[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X00A438VG96V20V1VMDHCM":3,"skill-same:01M6X00A438VG96V20V1VMDHCM":86},{"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":26,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":57,"commitSha":58,"skillDirectory":5,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6X00A438VG96V20V1VMDHCM","waza-runner",null,"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.","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\u002Fwaza-runner\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"waza runner","waza","runner","evals","frontmatter","for","my","triggers","authoring","do","general","testing","unrelated","writing skills","my skill","run","sensei","Test Skill","run evals","performance","writing","2026-11-10 10:12:30",false,"---\nname: waza-runner\ndescription: |\n  Run evaluations on Agent Skills to measure their effectiveness. \n  USE 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\".\n  DO NOT USE FOR: writing skills (use skill-authoring), improving frontmatter \n  (use sensei), or general testing unrelated to skills.\nmetadata:\n  author: spboyer\n  version: \"1.0\"\n---\n\n# Skill Eval Runner\n\n> Evaluate Agent Skills like you evaluate AI Agents\n\nThis skill runs evaluations on other skills to measure their effectiveness using the same patterns that power AI agent evaluations.\n\n## When to Use\n\n- Running quality evaluations on a skill\n- Testing if a skill triggers on correct prompts\n- Measuring skill behavior quality\n- Generating eval reports for CI\u002FCD\n\n## Commands\n\n### Run Evals\n```\nRun evals on \u003Cskill-name>\n```\n\n### Initialize Eval Suite\n```\nCreate evals for \u003Cskill-name>\n```\n\n### Generate Report\n```\nGenerate eval report for \u003Cskill-name>\n```\n\n## Workflow\n\n1. **Check for Eval Suite**: Look for `eval.yaml` in the skill directory\n2. **Load Tasks**: Parse task definitions from `tasks\u002F*.yaml`\n3. **Execute**: Run each task through the configured graders\n4. **Report**: Output results in JSON or Markdown format\n\n## Metrics Measured\n\n| Metric | Description | Default Threshold |\n|--------|-------------|-------------------|\n| Task Completion | Did the skill accomplish the goal? | 80% |\n| Trigger Accuracy | Was skill invoked on correct prompts? | 90% |\n| Behavior Quality | Tool calls, efficiency, reasoning | 70% |\n\n## Grader Types\n\n- **Code Graders**: Deterministic assertions, regex matching\n- **LLM Graders**: Model-as-judge with configurable rubrics\n- **Human Graders**: Manual review workflow\n\n## Example Usage\n\n### Running Evals\n```bash\n# From CLI\nwaza run .\u002Fmy-skill\u002Feval.yaml\n\n# Output to file\nwaza run .\u002Fmy-skill\u002Feval.yaml -o results.json\n```\n\n### Interpreting Results\n```json\n{\n  \"summary\": {\n    \"pass_rate\": 0.85,\n    \"composite_score\": 0.82\n  },\n  \"metrics\": {\n    \"task_completion\": { \"score\": 0.9, \"passed\": true },\n    \"trigger_accuracy\": { \"score\": 0.95, \"passed\": true }\n  }\n}\n```\n\n## References\n\n- [Eval Specification](references\u002FEVAL-SPEC.md) - Full eval.yaml schema\n- [Writing Tasks](references\u002FWRITING-TASKS.md) - Task definition guide\n- [Grader Reference](references\u002FGRADERS.md) - Available graders\n","# Skill Eval Runner\n\n> Evaluate Agent Skills like you evaluate AI Agents\n\nThis skill runs evaluations on other skills to measure their effectiveness using the same patterns that power AI agent evaluations.\n\n## When to Use\n\n- Running quality evaluations on a skill\n- Testing if a skill triggers on correct prompts\n- Measuring skill behavior quality\n- Generating eval reports for CI\u002FCD\n\n## Commands\n\n### Run Evals\n```\nRun evals on \u003Cskill-name>\n```\n\n### Initialize Eval Suite\n```\nCreate evals for \u003Cskill-name>\n```\n\n### Generate Report\n```\nGenerate eval report for \u003Cskill-name>\n```\n\n## Workflow\n\n1. **Check for Eval Suite**: Look for `eval.yaml` in the skill directory\n2. **Load Tasks**: Parse task definitions from `tasks\u002F*.yaml`\n3. **Execute**: Run each task through the configured graders\n4. **Report**: Output results in JSON or Markdown format\n\n## Metrics Measured\n\n| Metric | Description | Default Threshold |\n|--------|-------------|-------------------|\n| Task Completion | Did the skill accomplish the goal? | 80% |\n| Trigger Accuracy | Was skill invoked on correct prompts? | 90% |\n| Behavior Quality | Tool calls, efficiency, reasoning | 70% |\n\n## Grader Types\n\n- **Code Graders**: Deterministic assertions, regex matching\n- **LLM Graders**: Model-as-judge with configurable rubrics\n- **Human Graders**: Manual review workflow\n\n## Example Usage\n\n### Running Evals\n```bash\n# From CLI\nwaza run .\u002Fmy-skill\u002Feval.yaml\n\n# Output to file\nwaza run .\u002Fmy-skill\u002Feval.yaml -o results.json\n```\n\n### Interpreting Results\n```json\n{\n  \"summary\": {\n    \"pass_rate\": 0.85,\n    \"composite_score\": 0.82\n  },\n  \"metrics\": {\n    \"task_completion\": { \"score\": 0.9, \"passed\": true },\n    \"trigger_accuracy\": { \"score\": 0.95, \"passed\": true }\n  }\n}\n```\n\n## References\n\n- [Eval Specification](references\u002FEVAL-SPEC.md) - Full eval.yaml schema\n- [Writing Tasks](references\u002FWRITING-TASKS.md) - Task definition guide\n- [Grader Reference](references\u002FGRADERS.md) - Available graders\n",{"name":5,"metadata":53,"description":56},{"author":54,"version":55},"spboyer","1.0","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.\n","main","116214a33b5e07766539f64c0ea21521467829bf",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":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add microsoft\u002Fwaza --skill waza-runner",{"tool":72,"command":73},"bunx","bunx skills add microsoft\u002Fwaza --skill waza-runner",{"tool":75,"command":76},"pnpm","pnpm dlx skills add microsoft\u002Fwaza --skill waza-runner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fwaza-runner\u002FSKILL.md",true,[80],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002FEVAL-SPEC.md","REFERENCE","参考文档",3171,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fwaza-runner\u002Freferences\u002FEVAL-SPEC.md",[87,113,142,162,175,186],{"skillNo":88,"name":28,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":94,"publishedAt":48},"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",[92,93],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[28,95,96,97,98,99,100,101,102,103,104,105,106,107,42,108,109,110,111,112,38],"evaluate skill","new","eval suite","skill-creator","counting","workflow skill","executor","fixture","eval","compare results","model","Evaluation","code","generate","copilot","init","workflow","ai agent",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":128,"publishedAt":48},"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",[119,120,125],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":126,"categoryName":127,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000036","内容创作者",[129,28,130,131,35,132,32,36,37,30,43,133,134,103,135,136,41,42,137,138,97,139,140,111,112,47,38,141],"interactive","waza interactive","ready","tests","only","use","work","improve","create","debug","failing","general coding","create eval",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":48},"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",[148],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[150,151,107,152,153,154,32,155,156,157,158,159,160,161],"explainer","code explainer","plain","snippets","down","reviews","step by step","english","what the","plain english","learning","documentation",{"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":168,"publishedAt":48},"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",[],[169,170,171,102,131,172,173,174],"compatibility skill","compatibility","it","read","report","status",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":48},"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",[],[182,183,184,173,174,185,172],"evidence","judge","evidence judge","summarize",{"skillNo":187,"name":144,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":195,"publishedAt":48},"01M6WZZE4CBXD08ZXA3SGPK2BF","**UTILITY SKILL** - Explain code snippets, functions, and algorithms in plain language.\nUSE FOR: explain code, what does this code do, break down this function,\nhelp me understand this, walk through this algorithm, clarify this logic,\nexplain this snippet, describe what happens here.\nDO NOT USE FOR: writing new code (use code generation), fixing bugs (use debugging),\nrefactoring (use refactoring skills), code review with action items.\nINVOKES: file reading tools to access code, language detection for tailored explanations.\nFOR SINGLE OPERATIONS: If the user just needs to see file contents, use file reading tools directly.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fexamples\u002Fcode-explainer\u002FSKILL.md",[191,194],{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[151,150,107,196,96,197,198,199,200,201,202,153,203,204,205,206,207,208,209,210,47,211],"utility","action items","describe","file reading","break","action","reading","me","clarify","access","refactoring","Code Generation","explain code","debugging","review","code review"]