[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GTSEQK65P0VCARCD4G521D":3,"skill-same:01M6GTSEQK65P0VCARCD4G521D":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M6GTSEQK65P0VCARCD4G521D","goat",null,"Use when you describe an outcome and need the right goat-* workflow chosen for you.","blundergoat\u002Fgoat-flow","blundergoat","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260647401?v=4","01M6GTR7WK4KVYK7N5DEQGA7BT","01M6GTR84KH4BAF65ZV9V9DNG9",32,"MIT","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgoat\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26],"workflow","outcome","use","you","2026-11-10 10:12:30",false,"---\nname: goat\ndescription: \"Use when you describe an outcome and need the right goat-* workflow chosen for you.\"\ngoat-flow-skill-version: \"1.18.0\"\n---\n# \u002Fgoat\n\n## Shared Conventions\n\nRead `.goat-flow\u002Fskill-docs\u002Fskill-preamble.md` for shared conventions.\n\n## Boundary Commands\n\n- **NEVER:** Investigate implementation or make changes before routing.\n- **ALWAYS:** Honor explicit invocations; answer simple facts directly; split other intents and route each.\n- **DEFER TO:** Routed skills, direct execution for simple changes, or direct answers.\n\n**If a symptom tempts code reading, STOP.** The dispatcher routes; the routed skill investigates.\n\n| Excuse | Reality |\n|--------|---------|\n| \"I can see it - routing is overhead\" | Route before investigation. |\n| \"The user said 'just fix it'\" | Route to \u002Fgoat-debug. |\n\n## How It Works\n\n0. **EXPLICIT PASS-THROUGH** - named goat-* invocation: dispatch immediately with the remaining text as its brief; skip UNDERSTAND, GATHER, and reclassification. The target skill owns Step 0.\n1. **UNDERSTAND (inferred only)** - classify intent; split multiple intents; ask only if order matters.\n   - **Simple-fact fast path:** for one factual question, answer directly after UNDERSTAND; skip GATHER and the Route Snapshot.\n2. **GATHER (inferred skill or direct-execution routing only)** - before routing, check:\n   - Ask-first boundaries: compare request-named files with active instruction boundaries; no matching request file -> `target-files=unknown`\n   - Routed skills own learning-loop retrieval; do not pre-read their learning-loop indexes in the dispatcher\n   - Direct execution only: run the shared preamble's INDEX-first retrieval before emitting the Route Snapshot\n   - If the boundary scan or direct-execution retrieval fails, note `gather-degraded` and route anyway\n   - Only direct-execution snapshots include the retrieval result\n3. **ROUTE (inferred skill or direct-execution only)** - dispatch using the map. Emit a Route Snapshot:\n\n```\nIntent: \u003Cclassified user intent>\nRoute: \u003C\u002Fgoat-* skill or direct path>\nDepth: \u003Cuser request | destination Step 0 | not applicable>\nRationale: \u003Cverified routing rule and boundary state>\nRelevant prior learnings: \u003Cdirect route: matches | none | retrieval miss; routed skill: omit>\n```\n\nOnly user-requested depth is forwarded; otherwise destination Step 0 selects. Markers are not depth arguments. Direct: not applicable; quality: no Route Snapshot.\n\n## Route Map\n\n| Intent | Route |\n|--------|-------|\n| Bug, failure, unexpected behaviour; verify a fix | `\u002Fgoat-debug` |\n| Browser-visible issue | Browser evidence first; then `\u002Fgoat-debug` (Diagnose mode) |\n| Understand, explain, explore unfamiliar code | `\u002Fgoat-debug` (Investigate mode) |\n| GOAT Flow setup\u002Fprocess\u002Fharness\u002Fskills quality assessment | `goat-flow quality` CLI\u002Fdashboard prompt flow (no goat skill wrapper) |\n| Code quality review, area audit, diff check | `\u002Fgoat-review` |\n| Multi-perspective critique | `\u002Fgoat-critique` |\n| Security, compliance, dependency audit | `\u002Fgoat-security` |\n| Comment, documentation, naming, or private-placement remediation | `\u002Fgoat-clarity` |\n| Testing gaps, coverage, verification planning | `\u002Fgoat-qa` |\n| Bare task path (no action verb) | Bare or ambiguous task paths are read-only context. Do not update `.active`, milestone status, or code from a path alone |\n| Plan\u002Fdesign or non-trivial build\u002Fchange | `\u002Fgoat-plan`; build\u002Fchange carries `return-to-implement`, plan\u002Fdesign stops after planning |\n| Hotfix or simple implementation (1-2 files, obvious change) | No skill; use execution loop directly |\n| Simple question | Answer directly |\n\n## Constraints\n\n- MUST respect explicit skill invocations - no reclassification\n- MUST NOT investigate implementation or make changes before routing; the Simple-fact fast path may read only the minimum source or reference needed to answer\n- MUST understand intent conversationally, not via keyword lookup - 0-2 clarification questions max; route with stated assumption if still ambiguous\n- MUST emit a Route Snapshot for every inferred skill or direct-execution dispatch - simple-fact answers are exempt\n- MUST split multi-intent requests into numbered intents and route each\n- MUST pass the complete brief and preserve context; `return-to-implement` preserves build authorization, but Ask First boundaries still gate\n","# \u002Fgoat\n\n## Shared Conventions\n\nRead `.goat-flow\u002Fskill-docs\u002Fskill-preamble.md` for shared conventions.\n\n## Boundary Commands\n\n- **NEVER:** Investigate implementation or make changes before routing.\n- **ALWAYS:** Honor explicit invocations; answer simple facts directly; split other intents and route each.\n- **DEFER TO:** Routed skills, direct execution for simple changes, or direct answers.\n\n**If a symptom tempts code reading, STOP.** The dispatcher routes; the routed skill investigates.\n\n| Excuse | Reality |\n|--------|---------|\n| \"I can see it - routing is overhead\" | Route before investigation. |\n| \"The user said 'just fix it'\" | Route to \u002Fgoat-debug. |\n\n## How It Works\n\n0. **EXPLICIT PASS-THROUGH** - named goat-* invocation: dispatch immediately with the remaining text as its brief; skip UNDERSTAND, GATHER, and reclassification. The target skill owns Step 0.\n1. **UNDERSTAND (inferred only)** - classify intent; split multiple intents; ask only if order matters.\n   - **Simple-fact fast path:** for one factual question, answer directly after UNDERSTAND; skip GATHER and the Route Snapshot.\n2. **GATHER (inferred skill or direct-execution routing only)** - before routing, check:\n   - Ask-first boundaries: compare request-named files with active instruction boundaries; no matching request file -> `target-files=unknown`\n   - Routed skills own learning-loop retrieval; do not pre-read their learning-loop indexes in the dispatcher\n   - Direct execution only: run the shared preamble's INDEX-first retrieval before emitting the Route Snapshot\n   - If the boundary scan or direct-execution retrieval fails, note `gather-degraded` and route anyway\n   - Only direct-execution snapshots include the retrieval result\n3. **ROUTE (inferred skill or direct-execution only)** - dispatch using the map. Emit a Route Snapshot:\n\n```\nIntent: \u003Cclassified user intent>\nRoute: \u003C\u002Fgoat-* skill or direct path>\nDepth: \u003Cuser request | destination Step 0 | not applicable>\nRationale: \u003Cverified routing rule and boundary state>\nRelevant prior learnings: \u003Cdirect route: matches | none | retrieval miss; routed skill: omit>\n```\n\nOnly user-requested depth is forwarded; otherwise destination Step 0 selects. Markers are not depth arguments. Direct: not applicable; quality: no Route Snapshot.\n\n## Route Map\n\n| Intent | Route |\n|--------|-------|\n| Bug, failure, unexpected behaviour; verify a fix | `\u002Fgoat-debug` |\n| Browser-visible issue | Browser evidence first; then `\u002Fgoat-debug` (Diagnose mode) |\n| Understand, explain, explore unfamiliar code | `\u002Fgoat-debug` (Investigate mode) |\n| GOAT Flow setup\u002Fprocess\u002Fharness\u002Fskills quality assessment | `goat-flow quality` CLI\u002Fdashboard prompt flow (no goat skill wrapper) |\n| Code quality review, area audit, diff check | `\u002Fgoat-review` |\n| Multi-perspective critique | `\u002Fgoat-critique` |\n| Security, compliance, dependency audit | `\u002Fgoat-security` |\n| Comment, documentation, naming, or private-placement remediation | `\u002Fgoat-clarity` |\n| Testing gaps, coverage, verification planning | `\u002Fgoat-qa` |\n| Bare task path (no action verb) | Bare or ambiguous task paths are read-only context. Do not update `.active`, milestone status, or code from a path alone |\n| Plan\u002Fdesign or non-trivial build\u002Fchange | `\u002Fgoat-plan`; build\u002Fchange carries `return-to-implement`, plan\u002Fdesign stops after planning |\n| Hotfix or simple implementation (1-2 files, obvious change) | No skill; use execution loop directly |\n| Simple question | Answer directly |\n\n## Constraints\n\n- MUST respect explicit skill invocations - no reclassification\n- MUST NOT investigate implementation or make changes before routing; the Simple-fact fast path may read only the minimum source or reference needed to answer\n- MUST understand intent conversationally, not via keyword lookup - 0-2 clarification questions max; route with stated assumption if still ambiguous\n- MUST emit a Route Snapshot for every inferred skill or direct-execution dispatch - simple-fact answers are exempt\n- MUST split multi-intent requests into numbered intents and route each\n- MUST pass the complete brief and preserve context; `return-to-implement` preserves build authorization, but Ask First boundaries still gate\n",{"name":5,"description":7,"goat-flow-skill-version":32},"1.18.0","main","369a5f67ee6d91bd7cda2b7d745dd5c256980543",".agents\u002Fskills\u002Fgoat",2,"https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow","https:\u002F\u002Fgoat-flow.com","https:\u002F\u002Fgithub.com\u002Fblundergoat","2026-11-12 03:36:32",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add blundergoat\u002Fgoat-flow --skill goat",{"tool":47,"command":48},"bunx","bunx skills add blundergoat\u002Fgoat-flow --skill goat",{"tool":50,"command":51},"pnpm","pnpm dlx skills add blundergoat\u002Fgoat-flow --skill goat","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgoat\u002FSKILL.md",true,[],[56,62,79,102,124,135],{"skillNo":57,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":61,"publishedAt":27},"01M6GV2QNW1KRHYPSNXA2F0A3G","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fgoat\u002FSKILL.md",[60],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[5,23,24,25,26],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":73,"publishedAt":27},"01M6GV2AQBX5PYWK2CT1B9D82R","goat-security","Use when assessing security implications of code changes, architecture decisions, or new features.","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fgoat-security\u002FSKILL.md",[68],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,74,75,76,77,78,25],"goat security","security","architecture","code","decisions",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":89,"publishedAt":27},"01M6GV1W3W2Q94F9GSNFC5PS7Z","goat-review","Use when reviewing a diff, PR, or set of code changes, or auditing a codebase area for quality issues. Triggers: 'review this', 'code review', 'audit X', 'look at these changes'.","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fgoat-review\u002FSKILL.md",[85,88],{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[5,90,91,25,92,93,94,95,96,97,98,99,77,100,101],"goat review","review","diff","look","triggers","at","audit","quality","code review","pr","issues","SET",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":112,"publishedAt":27},"01M6GV17R6Z0D01Q69MX2FDNQZ","goat-qa","Use when evaluating test coverage gaps, planning test strategy, or assessing testing risk for code changes.","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fgoat-qa\u002FSKILL.md",[108,111],{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[5,113,114,115,116,117,118,77,119,120,121,25,122,123],"goat qa","qa","coverage","testing","test","coverage gaps","planning","risk","strategy","test coverage","test strategy",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":27},"01M6GV0VC60WAVV90K1FGJBBE2","goat-plan","Use when creating, updating, reconciling, or resuming milestone plans.","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fgoat-plan\u002FSKILL.md",[],[5,131,132,133,25,134],"goat plan","plan","milestone","plans",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":27},"01M6GV0B1S1D5C7NR86VP2BH9R","goat-debug","Use when diagnosing a bug, unexpected behaviour, system failure, or unfamiliar code that needs structured investigation.","https:\u002F\u002Fgithub.com\u002Fblundergoat\u002Fgoat-flow\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fgoat-debug\u002FSKILL.md",[141],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},[143,144,5,145,146,25,147,148,77],"debug","goat debug","structured","bug","system","investigation"]