage Issues\n\n- **intent:** triage issues, review issues, assign issues, label issues\n- **summary:** Run the Lead triage flow on open GitHub issues\n- **action:** coordinator\n- **command:** GitHub Issues Mode → Lead triage\n- **args:** (none)\n- **confirm:** false\n\n### Activate Ralph\n\n- **intent:** activate ralph, start ralph, ralph go, start work monitor, start auto-work\n- **summary:** Activate Ralph — Work Monitor — to pick up and run queued issues\n- **action:** coordinator\n- **command:** Ralph — Work Monitor triggers\n- **args:** (none)\n- **confirm:** false\n\n### Set Ralph Polling Interval\n\n- **intent:** set ralph interval, change ralph timing, how often does ralph check, ralph every N minutes\n- **summary:** Tell Ralph how frequently to poll for new work\n- **action:** coordinator\n- **command:** Ralph trigger: \"Ralph, check every N minutes\"\n- **args:**\n  - `interval`: How often should Ralph poll? (in minutes) | default: 10\n- **confirm:** false\n\n### Start Squad Watch\n\n- **intent:** start watch, squad watch, monitor issues, watch for issues, auto-triage\n- **summary:** Start squad watch to continuously poll and triage issues\n- **action:** shell\n- **command:** squad watch\n- **args:**\n  - `interval`: Poll interval in minutes | default: 10\n- **confirm:** false\n- **platform_caveats:** CLI-only — long-running foreground process. Not viable in VS Code without an integrated terminal. Run: `squad watch --interval {n}` in your terminal.\n\n---\n\n## Plugins & Skills\n\n### Browse Plugin Marketplace\n\n- **intent:** browse plugins, explore plugins, what plugins are available, plugin marketplace\n- **summary:** Browse available plugins in the Squad marketplace\n- **action:** shell\n- **command:** squad plugin marketplace browse\n- **args:**\n  - `name`: Plugin name to search for | default: (browse all)\n- **confirm:** false\n\n### Add Marketplace Plugin\n\n- **intent:** add plugin, install plugin, get plugin from marketplace\n- **summary:** Add a plugin from the marketplace to this Squad\n- **action:** shell\n- **command:** squad plugin marketplace add\n- **args:**\n  - `plugin`: Plugin owner\u002Frepo (e.g., owner\u002Fplugin-name)\n- **confirm:** false\n\n### Remove Marketplace Plugin\n\n- **intent:** remove plugin, uninstall plugin, delete plugin\n- **summary:** Remove an installed marketplace plugin\n- **action:** shell\n- **command:** squad plugin marketplace remove\n- **args:**\n  - `name`: Plugin name to remove\n- **confirm:** true\n\n### List Marketplace Plugins\n\n- **intent:** list plugins, show installed plugins, what plugins do I have\n- **summary:** List all plugins registered in this Squad\n- **action:** shell\n- **command:** squad plugin marketplace list\n- **args:** (none)\n- **confirm:** false\n\n### List Installed Skills\n\n- **intent:** list skills, show skills, what skills are installed, skill catalog\n- **summary:** List all skills installed in .squad\u002Fskills\u002F and .github\u002Fskills\u002F\n- **action:** coordinator\n- **command:** Direct Mode — list .squad\u002Fskills\u002F and .github\u002Fskills\u002F directories\n- **args:** (none)\n- **confirm:** false\n\n---\n\n## Model & Cost\n\n### Set Default Model\n\n- **intent:** set default model, change model, use gpt, use claude, switch model\n- **summary:** Set the default model for all agents in config.json\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → defaultModel\n- **args:**\n  - `model`: Model name (e.g., gpt-5.6-luna, claude-sonnet-4.5, gpt-5.3-codex)\n- **confirm:** false\n\n### Override Per-Agent Model\n\n- **intent:** set model for agent, agent model override, use different model for one agent\n- **summary:** Set a model override for a specific agent in config.json\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → agentModelOverrides.{agentName}\n- **args:**\n  - `agent`: Agent name (must match name in team.md)\n  - `model`: Model name (e.g., gpt-5.6-luna, claude-sonnet-4.5)\n- **confirm:** false\n\n### Clear Model Preference\n\n- **intent:** clear model, reset model, remove model preference, use default model\n- **summary:** Remove a model override from config.json (reverts to system default)\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → remove defaultModel or agentModelOverrides.{agentName}\n- **args:**\n  - `scope`: Clear default or a specific agent? | choices: {default model, specific agent} | default: default model\n  - `agent`: Agent name (only if scope = specific agent)\n- **confirm:** false\n\n---\n\n## Sessions & State\n\n### Catch-Up Summary\n\n- **intent:** catch me up, what happened, status, what did the team do, session summary\n- **summary:** Summarize recent agent activity and key decisions\n- **action:** coordinator\n- **command:** Session catch-up flow (lazy scan)\n- **args:** (none)\n- **confirm:** false\n\n### Show Recent Decisions\n\n- **intent:** show decisions, recent decisions, what decisions were made, decision log\n- **summary:** Display recent entries from .squad\u002Fdecisions.md\n- **action:** coordinator\n- **command:** Direct Mode — read decisions.md, answer\n- **args:** (none)\n- **confirm:** false\n\n### Archive Old Decisions\n\n- **intent:** archive decisions, clean up decisions, move old decisions, compact decisions\n- **summary:** Move old decisions from decisions.md to decisions-archive.md\n- **action:** coordinator\n- **command:** Move entries older than threshold from .squad\u002Fdecisions.md → .squad\u002Fdecisions-archive.md\n- **args:**\n  - `olderThan`: Archive decisions older than how many days? | default: 30\n- **confirm:** true\n\n### Summarize Agent History\n\n- **intent:** summarize history, what did agent do, agent history, compress history\n- **summary:** Spawn an agent to summarize and compress a team member's history file\n- **action:** coordinator\n- **command:** Spawn agent with history.md summarization task\n- **args:**\n  - `member`: Which team member's history to summarize?\n- **confirm:** false\n","## Menu Presentation Rules\n\n**Host-dependent invocation:** `user-invocable: true` declares menu intent, not a guarantee\nthat every host exposes `\u002Fsquad`. Use natural-language triggers or the host skill picker\u002Ftool\nwhen slash invocation is unavailable. This menu is separate from the `Squad` coordinator agent.\n\nWhen the user triggers this skill (via `\u002Fsquad` slash command, \"squad commands\", \"help\", \"what can squad do\", etc.):\n\n1. **Category-level menu first.** Present category names as an `ask_user` choice list:\n   ```\n   ? Squad Commands — pick a category:\n   1. Install & Upgrade\n   2. Team Management\n   3. Issues & PRs\n   4. Plugins & Skills\n   5. Model & Cost\n   6. Sessions & State\n   ```\n2. **Drill-down.** After selection, show operation titles in that category as a second `ask_user` list.\n3. **Direct match skips the menu.** If the user says \"how do I upgrade with state backend,\" match to the specific entry and go straight to argument collection.\n4. **Compact fallback.** If `ask_user` is unavailable, render as a markdown table instead.\n5. **Back \u002F Cancel.** Include \"← Back to categories\" in sub-menus. Include \"Cancel\" in confirmation prompts. Respect \"never mind\" \u002F \"cancel\" at any point.\n\n**Argument collection:** For entries with `args`, iterate the list sequentially. Use `ask_user` with choices when `choices` is provided; free-text prompt otherwise. If the user says \"just do it\" or \"defaults are fine,\" skip remaining args and use their defaults.\n\n**Confirmation template:**\n```\n⚠️ This will {action-description}.\n{what will change}\nProceed? (yes \u002F no)\n```\n\n---\n\n## Install & Upgrade\n\n### Upgrade Squad CLI\n\n- **intent:** upgrade squad, update squad, install latest version, get new version\n- **summary:** Upgrade Squad CLI to the latest version for your channel\n- **action:** shell\n- **command:** squad upgrade\n- **args:**\n  - `state-backend`: Which state backend? | choices: {worktree, git-notes, orphan, two-layer} | default: (keep current)\n- **confirm:** false\n- **platform_caveats:** Requires terminal. In VS Code, open the integrated terminal and run the command directly.\n\n### Initialize Squad\n\n- **intent:** set up squad, initialize squad, create team, start squad in this project\n- **summary:** Scaffold Squad in the current directory (idempotent)\n- **action:** shell\n- **command:** squad init\n- **args:** (none)\n- **confirm:** false\n- **platform_caveats:** Requires terminal. Recommend a standalone terminal for best results.\n\n### Switch State Backend\n\n- **intent:** switch state backend, change state storage, use git-notes, use orphan branch\n- **summary:** Change where Squad stores mutable state (config.json)\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → stateBackend\n- **args:**\n  - `stateBackend`: Which state backend? | choices: {worktree, git-notes, orphan, two-layer} | default: (keep current)\n- **confirm:** true\n- **platform_caveats:** May require migration if switching away from worktree. Show current value and new value before confirming.\n\n---\n\n## Team Management\n\n### Add Team Member\n\n- **intent:** add team member, hire agent, add agent, add developer, recruit\n- **summary:** Add a new agent to the team roster\n- **action:** coordinator\n- **command:** Add Team Member flow (Init Mode \u002F Team Mode)\n- **args:**\n  - `role`: What role should this agent fill? (e.g., Frontend Dev, Backend Dev, QA Engineer)\n  - `name`: Preferred name or casting universe? | default: (auto-cast from active universe)\n- **confirm:** false\n\n### Remove Team Member\n\n- **intent:** remove team member, fire agent, delete agent, remove developer\n- **summary:** Remove an agent and delete their charter and history files\n- **action:** coordinator\n- **command:** Remove Team Member flow\n- **args:**\n  - `member`: Which team member to remove? (name or role)\n- **confirm:** true\n\n### Reassign Roles\n\n- **intent:** reassign role, change role, swap roles, update team member role\n- **summary:** Update a team member's role in team.md and their charter\n- **action:** coordinator\n- **command:** Update team.md roster + charter.md\n- **args:**\n  - `member`: Which team member?\n  - `newRole`: New role?\n- **confirm:** false\n\n### Show Roster\n\n- **intent:** show roster, who is on the team, list team members, show team, capability profile\n- **summary:** Display the current team roster and capability profile\n- **action:** coordinator\n- **command:** Direct Mode — read team.md, answer\n- **args:** (none)\n- **confirm:** false\n\n---\n\n## Issues & PRs\n\n### Connect GitHub Repo\n\n- **intent:** connect github, enable issues, set up issues, link repository, github issues mode\n- **summary:** Connect this project to GitHub Issues via gh auth\n- **action:** coordinator\n- **command:** GitHub Issues Mode (connection flow)\n- **args:** (none)\n- **confirm:** false\n- **platform_caveats:** Requires `gh auth login` to have been run in the terminal.\n\n### Triage Issues\n\n- **intent:** triage issues, review issues, assign issues, label issues\n- **summary:** Run the Lead triage flow on open GitHub issues\n- **action:** coordinator\n- **command:** GitHub Issues Mode → Lead triage\n- **args:** (none)\n- **confirm:** false\n\n### Activate Ralph\n\n- **intent:** activate ralph, start ralph, ralph go, start work monitor, start auto-work\n- **summary:** Activate Ralph — Work Monitor — to pick up and run queued issues\n- **action:** coordinator\n- **command:** Ralph — Work Monitor triggers\n- **args:** (none)\n- **confirm:** false\n\n### Set Ralph Polling Interval\n\n- **intent:** set ralph interval, change ralph timing, how often does ralph check, ralph every N minutes\n- **summary:** Tell Ralph how frequently to poll for new work\n- **action:** coordinator\n- **command:** Ralph trigger: \"Ralph, check every N minutes\"\n- **args:**\n  - `interval`: How often should Ralph poll? (in minutes) | default: 10\n- **confirm:** false\n\n### Start Squad Watch\n\n- **intent:** start watch, squad watch, monitor issues, watch for issues, auto-triage\n- **summary:** Start squad watch to continuously poll and triage issues\n- **action:** shell\n- **command:** squad watch\n- **args:**\n  - `interval`: Poll interval in minutes | default: 10\n- **confirm:** false\n- **platform_caveats:** CLI-only — long-running foreground process. Not viable in VS Code without an integrated terminal. Run: `squad watch --interval {n}` in your terminal.\n\n---\n\n## Plugins & Skills\n\n### Browse Plugin Marketplace\n\n- **intent:** browse plugins, explore plugins, what plugins are available, plugin marketplace\n- **summary:** Browse available plugins in the Squad marketplace\n- **action:** shell\n- **command:** squad plugin marketplace browse\n- **args:**\n  - `name`: Plugin name to search for | default: (browse all)\n- **confirm:** false\n\n### Add Marketplace Plugin\n\n- **intent:** add plugin, install plugin, get plugin from marketplace\n- **summary:** Add a plugin from the marketplace to this Squad\n- **action:** shell\n- **command:** squad plugin marketplace add\n- **args:**\n  - `plugin`: Plugin owner\u002Frepo (e.g., owner\u002Fplugin-name)\n- **confirm:** false\n\n### Remove Marketplace Plugin\n\n- **intent:** remove plugin, uninstall plugin, delete plugin\n- **summary:** Remove an installed marketplace plugin\n- **action:** shell\n- **command:** squad plugin marketplace remove\n- **args:**\n  - `name`: Plugin name to remove\n- **confirm:** true\n\n### List Marketplace Plugins\n\n- **intent:** list plugins, show installed plugins, what plugins do I have\n- **summary:** List all plugins registered in this Squad\n- **action:** shell\n- **command:** squad plugin marketplace list\n- **args:** (none)\n- **confirm:** false\n\n### List Installed Skills\n\n- **intent:** list skills, show skills, what skills are installed, skill catalog\n- **summary:** List all skills installed in .squad\u002Fskills\u002F and .github\u002Fskills\u002F\n- **action:** coordinator\n- **command:** Direct Mode — list .squad\u002Fskills\u002F and .github\u002Fskills\u002F directories\n- **args:** (none)\n- **confirm:** false\n\n---\n\n## Model & Cost\n\n### Set Default Model\n\n- **intent:** set default model, change model, use gpt, use claude, switch model\n- **summary:** Set the default model for all agents in config.json\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → defaultModel\n- **args:**\n  - `model`: Model name (e.g., gpt-5.6-luna, claude-sonnet-4.5, gpt-5.3-codex)\n- **confirm:** false\n\n### Override Per-Agent Model\n\n- **intent:** set model for agent, agent model override, use different model for one agent\n- **summary:** Set a model override for a specific agent in config.json\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → agentModelOverrides.{agentName}\n- **args:**\n  - `agent`: Agent name (must match name in team.md)\n  - `model`: Model name (e.g., gpt-5.6-luna, claude-sonnet-4.5)\n- **confirm:** false\n\n### Clear Model Preference\n\n- **intent:** clear model, reset model, remove model preference, use default model\n- **summary:** Remove a model override from config.json (reverts to system default)\n- **action:** file-edit\n- **command:** .squad\u002Fconfig.json → remove defaultModel or agentModelOverrides.{agentName}\n- **args:**\n  - `scope`: Clear default or a specific agent? | choices: {default model, specific agent} | default: default model\n  - `agent`: Agent name (only if scope = specific agent)\n- **confirm:** false\n\n---\n\n## Sessions & State\n\n### Catch-Up Summary\n\n- **intent:** catch me up, what happened, status, what did the team do, session summary\n- **summary:** Summarize recent agent activity and key decisions\n- **action:** coordinator\n- **command:** Session catch-up flow (lazy scan)\n- **args:** (none)\n- **confirm:** false\n\n### Show Recent Decisions\n\n- **intent:** show decisions, recent decisions, what decisions were made, decision log\n- **summary:** Display recent entries from .squad\u002Fdecisions.md\n- **action:** coordinator\n- **command:** Direct Mode — read decisions.md, answer\n- **args:** (none)\n- **confirm:** false\n\n### Archive Old Decisions\n\n- **intent:** archive decisions, clean up decisions, move old decisions, compact decisions\n- **summary:** Move old decisions from decisions.md to decisions-archive.md\n- **action:** coordinator\n- **command:** Move entries older than threshold from .squad\u002Fdecisions.md → .squad\u002Fdecisions-archive.md\n- **args:**\n  - `olderThan`: Archive decisions older than how many days? | default: 30\n- **confirm:** true\n\n### Summarize Agent History\n\n- **intent:** summarize history, what did agent do, agent history, compress history\n- **summary:** Spawn an agent to summarize and compress a team member's history file\n- **action:** coordinator\n- **command:** Spawn agent with history.md summarization task\n- **args:**\n  - `member`: Which team member's history to summarize?\n- **confirm:** false\n",{"name":5,"description":7,"allowedTools":43,"user-invocable":44},[],true,"main","116214a33b5e07766539f64c0ea21521467829bf",".github\u002Fskills\u002Fsquad",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","2026-11-15 04:18:35",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":44},[57,60,63],{"tool":58,"command":59},"npx","npx skills add microsoft\u002Fwaza --skill squad",{"tool":61,"command":62},"bunx","bunx skills add microsoft\u002Fwaza --skill squad",{"tool":64,"command":65},"pnpm","pnpm dlx skills add microsoft\u002Fwaza --skill squad","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsquad\u002FSKILL.md",[],[69,104,129,158,178,191],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":83,"publishedAt":38},"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",[75,80],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":81,"categoryName":82,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发",[84,85,86,87,88,89,29,90,91,92,93,94,95,96,97,98,99,100,101,102,103],"waza runner","runner","waza","frontmatter","run","triggers","my","general","for","evals","unrelated","writing skills","my skill","sensei","Test Skill","run evals","performance","writing","testing","authoring",{"skillNo":105,"name":86,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":111,"publishedAt":38},"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",[109,110],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":81,"categoryName":82,"taxonomyType":78,"taxonomyTypeDesc":79},[86,88,112,113,114,115,116,33,117,118,119,120,121,122,123,124,125,102,126,127,128],"workflow skill","executor","fixture","eval","compare results","Evaluation","evaluate skill","code","eval suite","generate","copilot","init","workflow","ai agent","counting","new","skill-creator",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":144,"publishedAt":38},"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",[135,136,141],{"categoryNo":81,"categoryName":82,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":137,"categoryName":138,"taxonomyType":139,"taxonomyTypeDesc":140},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":142,"categoryName":143,"taxonomyType":139,"taxonomyTypeDesc":140},"01JBSEEDCAT000000000000036","内容创作者",[145,86,146,147,101,102,125,148,149,120,92,103,29,91,93,150,151,152,115,153,154,96,88,155,156,97,157,124],"waza interactive","interactive","tests","use","general coding","ready","only","failing","work","improve","create","debug","create eval",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":38},"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",[164],{"categoryNo":137,"categoryName":138,"taxonomyType":139,"taxonomyTypeDesc":140},[166,167,119,168,169,170,92,171,172,173,174,175,176,177],"code explainer","explainer","learning","plain","down","reviews","step by step","english","snippets","what the","plain english","documentation",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":38},"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",[],[185,186,187,114,150,188,189,190],"compatibility skill","compatibility","it","read","report","status",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":38},"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",[],[198,199,200,188,189,190,201],"evidence","evidence judge","judge","summarize"]