[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NWK88674VERQKCZN4EX6AT":3,"skill-same:01M6NWK88674VERQKCZN4EX6AT":69},{"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":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6NWK88674VERQKCZN4EX6AT","tdd-migration-pipeline",null,"Orchestrator-only workflow for migrating\u002Frewriting codebases with full TDD and agent delegation","rubicanjr\u002FFinCognis","rubicanjr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234912519?v=4","01M6NT156NND8J474G34SB3923","Rubi","01M6NT15B70RWXE1N3YV0BZY8A",0,"MIT","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Ftdd-migration-pipeline\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"tdd","pipeline","migration","tdd migration pipeline","workflow","delegation","Bash","read","orchestrator","only","task","full","with","for","2026-11-10 10:12:30",false,"---\nname: tdd-migration-pipeline\ndescription: Orchestrator-only workflow for migrating\u002Frewriting codebases with full TDD and agent delegation\nallowed-tools: [Task, TodoWrite, Read, Bash]\n---\n\n# TDD Migration Pipeline\n\nOrchestrator-only workflow for migrating or rewriting codebases. You do NOT read files, write code, or validate anything yourself. You only instruct agents and pipe context (paths, not contents).\n\n## When to Use\n\n- Migrating codebase from one language\u002Fframework to another\n- Rewriting a system with TDD guarantees\n- Large-scale refactoring with behavioral contracts\n- When you want zero context growth in the orchestrator\n\n## Core Principles\n\n1. **ZERO orchestrator execution** - only instruct and pipe context\n2. **All work done by agents** - you never read\u002Fwrite\u002Fvalidate\n3. **Context window stays flat** - pass paths, not contents\n4. **New code in separate directory** - never modify source\n\n## Your Constraints\n\n- Never say \"let me read...\" or \"looking at...\"\n- Only say \"Agent X: do Y with Z\"\n- Your context should NOT grow during execution\n- All agents must use `qlty` and `tldr` skills\n\n## Pipeline Phases\n\n### Phase 1: SPEC\n```\nInstruct spec-agent (use scout or architect):\n- Analyze {source_path} using tldr-skill\n- Output: spec.md with behavioral contracts, types, edge cases\n```\n\n**Agent prompt template:**\n```\nAnalyze the codebase at {source_path} using tldr commands (tldr structure, tldr extract, tldr calls).\nCreate spec.md with:\n- All behavioral contracts (what each function\u002Fclass promises)\n- Input\u002Foutput types\n- Edge cases and invariants\n- Dependencies between components\nWrite to: {target_dir}\u002Fspec.md\n```\n\n### Phase 2: FAILING TESTS\n```\nInstruct test-agent (use arbiter):\n- Read spec.md\n- Write failing tests in {target_dir}\u002Ftests\u002F\n- Tests should define expected behavior before implementation\n\nInstruct review-agent (use critic):\n- Validate tests cover spec completely\n- No gaps in behavioral coverage\n```\n\n### Phase 3: ADVERSARIAL (x3 iterations)\n```\nInstruct premortem-agent (use premortem skill):\n- Review spec + tests\n- Identify failure modes, race conditions, edge cases\n- DO NOT ASK - just add mitigations directly to spec\n- Run 3 passes with fresh perspective each time\n```\n\n**Key:** Each pass should find NEW issues, not repeat previous ones.\n\n### Phase 4: PHASED PLAN\n```\nInstruct planner-agent (use architect or plan-agent):\n- Input: spec.md + tests + mitigations\n- Output: phased-plan.yaml\n- Requirements:\n  - Dependency-ordered phases\n  - Each phase = one testable unit\n  - Clear inputs\u002Foutputs per phase\n```\n\n### Phase 5: BUILD LOOP (per phase)\n```\nFor each phase in phased-plan.yaml:\n\n  Instruct builder-agent (use kraken or spark):\n  - Write code to pass tests for this phase\n  - Use qlty for quality checks\n  - Run tests after each change\n\n  Instruct review-agent (use critic or judge):\n  - Validate implementation matches spec\n  - Check for regressions in previous phases\n  - Verify no breaking changes\n```\n\n### Phase 6: INTEGRATION VALIDATION\n```\nInstruct integration-agent (use atlas or validator):\n- Use tldr to diff against {reference_repo}\n- Check for:\n  - No race conditions\n  - No hangs or deadlocks\n  - No breaking changes vs original\n  - All behavioral contracts preserved\n- Output: validation-report.md\n```\n\n## Invocation\n\nWhen invoking this workflow, specify:\n\n```yaml\nSOURCE: {path to source code}\nTARGET_DIR: {new folder for migrated code}\nTARGET_LANG: {typescript|python|go|rust|etc}\nREFERENCE_REPO: {url or path for final diff comparison}\nSKILLS: [tldr-code, qlty-check, {domain-specific}]\n```\n\n## Agent Mapping\n\n| Phase | Agent Type | Subagent |\n|-------|-----------|----------|\n| Spec | research | `scout` or `architect` |\n| Tests | validate | `arbiter` |\n| Review | review | `critic` or `judge` |\n| Premortem | review | `premortem` skill |\n| Plan | plan | `architect` or `plan-agent` |\n| Build | implement | `kraken` (large) or `spark` (small) |\n| Integration | validate | `atlas` or `validator` |\n\n## Example Orchestration\n\n```\n# Phase 1\nTask(scout): \"Analyze \u002Fsrc\u002Fold-system using tldr structure and tldr extract.\n              Create spec.md at \u002Fmigration\u002Fspec.md with all behavioral contracts.\"\n\n# Phase 2\nTask(arbiter): \"Read \u002Fmigration\u002Fspec.md. Write failing tests to \u002Fmigration\u002Ftests\u002F\n               that define expected behavior.\"\n\nTask(critic): \"Review \u002Fmigration\u002Fspec.md vs \u002Fmigration\u002Ftests\u002F.\n              Report any behavioral gaps.\"\n\n# Phase 3 (x3)\nTask(premortem): \"Review \u002Fmigration\u002Fspec.md and \u002Fmigration\u002Ftests\u002F.\n                 Identify failure modes. Add mitigations directly to spec. Pass 1\u002F3.\"\n[repeat with \"Pass 2\u002F3\", \"Pass 3\u002F3\"]\n\n# Phase 4\nTask(architect): \"From \u002Fmigration\u002Fspec.md and \u002Fmigration\u002Ftests\u002F,\n                 create \u002Fmigration\u002Fphased-plan.yaml with dependency-ordered phases.\"\n\n# Phase 5 (loop)\nTask(kraken): \"Implement phase 1 from \u002Fmigration\u002Fphased-plan.yaml.\n              Code goes in \u002Fmigration\u002Fsrc\u002F. Run tests after.\"\n\nTask(critic): \"Review \u002Fmigration\u002Fsrc\u002F against \u002Fmigration\u002Fspec.md.\n              Check for spec compliance and regressions.\"\n[repeat for each phase]\n\n# Phase 6\nTask(atlas): \"Run full integration tests on \u002Fmigration\u002Fsrc\u002F.\n             Use tldr to diff against \u002Fsrc\u002Fold-system.\n             Output \u002Fmigration\u002Fvalidation-report.md.\"\n```\n\n## Anti-Patterns (DO NOT)\n\n- Reading files into your context (\"let me check the code...\")\n- Writing code directly (\"I'll implement this function...\")\n- Validating anything yourself (\"looking at the tests, I see...\")\n- Modifying the source directory\n- Skipping the adversarial phase\n- Running build without tests first\n\n## Success Criteria\n\n- [ ] All tests pass\n- [ ] qlty reports clean\n- [ ] tldr diff shows no breaking changes\n- [ ] No race conditions or hangs\n- [ ] validation-report.md confirms behavioral equivalence\n","# TDD Migration Pipeline\n\nOrchestrator-only workflow for migrating or rewriting codebases. You do NOT read files, write code, or validate anything yourself. You only instruct agents and pipe context (paths, not contents).\n\n## When to Use\n\n- Migrating codebase from one language\u002Fframework to another\n- Rewriting a system with TDD guarantees\n- Large-scale refactoring with behavioral contracts\n- When you want zero context growth in the orchestrator\n\n## Core Principles\n\n1. **ZERO orchestrator execution** - only instruct and pipe context\n2. **All work done by agents** - you never read\u002Fwrite\u002Fvalidate\n3. **Context window stays flat** - pass paths, not contents\n4. **New code in separate directory** - never modify source\n\n## Your Constraints\n\n- Never say \"let me read...\" or \"looking at...\"\n- Only say \"Agent X: do Y with Z\"\n- Your context should NOT grow during execution\n- All agents must use `qlty` and `tldr` skills\n\n## Pipeline Phases\n\n### Phase 1: SPEC\n```\nInstruct spec-agent (use scout or architect):\n- Analyze {source_path} using tldr-skill\n- Output: spec.md with behavioral contracts, types, edge cases\n```\n\n**Agent prompt template:**\n```\nAnalyze the codebase at {source_path} using tldr commands (tldr structure, tldr extract, tldr calls).\nCreate spec.md with:\n- All behavioral contracts (what each function\u002Fclass promises)\n- Input\u002Foutput types\n- Edge cases and invariants\n- Dependencies between components\nWrite to: {target_dir}\u002Fspec.md\n```\n\n### Phase 2: FAILING TESTS\n```\nInstruct test-agent (use arbiter):\n- Read spec.md\n- Write failing tests in {target_dir}\u002Ftests\u002F\n- Tests should define expected behavior before implementation\n\nInstruct review-agent (use critic):\n- Validate tests cover spec completely\n- No gaps in behavioral coverage\n```\n\n### Phase 3: ADVERSARIAL (x3 iterations)\n```\nInstruct premortem-agent (use premortem skill):\n- Review spec + tests\n- Identify failure modes, race conditions, edge cases\n- DO NOT ASK - just add mitigations directly to spec\n- Run 3 passes with fresh perspective each time\n```\n\n**Key:** Each pass should find NEW issues, not repeat previous ones.\n\n### Phase 4: PHASED PLAN\n```\nInstruct planner-agent (use architect or plan-agent):\n- Input: spec.md + tests + mitigations\n- Output: phased-plan.yaml\n- Requirements:\n  - Dependency-ordered phases\n  - Each phase = one testable unit\n  - Clear inputs\u002Foutputs per phase\n```\n\n### Phase 5: BUILD LOOP (per phase)\n```\nFor each phase in phased-plan.yaml:\n\n  Instruct builder-agent (use kraken or spark):\n  - Write code to pass tests for this phase\n  - Use qlty for quality checks\n  - Run tests after each change\n\n  Instruct review-agent (use critic or judge):\n  - Validate implementation matches spec\n  - Check for regressions in previous phases\n  - Verify no breaking changes\n```\n\n### Phase 6: INTEGRATION VALIDATION\n```\nInstruct integration-agent (use atlas or validator):\n- Use tldr to diff against {reference_repo}\n- Check for:\n  - No race conditions\n  - No hangs or deadlocks\n  - No breaking changes vs original\n  - All behavioral contracts preserved\n- Output: validation-report.md\n```\n\n## Invocation\n\nWhen invoking this workflow, specify:\n\n```yaml\nSOURCE: {path to source code}\nTARGET_DIR: {new folder for migrated code}\nTARGET_LANG: {typescript|python|go|rust|etc}\nREFERENCE_REPO: {url or path for final diff comparison}\nSKILLS: [tldr-code, qlty-check, {domain-specific}]\n```\n\n## Agent Mapping\n\n| Phase | Agent Type | Subagent |\n|-------|-----------|----------|\n| Spec | research | `scout` or `architect` |\n| Tests | validate | `arbiter` |\n| Review | review | `critic` or `judge` |\n| Premortem | review | `premortem` skill |\n| Plan | plan | `architect` or `plan-agent` |\n| Build | implement | `kraken` (large) or `spark` (small) |\n| Integration | validate | `atlas` or `validator` |\n\n## Example Orchestration\n\n```\n# Phase 1\nTask(scout): \"Analyze \u002Fsrc\u002Fold-system using tldr structure and tldr extract.\n              Create spec.md at \u002Fmigration\u002Fspec.md with all behavioral contracts.\"\n\n# Phase 2\nTask(arbiter): \"Read \u002Fmigration\u002Fspec.md. Write failing tests to \u002Fmigration\u002Ftests\u002F\n               that define expected behavior.\"\n\nTask(critic): \"Review \u002Fmigration\u002Fspec.md vs \u002Fmigration\u002Ftests\u002F.\n              Report any behavioral gaps.\"\n\n# Phase 3 (x3)\nTask(premortem): \"Review \u002Fmigration\u002Fspec.md and \u002Fmigration\u002Ftests\u002F.\n                 Identify failure modes. Add mitigations directly to spec. Pass 1\u002F3.\"\n[repeat with \"Pass 2\u002F3\", \"Pass 3\u002F3\"]\n\n# Phase 4\nTask(architect): \"From \u002Fmigration\u002Fspec.md and \u002Fmigration\u002Ftests\u002F,\n                 create \u002Fmigration\u002Fphased-plan.yaml with dependency-ordered phases.\"\n\n# Phase 5 (loop)\nTask(kraken): \"Implement phase 1 from \u002Fmigration\u002Fphased-plan.yaml.\n              Code goes in \u002Fmigration\u002Fsrc\u002F. Run tests after.\"\n\nTask(critic): \"Review \u002Fmigration\u002Fsrc\u002F against \u002Fmigration\u002Fspec.md.\n              Check for spec compliance and regressions.\"\n[repeat for each phase]\n\n# Phase 6\nTask(atlas): \"Run full integration tests on \u002Fmigration\u002Fsrc\u002F.\n             Use tldr to diff against \u002Fsrc\u002Fold-system.\n             Output \u002Fmigration\u002Fvalidation-report.md.\"\n```\n\n## Anti-Patterns (DO NOT)\n\n- Reading files into your context (\"let me check the code...\")\n- Writing code directly (\"I'll implement this function...\")\n- Validating anything yourself (\"looking at the tests, I see...\")\n- Modifying the source directory\n- Skipping the adversarial phase\n- Running build without tests first\n\n## Success Criteria\n\n- [ ] All tests pass\n- [ ] qlty reports clean\n- [ ] tldr diff shows no breaking changes\n- [ ] No race conditions or hangs\n- [ ] validation-report.md confirms behavioral equivalence\n",{"name":5,"description":7,"allowed-tools":43},[44,45,46,30],"Task","TodoWrite","Read","main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Ftdd-migration-pipeline","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis","https:\u002F\u002Fgithub.com\u002Frubicanjr","linktr.ee\u002Ffinanskodu","Industrial Engineer & CIO @FinansKodu. Architecting AI-driven financial agents and autonomous workflows. 🏗️ Building systems, not just prompts.","2026-06-09 13:50:15",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add rubicanjr\u002FFinCognis --skill tdd-migration-pipeline",{"tool":61,"command":62},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill tdd-migration-pipeline",{"tool":64,"command":65},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill tdd-migration-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Ftdd-migration-pipeline\u002FSKILL.md",true,[],[70,86,95,115,144,163],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":77,"publishedAt":38},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router","Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[76],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[78,28,79,80,81,82,83,84,85],"workflow router","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":87,"name":88,"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":92,"publishedAt":38},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[88,93,94],"verification","false",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":104,"publishedAt":38},"01M6NWS0XW9CVQZBDA1EGW0TWC","websocket-patterns","Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwebsocket-patterns\u002Fskill.md",[101],{"categoryNo":102,"categoryName":103,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[105,106,107,108,109,110,111,112,113,114],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":125,"publishedAt":38},"01M6NWRDQDX9ZNETAWRRMQWV52","visual-verdict","Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS\u002FREVISE\u002FFAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[121,124],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[126,127,128,129,130,131,132,133,134,37,135,136,137,108,138,139,140,141,142,143],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"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":150,"publishedAt":38},"01M6NWR8HSNRS7MNDK2J02QYMN","verification-loop","Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[151,152,93,153,154,155,156,157,158,159,160,161,162],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":38},"01M6NWR4HHSFR0VR5EXFRWA747","vector-db-patterns","Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvector-db-patterns\u002Fskill.md",[],[170,171,172,173,106,174,175,176,177,112,178,179,180,181,182,37,183,184],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]