[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WZTV7WJAMQ5680D4PD8YSB":3,"skill-same:01M6WZTV7WJAMQ5680D4PD8YSB":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6WZTV7WJAMQ5680D4PD8YSB","coordinator-init-mode",null,"The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad\u002F scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad\u002Fteam.md exists.","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\u002Fcoordinator-init-mode\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"coordinator init mode","init mode","init","mode","coordinator","when","phase","initialization","for","checker","with","complete","project","scaffolding","files","repo","reviewer","ralph","wait for","team","2026-11-10 10:12:30",false,"---\nname: \"coordinator-init-mode\"\ndescription: \"The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad\u002F scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad\u002Fteam.md exists.\"\nallowedTools: []\nconfidence: high\ndomain: squad-internals\nsource: \"Extracted from squad.agent.md (bradygaster\u002Fsquad#1308), with Waza project overrides for paired casting initialization and governance-aligned reviewer seeding.\"\n---\n\n> **Load this skill when:** you detect that no `.squad\u002Fteam.md` exists in the resolved team root — that means this is a fresh repo or a repo that has never been squadified, and Init Mode is the right path. The short stub in `squad.agent.md` tells you to load this skill; the full two-phase protocol lives here.\n>\n> **⚠️ Eager-execution exception:** Init Mode is the ONE exception to the eager-execution \u002F parallel-fan-out doctrine. Phase 1 MUST end with a user confirmation before any file is created. Do not bypass.\n\n## Phase 1: Propose the Team\n\nNo team exists yet. **Propose one — but DO NOT create any files until the user confirms.**\n\n1. **Identify the user.** Run `git config user.name` to learn who you're working with. Use their name in conversation (e.g., *\"Hey {user}, what are you building?\"*). Store their name (NOT email) in `team.md` under Project Context. **Never read or store `git config user.email`** — email addresses are PII and must not be written to committed files.\n2. Ask: *\"What are you building? (language, stack, what it does)\"*\n3. **Cast the team.** Before proposing names, run the Casting & Persistent Naming algorithm (see the canonical Casting reference at `.squad\u002Ftemplates\u002Fcasting-reference.md`):\n   - Determine team size: pick **4–5 cast (user-domain) agents**, then add the **4 always-on built-ins** (Scribe + Ralph + Rai + Fact Checker — see their dedicated sections in `squad.agent.md`). A typical fresh squad has **8–9 total roster entries**, not 4–5.\n   - Determine assignment shape from the user's project description.\n   - Derive resonance signals from the session and repo context.\n   - Select a universe. Allocate character names from that universe.\n   - Scribe is always \"Scribe\" — exempt from casting.\n   - Ralph is always \"Ralph\" — exempt from casting.\n   - Rai is always \"Rai\" — exempt from casting.\n   - Fact Checker is always \"Fact Checker\" — exempt from casting (same pattern as Scribe \u002F Ralph \u002F Rai).\n4. Propose the team with their cast names. Example (names will vary per cast):\n\n```\n?️  {CastName1}  — Lead          Scope, decisions, code review\n⚛️  {CastName2}  — Frontend Dev  React, UI, components\n?  {CastName3}  — Backend Dev   APIs, database, services\n?  {CastName4}  — Tester        Tests, quality, edge cases\n?  Scribe       — (silent)      Memory, decisions, session logs\n?  Ralph        — (monitor)     Work queue, backlog, keep-alive\n?️  Rai         — (background)  RAI awareness, content safety\n?  Fact Checker — (verifier)    Verification + Devil's Advocate\n```\n\n5. Use the `ask_user` tool to confirm the roster. Provide choices so the user sees a selectable menu.\n\n   The `question` must be **self-contained** because the client may render the blocking input request without the assistant text that preceded it.\n\n   The `question` must reuse every roster line from the exact proposal emitted in step 4, in the same order. Do not regenerate, summarize, truncate, omit, or replace any roster row with an ellipsis. Every proposed member must appear with their emoji, cast name, role, and concise responsibility\u002Fscope — including all four always-on built-ins (Scribe, Ralph, Rai, Fact Checker).\n\n   Shape:\n\n   ```\n   Confirm this team (universe: {ActualUniverse}):\n\n   {Every roster line from step 4, copied in full and in order}\n\n   Look right?\n   ```\n\n   Never use a bare \"Look right?\" question and never rely on preceding assistant output to identify the team being confirmed.\n\n   - **choices:** `[\"Yes, hire this team\", \"Add someone\", \"Change a role\"]`\n\n**⚠️ STOP. Your response ENDS here. Do NOT proceed to Phase 2. Do NOT create any files or directories. Wait for the user's reply.**\n\n---\n\n## Phase 2: Create the Team\n\n**Trigger:** The user replied to Phase 1 with confirmation (\"yes\", \"looks good\", or similar affirmative), OR the user's reply to Phase 1 is a task (treat as implicit \"yes\").\n\n> If the user said \"add someone\" or \"change a role,\" go back to Phase 1 step 3 and re-propose. **Do NOT enter Phase 2 until the user confirms.**\n\n6. Create the `.squad\u002F` directory structure (see `.squad\u002Ftemplates\u002F` for format guides or use the standard structure: `team.md`, `routing.md`, `ceremonies.md`, `decisions.md`, `decisions\u002Finbox\u002F`, `casting\u002F`, `agents\u002F`, `orchestration-log\u002F`, `skills\u002F`, `log\u002F`, `rai\u002F`).\n\n**Casting state initialization — Waza project repair:** Begin with a genuinely empty new target. Use `.squad\u002Fcasting-transactions.md`'s actual locked SDK writer to initialize schema-v1 registry\u002Fhistory and their commit manifest together, including complete provenance and the first assignment snapshot; only then initialize policy config exclusively from approved defaults. Do not create either casting JSON file independently or copy legacy examples into live state. On non-local backends, require an equivalent atomic operation or stop; generic per-file state writes are not sufficient.\n\nInitialization requires a genuinely empty new target. The SDK prepares\u002Fvalidates\nexisting files before the callback, so it cannot normalize v0.10 files left in\nplace. Known frozen v0.10 state requires the guide's approved, quiesced\narchive-and-initialize procedure with disclosed downtime and continuity limits;\nnever infer legacy status from a managed-pair validation failure.\n\n**Seeding:** Create initial `history.md` context only where the agent's charter permits that output; Rai and Fact Checker do not create histories. Agent folder names are the cast name in lowercase (e.g., `.squad\u002Fagents\u002Fripley\u002F`). The Scribe's charter includes maintaining `decisions.md` and cross-agent context sharing. `.squad\u002Fagents\u002Frai\u002Fcharter.md` is seeded from `Rai-charter.md`, and `.squad\u002Frai\u002Fpolicy.md` is seeded from `rai-policy.md`. `.squad\u002Fagents\u002Ffact-checker\u002Fcharter.md` is seeded from `fact-checker-charter.md` and `.squad\u002Ffact-checker\u002Fpolicy.md` is seeded from `fact-checker-policy.md`.\n\n**Waza reviewer seeding override (Squad only):** Use the project-repaired templates\nunder `.squad\u002Ftemplates\u002F`, not pristine upstream replacements. Seeded review policy\nmust agree with `.squad\u002Fgovernance.md` and the support charters: rejection includes\nconcrete counter-evidence, a different qualified revision owner, and focused\nrereview rather than author\u002Frejecting-gate pairing. Ordinary Copilot work does\nnot enter Squad Init Mode or acquire these coordination rules.\nAfter successful focused rereview of the independently corrected revision, the selected\ngate may issue approval\u002FPASS, not native repository approval, merge or publishing authority.\nCharter output\u002Fpersistence restrictions take precedence over generic history, audit-trail or\ndecision-inbox instructions. Return findings in the current review response; only an authorized\ncoordinator or Scribe handles required persistence under the current state contract.\n\n**Team.md structure:** `team.md` MUST contain a section titled exactly `## Members` (not \"## Team Roster\" or other variations) containing the roster table. This header is hard-coded in GitHub workflows (`squad-heartbeat.yml`, `squad-issue-assign.yml`, `squad-triage.yml`, `sync-squad-labels.yml`) for label automation. If the header is missing or titled differently, label routing breaks.\n\n**Merge driver for append-only files:** Create or update `.gitattributes` at the repo root to enable conflict-free merging of `.squad\u002F` state across branches:\n\n```\n.squad\u002Fdecisions.md merge=union\n.squad\u002Fagents\u002F*\u002Fhistory.md merge=union\n.squad\u002Flog\u002F** merge=union\n.squad\u002Forchestration-log\u002F** merge=union\n.squad\u002Frai\u002Faudit-trail.md merge=union\n```\n\nThe `union` merge driver keeps all lines from both sides, which is correct for append-only files. This makes worktree-local strategy work seamlessly when branches merge — decisions, memories, and logs from all branches combine automatically.\n\n7. Say: *\"✅ Team hired. Try: '{FirstCastName}, set up the project structure'\"*\n\n8. **Post-setup input sources** (optional — ask after team is created, not during casting):\n   - **PRD\u002Fspec:** *\"Do you have a PRD or spec document? (file path, paste it, or skip)\"* → If provided, follow PRD Mode flow.\n   - **GitHub issues:** *\"Is there a GitHub repo with issues I should pull from? (owner\u002Frepo, or skip)\"* → If provided, follow GitHub Issues Mode flow.\n   - **Waza membership policy:** Propose AI members only under `.squad\u002Fgovernance.md`; do not add human members or human issue\u002Fimplementation handoffs. Preserve the project owner\u002Frequester and required repository approvals.\n   - **Copilot agent:** *\"Want to include @copilot? It can pick up issues autonomously. (yes\u002Fno)\"* → If yes, follow Copilot Coding Agent Member section and ask about auto-assignment.\n   - These are additive. **Don't block** — if the user skips or gives a task instead, proceed immediately.\n","> **Load this skill when:** you detect that no `.squad\u002Fteam.md` exists in the resolved team root — that means this is a fresh repo or a repo that has never been squadified, and Init Mode is the right path. The short stub in `squad.agent.md` tells you to load this skill; the full two-phase protocol lives here.\n>\n> **⚠️ Eager-execution exception:** Init Mode is the ONE exception to the eager-execution \u002F parallel-fan-out doctrine. Phase 1 MUST end with a user confirmation before any file is created. Do not bypass.\n\n## Phase 1: Propose the Team\n\nNo team exists yet. **Propose one — but DO NOT create any files until the user confirms.**\n\n1. **Identify the user.** Run `git config user.name` to learn who you're working with. Use their name in conversation (e.g., *\"Hey {user}, what are you building?\"*). Store their name (NOT email) in `team.md` under Project Context. **Never read or store `git config user.email`** — email addresses are PII and must not be written to committed files.\n2. Ask: *\"What are you building? (language, stack, what it does)\"*\n3. **Cast the team.** Before proposing names, run the Casting & Persistent Naming algorithm (see the canonical Casting reference at `.squad\u002Ftemplates\u002Fcasting-reference.md`):\n   - Determine team size: pick **4–5 cast (user-domain) agents**, then add the **4 always-on built-ins** (Scribe + Ralph + Rai + Fact Checker — see their dedicated sections in `squad.agent.md`). A typical fresh squad has **8–9 total roster entries**, not 4–5.\n   - Determine assignment shape from the user's project description.\n   - Derive resonance signals from the session and repo context.\n   - Select a universe. Allocate character names from that universe.\n   - Scribe is always \"Scribe\" — exempt from casting.\n   - Ralph is always \"Ralph\" — exempt from casting.\n   - Rai is always \"Rai\" — exempt from casting.\n   - Fact Checker is always \"Fact Checker\" — exempt from casting (same pattern as Scribe \u002F Ralph \u002F Rai).\n4. Propose the team with their cast names. Example (names will vary per cast):\n\n```\n?️  {CastName1}  — Lead          Scope, decisions, code review\n⚛️  {CastName2}  — Frontend Dev  React, UI, components\n?  {CastName3}  — Backend Dev   APIs, database, services\n?  {CastName4}  — Tester        Tests, quality, edge cases\n?  Scribe       — (silent)      Memory, decisions, session logs\n?  Ralph        — (monitor)     Work queue, backlog, keep-alive\n?️  Rai         — (background)  RAI awareness, content safety\n?  Fact Checker — (verifier)    Verification + Devil's Advocate\n```\n\n5. Use the `ask_user` tool to confirm the roster. Provide choices so the user sees a selectable menu.\n\n   The `question` must be **self-contained** because the client may render the blocking input request without the assistant text that preceded it.\n\n   The `question` must reuse every roster line from the exact proposal emitted in step 4, in the same order. Do not regenerate, summarize, truncate, omit, or replace any roster row with an ellipsis. Every proposed member must appear with their emoji, cast name, role, and concise responsibility\u002Fscope — including all four always-on built-ins (Scribe, Ralph, Rai, Fact Checker).\n\n   Shape:\n\n   ```\n   Confirm this team (universe: {ActualUniverse}):\n\n   {Every roster line from step 4, copied in full and in order}\n\n   Look right?\n   ```\n\n   Never use a bare \"Look right?\" question and never rely on preceding assistant output to identify the team being confirmed.\n\n   - **choices:** `[\"Yes, hire this team\", \"Add someone\", \"Change a role\"]`\n\n**⚠️ STOP. Your response ENDS here. Do NOT proceed to Phase 2. Do NOT create any files or directories. Wait for the user's reply.**\n\n---\n\n## Phase 2: Create the Team\n\n**Trigger:** The user replied to Phase 1 with confirmation (\"yes\", \"looks good\", or similar affirmative), OR the user's reply to Phase 1 is a task (treat as implicit \"yes\").\n\n> If the user said \"add someone\" or \"change a role,\" go back to Phase 1 step 3 and re-propose. **Do NOT enter Phase 2 until the user confirms.**\n\n6. Create the `.squad\u002F` directory structure (see `.squad\u002Ftemplates\u002F` for format guides or use the standard structure: `team.md`, `routing.md`, `ceremonies.md`, `decisions.md`, `decisions\u002Finbox\u002F`, `casting\u002F`, `agents\u002F`, `orchestration-log\u002F`, `skills\u002F`, `log\u002F`, `rai\u002F`).\n\n**Casting state initialization — Waza project repair:** Begin with a genuinely empty new target. Use `.squad\u002Fcasting-transactions.md`'s actual locked SDK writer to initialize schema-v1 registry\u002Fhistory and their commit manifest together, including complete provenance and the first assignment snapshot; only then initialize policy config exclusively from approved defaults. Do not create either casting JSON file independently or copy legacy examples into live state. On non-local backends, require an equivalent atomic operation or stop; generic per-file state writes are not sufficient.\n\nInitialization requires a genuinely empty new target. The SDK prepares\u002Fvalidates\nexisting files before the callback, so it cannot normalize v0.10 files left in\nplace. Known frozen v0.10 state requires the guide's approved, quiesced\narchive-and-initialize procedure with disclosed downtime and continuity limits;\nnever infer legacy status from a managed-pair validation failure.\n\n**Seeding:** Create initial `history.md` context only where the agent's charter permits that output; Rai and Fact Checker do not create histories. Agent folder names are the cast name in lowercase (e.g., `.squad\u002Fagents\u002Fripley\u002F`). The Scribe's charter includes maintaining `decisions.md` and cross-agent context sharing. `.squad\u002Fagents\u002Frai\u002Fcharter.md` is seeded from `Rai-charter.md`, and `.squad\u002Frai\u002Fpolicy.md` is seeded from `rai-policy.md`. `.squad\u002Fagents\u002Ffact-checker\u002Fcharter.md` is seeded from `fact-checker-charter.md` and `.squad\u002Ffact-checker\u002Fpolicy.md` is seeded from `fact-checker-policy.md`.\n\n**Waza reviewer seeding override (Squad only):** Use the project-repaired templates\nunder `.squad\u002Ftemplates\u002F`, not pristine upstream replacements. Seeded review policy\nmust agree with `.squad\u002Fgovernance.md` and the support charters: rejection includes\nconcrete counter-evidence, a different qualified revision owner, and focused\nrereview rather than author\u002Frejecting-gate pairing. Ordinary Copilot work does\nnot enter Squad Init Mode or acquire these coordination rules.\nAfter successful focused rereview of the independently corrected revision, the selected\ngate may issue approval\u002FPASS, not native repository approval, merge or publishing authority.\nCharter output\u002Fpersistence restrictions take precedence over generic history, audit-trail or\ndecision-inbox instructions. Return findings in the current review response; only an authorized\ncoordinator or Scribe handles required persistence under the current state contract.\n\n**Team.md structure:** `team.md` MUST contain a section titled exactly `## Members` (not \"## Team Roster\" or other variations) containing the roster table. This header is hard-coded in GitHub workflows (`squad-heartbeat.yml`, `squad-issue-assign.yml`, `squad-triage.yml`, `sync-squad-labels.yml`) for label automation. If the header is missing or titled differently, label routing breaks.\n\n**Merge driver for append-only files:** Create or update `.gitattributes` at the repo root to enable conflict-free merging of `.squad\u002F` state across branches:\n\n```\n.squad\u002Fdecisions.md merge=union\n.squad\u002Fagents\u002F*\u002Fhistory.md merge=union\n.squad\u002Flog\u002F** merge=union\n.squad\u002Forchestration-log\u002F** merge=union\n.squad\u002Frai\u002Faudit-trail.md merge=union\n```\n\nThe `union` merge driver keeps all lines from both sides, which is correct for append-only files. This makes worktree-local strategy work seamlessly when branches merge — decisions, memories, and logs from all branches combine automatically.\n\n7. Say: *\"✅ Team hired. Try: '{FirstCastName}, set up the project structure'\"*\n\n8. **Post-setup input sources** (optional — ask after team is created, not during casting):\n   - **PRD\u002Fspec:** *\"Do you have a PRD or spec document? (file path, paste it, or skip)\"* → If provided, follow PRD Mode flow.\n   - **GitHub issues:** *\"Is there a GitHub repo with issues I should pull from? (owner\u002Frepo, or skip)\"* → If provided, follow GitHub Issues Mode flow.\n   - **Waza membership policy:** Propose AI members only under `.squad\u002Fgovernance.md`; do not add human members or human issue\u002Fimplementation handoffs. Preserve the project owner\u002Frequester and required repository approvals.\n   - **Copilot agent:** *\"Want to include @copilot? It can pick up issues autonomously. (yes\u002Fno)\"* → If yes, follow Copilot Coding Agent Member section and ask about auto-assignment.\n   - These are additive. **Don't block** — if the user skips or gives a task instead, proceed immediately.\n",{"name":5,"domain":44,"source":45,"confidence":46,"description":7,"allowedTools":47},"squad-internals","Extracted from squad.agent.md (bradygaster\u002Fsquad#1308), with Waza project overrides for paired casting initialization and governance-aligned reviewer seeding.","high",[],"main","116214a33b5e07766539f64c0ea21521467829bf",".github\u002Fskills\u002Fcoordinator-init-mode",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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add microsoft\u002Fwaza --skill coordinator-init-mode",{"tool":64,"command":65},"bunx","bunx skills add microsoft\u002Fwaza --skill coordinator-init-mode",{"tool":67,"command":68},"pnpm","pnpm dlx skills add microsoft\u002Fwaza --skill coordinator-init-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcoordinator-init-mode\u002FSKILL.md",true,[],[73,108,133,162,182,195],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":87,"publishedAt":39},"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",[79,84],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":85,"categoryName":86,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000023","Skill与智能体开发",[88,89,90,91,92,93,94,95,96,27,97,98,99,100,101,102,103,104,105,106,107],"waza runner","runner","waza","frontmatter","run","triggers","do","my","general","evals","unrelated","writing skills","my skill","sensei","Test Skill","run evals","performance","writing","testing","authoring",{"skillNo":109,"name":90,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":115,"publishedAt":39},"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",[113,114],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},{"categoryNo":85,"categoryName":86,"taxonomyType":82,"taxonomyTypeDesc":83},[90,92,116,117,118,119,120,121,122,123,124,125,126,127,21,128,129,106,130,131,132],"workflow skill","executor","fixture","eval","compare results","model","Evaluation","evaluate skill","code","eval suite","generate","copilot","workflow","ai agent","counting","new","skill-creator",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":148,"publishedAt":39},"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",[139,140,145],{"categoryNo":85,"categoryName":86,"taxonomyType":82,"taxonomyTypeDesc":83},{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":146,"categoryName":147,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000036","内容创作者",[149,90,150,151,105,106,129,152,153,125,27,107,94,96,97,154,155,156,119,157,158,100,92,159,160,101,161,128],"waza interactive","interactive","tests","use","general coding","ready","only","failing","work","improve","create","debug","create eval",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":39},"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",[168],{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},[170,171,124,172,173,174,27,175,176,177,178,179,180,181],"code explainer","explainer","learning","plain","down","reviews","step by step","english","snippets","what the","plain english","documentation",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":39},"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",[],[189,190,191,118,154,192,193,194],"compatibility skill","compatibility","it","read","report","status",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":39},"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",[],[202,203,204,192,193,194,205],"evidence","evidence judge","judge","summarize"]