[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DNHZH4V8S59DPD224JCZ0D":3,"skill-same:01M6DNHZH4V8S59DPD224JCZ0D":82},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6DNHZH4V8S59DPD224JCZ0D","aac-review-eval-harness",null,"Review workflow: Eval Harness Workflow","msayedshokry\u002FAgileAgentCanvasExt","msayedshokry","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35009459?v=4","01M6DN5RZZ297CGWTNJ6ERZQ8W","Mohamed Sayed","01M6DN5S4XS7SVCSXZRW2XR0XF",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Fskills\u002Faac-review-eval-harness\u002FSKILL.md",[],[19,20,21,22,23,24],"review","harness","eval harness","eval","aac review eval harness","workflow","2026-11-10 10:12:30",false,"---\nname: aac-review-eval-harness\ndescription: 'Review workflow: Eval Harness Workflow\r'\n---\n\n# Eval Harness Workflow\r\n\r\nYou are an Eval-Driven Development (EDD) Coach. Help the team define pass\u002Ffail criteria before implementation and track reliability metrics.\r\n\r\n## Steps\r\n\r\n### 1. Define Capability Evals\r\n\r\nFor each new feature or behavior, define:\r\n- **Task**: What the system should accomplish\r\n- **Success Criteria**: Specific, testable criteria (checkboxes)\r\n- **Expected Output**: What correct output looks like\r\n\r\n### 2. Define Regression Evals\r\n\r\nFor each existing feature that might be affected:\r\n- **Baseline**: Current state (SHA or checkpoint)\r\n- **Tests**: List of existing tests to verify\r\n- **Expected Result**: All should still PASS\r\n\r\n### 3. Select Grader Type\r\n\r\nChoose the appropriate grader for each eval:\r\n- **Code-Based**: Deterministic checks (grep, test runners, build)\r\n- **Model-Based**: AI evaluation with structured scoring (1-5)\r\n- **Human**: Manual review with risk level flags\r\n\r\n### 4. Run Evals\r\n\r\nExecute all defined evals and record results.\r\n\r\n### 5. Report\r\n\r\nProduce structured eval results:\r\n\r\n```\r\nEVAL REPORT\r\n===========\r\nCapability: X\u002FY PASS (pass@1: Z%)\r\nRegression: X\u002FY PASS\r\nOverall:    PASS\u002FFAIL\r\n\r\nNew Capabilities:\r\n  ✅ ...\r\n  ❌ ...\r\n\r\nRegression Status:\r\n  ✅ ...\r\n```\r\n\r\n## Metrics Targets\r\n\r\n- pass@1 > 80% for capability evals\r\n- pass@3 > 90% for capability evals\r\n- 100% for regression evals (zero regressions)\r\n\r\n","# Eval Harness Workflow\r\n\r\nYou are an Eval-Driven Development (EDD) Coach. Help the team define pass\u002Ffail criteria before implementation and track reliability metrics.\r\n\r\n## Steps\r\n\r\n### 1. Define Capability Evals\r\n\r\nFor each new feature or behavior, define:\r\n- **Task**: What the system should accomplish\r\n- **Success Criteria**: Specific, testable criteria (checkboxes)\r\n- **Expected Output**: What correct output looks like\r\n\r\n### 2. Define Regression Evals\r\n\r\nFor each existing feature that might be affected:\r\n- **Baseline**: Current state (SHA or checkpoint)\r\n- **Tests**: List of existing tests to verify\r\n- **Expected Result**: All should still PASS\r\n\r\n### 3. Select Grader Type\r\n\r\nChoose the appropriate grader for each eval:\r\n- **Code-Based**: Deterministic checks (grep, test runners, build)\r\n- **Model-Based**: AI evaluation with structured scoring (1-5)\r\n- **Human**: Manual review with risk level flags\r\n\r\n### 4. Run Evals\r\n\r\nExecute all defined evals and record results.\r\n\r\n### 5. Report\r\n\r\nProduce structured eval results:\r\n\r\n```\r\nEVAL REPORT\r\n===========\r\nCapability: X\u002FY PASS (pass@1: Z%)\r\nRegression: X\u002FY PASS\r\nOverall:    PASS\u002FFAIL\r\n\r\nNew Capabilities:\r\n  ✅ ...\r\n  ❌ ...\r\n\r\nRegression Status:\r\n  ✅ ...\r\n```\r\n\r\n## Metrics Targets\r\n\r\n- pass@1 > 80% for capability evals\r\n- pass@3 > 90% for capability evals\r\n- 100% for regression evals (zero regressions)\r\n\r\n",{"name":5,"description":30},"Review workflow: Eval Harness Workflow ","main","473351382920a74eb8f353f979a06f6f05bb5f59","resources\u002F_aac\u002Fskills\u002Faac-review-eval-harness",0,"https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt","https:\u002F\u002Fgithub.com\u002Fmsayedshokry","2026-08-29 02:00:07",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add msayedshokry\u002FAgileAgentCanvasExt --skill aac-review-eval-harness",{"tool":44,"command":45},"bunx","bunx skills add msayedshokry\u002FAgileAgentCanvasExt --skill aac-review-eval-harness",{"tool":47,"command":48},"pnpm","pnpm dlx skills add msayedshokry\u002FAgileAgentCanvasExt --skill aac-review-eval-harness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Fskills\u002Faac-review-eval-harness\u002FSKILL.md",true,[52,58,64,70,74,78],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"brave_search.py","SCRIPT","脚本",9466,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrave-search\u002Fbrave_search.py",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"customize.toml","OTHER","其他",149,"https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Fskills\u002Faac-review-eval-harness\u002Fcustomize.toml",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"docs\u002Fbrave_search_api_reference.md","REFERENCE","参考文档",50806,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrave-search\u002Fdocs\u002Fbrave_search_api_reference.md",{"path":71,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":72,"sourceHtmlUrl":73},"pyproject.toml",242,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrave-search\u002Fpyproject.toml",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"run.sh",879,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrave-search\u002Frun.sh",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"sanity.sh",1174,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbrave-search\u002Fsanity.sh",[83,113,132,144,167,183],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":99,"publishedAt":25},"01M6DNRTHE3M1XG3KDJTEF6BG6","bmad-teach-me-testing","Teach testing progressively through structured sessions. Use when user says \"lets learn testing\" or \"I want to study test practices\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Fbmad-teach-me-testing\u002FSKILL.md",[89,94],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[100,101,102,103,104,105,106,107,108,109,110,111,112],"bmad","me","bmad teach me testing","teach me","teach","testing","test","sessions","learn","user","use","study","structured",{"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":120,"publishedAt":25},"01M6DNRG27V77JEGMPMJVRY0Q5","aac-testarch-trace","Generate traceability matrix and quality gate decision. Use when the user says \"lets create traceability matrix\" or \"I want to analyze test coverage\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-trace\u002FSKILL.md",[119],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[121,122,106,123,124,125,126,127,128,109,129,110,130,131],"aac testarch trace","trace","quality gate","create","generate","analyze","quality","decision","coverage","test coverage","gate",{"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":139,"publishedAt":25},"01M6DNR70G1S0DGDSHRWT1S1DD","aac-testarch-test-review","Review test quality using best practices validation. Use when user says \"lets review tests\" or \"I want to evaluate test quality\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-test-review\u002FSKILL.md",[138],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[19,140,106,141,142,127,109,110,143],"aac testarch test review","best practices","validation","tests",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":157,"publishedAt":25},"01M6DNQXV8F40EE78ZMWGWRPJM","aac-testarch-test-design","Create system-level or epic-level test plans. Use when the user says \"lets design test plan\" or \"I want to create test strategy\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-test-design\u002FSKILL.md",[150,151,154],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},{"categoryNo":152,"categoryName":153,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":155,"categoryName":156,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000032","设计师",[158,159,106,160,109,124,161,162,163,164,110,165,166],"aac testarch test design","test design","design","test plan","plan","system","strategy","test strategy","plans",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":25},"01M6DNQNG0T7Q5DKV3C03RY35D","aac-testarch-nfr","Audit NFR evidence for performance, security, reliability, and scalability. Use when implementation evidence exists and the user says \"audit NFR evidence\", \"audit NFRs\", or \"evaluate non-functional requirements\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-nfr\u002FSKILL.md",[],[174,175,176,177,178,179,109,180,181,110,182],"aac testarch nfr","reliability","evidence","implementation","scalability","requirements","audit","performance","security",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":25},"01M6DNQDPTGB49D8AAJV4GN2H8","aac-testarch-framework","Initialize test framework with Playwright or Cypress. Use when the user says \"lets setup test framework\" or \"I want to initialize testing framework\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-framework\u002FSKILL.md",[189],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},[191,192,193,109,110,194,195,196,106,197,105,198],"aac testarch framework","framework","initialize","testing framework","setup","test framework","playwright","cypress"]