[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X0JBQHTBCFPKP7P1SANDCC":3,"skill-same:01M6X0JBQHTBCFPKP7P1SANDCC":57},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M6X0JBQHTBCFPKP7P1SANDCC","validate-skills",null,"Validate that commands documented in skill files actually work. Use when creating, updating, or reviewing skills to ensure all documented commands exit with code 0.","microsoft\u002Fvstest","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6X0HC8J2E7YW8ZSEYN45EA0",977,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fvalidate-skills\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"validate","validate skills","code","work","use","files","exit","commands","with","when","2026-11-10 10:12:30",false,"---\nname: validate-skills\ndescription: Validate that commands documented in skill files actually work. Use when creating, updating, or reviewing skills to ensure all documented commands exit with code 0.\n---\n\n# Validating Skills\n\nVerify every executable command in a skill runs successfully on the current OS.\n\n## When to Use\n\n- After creating or updating a skill that contains executable commands\n- During skill review to catch stale or broken instructions\n- When switching OS (e.g. Windows → Linux) to confirm cross-platform commands\n\n## Procedure\n\n### 1. Detect Current OS\n\nDetermine which platform commands to extract:\n\n```powershell\n# PowerShell (Windows)\n$os = \"Windows\"\n```\n\n```bash\n# Bash (Linux \u002F macOS)\nOS=$(uname -s)   # \"Linux\" or \"Darwin\"\n```\n\n### 2. Extract Commands\n\nParse the target skill's `SKILL.md` and list every shell command for the detected OS:\n\n- Many skills document commands in tables with **Windows** and **Linux \u002F macOS** columns. Pick the column matching your OS.\n- If a command contains comments like `# Windows` or `# Linux \u002F macOS`, only run the one for your OS.\n- **Placeholder substitution:** Replace obvious placeholders (e.g. `\u003Cpath-to-csproj>`, `\u003Cskill-name>`) with real values from the repo. If no sensible value exists, skip the command.\n- **Adapt cross-platform commands:** Commands like `ls -la` should be adapted to PowerShell equivalents (`Get-ChildItem`) on Windows when no native Windows command is documented.\n\n### 3. Track Results\n\nUse the SQL tool to create a tracking table:\n\n```sql\nCREATE TABLE skill_commands (\n  id INTEGER PRIMARY KEY AUTOINCREMENT,\n  skill TEXT NOT NULL,\n  command TEXT NOT NULL,\n  expected_exit INTEGER DEFAULT 0,\n  actual_exit INTEGER,\n  status TEXT DEFAULT 'pending',\n  notes TEXT\n);\n```\n\n### 4. Run Each Command\n\nFor every extracted command:\n\n1. Run it from the repo root\n2. Record the exit code\n3. Classify the result:\n   - **Exit 0 → PASS**\n   - **Non-zero + environment issue (missing SDK, no internet) → ENV_ISSUE**\n   - **Non-zero + command\u002Fdocs wrong → ERROR**\n\n### 5. Safety Rules\n\n> **CRITICAL:** Never run unfiltered integration\u002Facceptance tests. They take hours.\n> - `test.sh --integrationTest` or `test.cmd -Integration` **MUST** include a `--filter` or `-p` flag.\n> - `test.sh -p smoke` is acceptable (scoped to smoke tests), but expect it to be slow.\n\n### 6. Report\n\nAfter all commands finish, print a summary:\n\n```\n=== Skill Validation Report ===\nSkill: \u003Cskill-name>\nOS: \u003CLinux|Darwin|Windows>\nCommands tested: N\nPASS: X\nENV_ISSUE: Y (list with reasons)\nERROR: Z (list failed commands with exit codes)\n```\n\n### 7. Fix or Flag\n\n- **ERROR (documentation bug):** Update the skill's `SKILL.md` to fix the command.\n- **ENV_ISSUE:** Add a troubleshooting note to the skill if the environment prerequisite is not already documented.\n- **PASS:** No action needed.\n\n## Ordering Tips\n\n- Run restore\u002Fbuild before tests (tests depend on build output)\n- Run the cheapest commands first to fail fast\n- Batch independent test commands in parallel when possible\n","# Validating Skills\n\nVerify every executable command in a skill runs successfully on the current OS.\n\n## When to Use\n\n- After creating or updating a skill that contains executable commands\n- During skill review to catch stale or broken instructions\n- When switching OS (e.g. Windows → Linux) to confirm cross-platform commands\n\n## Procedure\n\n### 1. Detect Current OS\n\nDetermine which platform commands to extract:\n\n```powershell\n# PowerShell (Windows)\n$os = \"Windows\"\n```\n\n```bash\n# Bash (Linux \u002F macOS)\nOS=$(uname -s)   # \"Linux\" or \"Darwin\"\n```\n\n### 2. Extract Commands\n\nParse the target skill's `SKILL.md` and list every shell command for the detected OS:\n\n- Many skills document commands in tables with **Windows** and **Linux \u002F macOS** columns. Pick the column matching your OS.\n- If a command contains comments like `# Windows` or `# Linux \u002F macOS`, only run the one for your OS.\n- **Placeholder substitution:** Replace obvious placeholders (e.g. `\u003Cpath-to-csproj>`, `\u003Cskill-name>`) with real values from the repo. If no sensible value exists, skip the command.\n- **Adapt cross-platform commands:** Commands like `ls -la` should be adapted to PowerShell equivalents (`Get-ChildItem`) on Windows when no native Windows command is documented.\n\n### 3. Track Results\n\nUse the SQL tool to create a tracking table:\n\n```sql\nCREATE TABLE skill_commands (\n  id INTEGER PRIMARY KEY AUTOINCREMENT,\n  skill TEXT NOT NULL,\n  command TEXT NOT NULL,\n  expected_exit INTEGER DEFAULT 0,\n  actual_exit INTEGER,\n  status TEXT DEFAULT 'pending',\n  notes TEXT\n);\n```\n\n### 4. Run Each Command\n\nFor every extracted command:\n\n1. Run it from the repo root\n2. Record the exit code\n3. Classify the result:\n   - **Exit 0 → PASS**\n   - **Non-zero + environment issue (missing SDK, no internet) → ENV_ISSUE**\n   - **Non-zero + command\u002Fdocs wrong → ERROR**\n\n### 5. Safety Rules\n\n> **CRITICAL:** Never run unfiltered integration\u002Facceptance tests. They take hours.\n> - `test.sh --integrationTest` or `test.cmd -Integration` **MUST** include a `--filter` or `-p` flag.\n> - `test.sh -p smoke` is acceptable (scoped to smoke tests), but expect it to be slow.\n\n### 6. Report\n\nAfter all commands finish, print a summary:\n\n```\n=== Skill Validation Report ===\nSkill: \u003Cskill-name>\nOS: \u003CLinux|Darwin|Windows>\nCommands tested: N\nPASS: X\nENV_ISSUE: Y (list with reasons)\nERROR: Z (list failed commands with exit codes)\n```\n\n### 7. Fix or Flag\n\n- **ERROR (documentation bug):** Update the skill's `SKILL.md` to fix the command.\n- **ENV_ISSUE:** Add a troubleshooting note to the skill if the environment prerequisite is not already documented.\n- **PASS:** No action needed.\n\n## Ordering Tips\n\n- Run restore\u002Fbuild before tests (tests depend on build output)\n- Run the cheapest commands first to fail fast\n- Batch independent test commands in parallel when possible\n",{"name":5,"description":7},"main","0ebb2cac77b3c1040fa4fb3c5316325f0db2a5f7",".github\u002Fskills\u002Fvalidate-skills",359,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 13:00:58",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add microsoft\u002Fvstest --skill validate-skills",{"tool":49,"command":50},"bunx","bunx skills add microsoft\u002Fvstest --skill validate-skills",{"tool":52,"command":53},"pnpm","pnpm dlx skills add microsoft\u002Fvstest --skill validate-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fvalidate-skills\u002FSKILL.md",true,[],[58,88,110,132],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":69,"publishedAt":29},"01M6X0JMT6KRQ3MH4E65C81W2R","vstest-build-test","Build, test, and validate changes in the vstest repository. Use when building vstest projects, running unit tests, smoke tests, or acceptance tests, or when deploying locally built vstest.console for manual testing.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fvstest-build-test\u002FSKILL.md",[64],{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[70,71,72,73,23,74,75,76,77,78,79,80,81,82,83,84,85,86,28,87],"build test","test","build","vstest build test","unit tests","changes","running","smoke tests","tests","manual","for","smoke","unit","manual testing","projects","testing","acceptance","repository",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":95,"publishedAt":29},"01M6X0J3STXVVDMPG251GRG4YA","trx-analysis","Parse and analyze Visual Studio TRX test result files. Use when asked about slow tests, test durations, test frequency, flaky tests, failure analysis, or test execution patterns from TRX files.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftrx-analysis\u002FSKILL.md",[94],{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},[96,97,23,98,99,100,71,101,102,103,28,104,24,105,78,106,107,108,109],"trx analysis","analysis","about","result","test execution","analyze","visual","studio","patterns","execution","failure analysis","visual studio","Frequency","parse",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":29},"01M6X0J07H9G388HD8TCK24ENH","expert-reviewing","Route code and dependency changes to relevant review dimensions based on affected files and folders. Use when reviewing PRs, including Dependabot updates, GitHub Actions and generated workflow changes, or specific vstest subsystems.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fexpert-review\u002FSKILL.md",[],[117,118,119,28,120,75,121,122,123,21,124,125,126,23,127,24,128,129,130,131],"expert reviewing","expert","github","affected","route","review","dimensions","workflow","updates","dependabot","generated","github actions","prs","actions","relevant",{"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":142,"publishedAt":29},"01M6X0HTMSNSG6Q38ZAC35RJFK","creating-skills","Create custom agent capabilities when discovering novel tools, receiving task-agnostic tips from reviewers, or after researching specialized workflows not covered in existing instructions. Teaches structure, YAML optimization for LLM discoverability, and token efficiency.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvstest\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcreating-skills\u002FSKILL.md",[138,139],{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},{"categoryNo":140,"categoryName":141,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000023","Skill与智能体开发",[143,144,145,146,147,148,80,149,150,151,152,153,154,155,156,157,158,159,28,160],"creating skills","create custom agent","Existing","custom","Optimization","tips","novel","token efficiency","Tools","token","task","structure","create","efficiency","capabilities","specialized","discoverability","workflows"]