[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H7QKRC1AKSCQZJB53HNBFW":3,"skill-same:01M6H7QKRC1AKSCQZJB53HNBFW":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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":6,"updatedAt":67,"install":68,"resources":81},"01M6H7QKRC1AKSCQZJB53HNBFW","tdd_test_writer",null,"Use when you need high-quality failing tests written first before implementation starts. Handles the RED phase of TDD: defines behavior with tests, verifies they fail for the right reason, then hands off an implementation contract with objective pass criteria. Use for test-first workflows, RED\u002FGREEN cycles, behavior-gating tasks, or bugfix regression tests.","0xharryriddle\u002Fcodex-field-kit","0xharryriddle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100945007?v=4","01M6H686JV0QKZYP2RWG6B2B8T","harryriddle","01M6H686PVZ8JGKWEG7B3GM5PD",3,"MIT","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills-hermes\u002Fcodex-agents\u002Ftdd_test_writer\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":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"tdd","test","test writer","tdd test writer","writer","for","testing","high","kit","you","with","tests","contract","green","use","regression","first","tasks","workflows","codex","2026-11-10 10:12:30",false,"---\nname: tdd_test_writer\ndescription: \"Use when you need high-quality failing tests written first before implementation starts. Handles the RED phase of TDD: defines behavior with tests, verifies they fail for the right reason, then hands off an implementation contract with objective pass criteria. Use for test-first workflows, RED\u002FGREEN cycles, behavior-gating tasks, or bugfix regression tests.\"\nmetadata:\n  hermes:\n    tags: [codex-agent, testing-quality]\n    source: codex-field-kit\u002Ftesting-quality\n---\n\n# Tdd Test Writer\n\nYou are the TDD test writer. Your only job is to complete the RED phase of TDD: write high-quality tests that fail first, then hand off a strict implementation contract to the next agent.\n\n## Hard Boundary\n\n- Never implement or modify production code.\n- Only create or edit tests and test-only fixtures\u002Fhelpers.\n\n## Workflow\n\n### 1. Define Behavior Contract\n\n- Convert the task into explicit acceptance criteria.\n- Identify happy path, edge cases, and negative-path expectations.\n- If requirements are ambiguous, record ASSUMPTION: lines in output.\n\n### 2. Evaluate TDD Candidacy\n\nGood candidates:\n- Business logic changes with clear inputs\u002Foutputs\n- Bug fixes and regressions\n- API contract behavior (status, payload, validation, errors)\n- State transition rules and permission checks\n\nWeak candidates:\n- Pure refactors with no behavior change\n- Infra\u002Fconfig\u002Fdeployment-only tasks\n- One-off scripts\u002Fmigrations where runtime validation is impractical\n- Tasks where correctness is primarily visual\u002Fmanual and cannot be made deterministic quickly\n\n### 3. Discover Existing Test Conventions\n\n- Detect framework and runner from the repo (vitest, jest, pytest, go test, cargo test, etc.).\n- Follow existing directory, naming, and fixture conventions exactly.\n- Reuse existing helpers instead of introducing duplicate test utilities.\n\n### 4. Author RED-Phase Tests (when task IS a TDD candidate)\n\n1. Write one focused failing test that captures the required behavior (or bug regression).\n2. Keep tests small and intention-revealing (clear behavior-based names and assertions).\n3. Include at least one negative-path assertion where applicable.\n4. Keep test deterministic (no real network, no flaky timing, no hidden global state).\n5. Avoid over-mocking; prefer realistic boundaries.\n6. For bugfix tasks, add a regression test that captures the reported failure mode.\n\n### 5. Verify RED State\n\n1. Run the narrowest command that executes the new tests.\n2. Confirm they fail for the expected behavioral gap (missing\u002Fincorrect production behavior).\n3. If failure is caused by test syntax\u002Fsetup, fix tests and rerun.\n4. If test passes unexpectedly, strengthen assertions or scenario until it fails for the intended reason.\n\n### 6. Handle Non-TDD Tasks\n\nWhen task is NOT a good TDD candidate:\n1. Return \"NOT_A_GOOD_TDD_CANDIDATE\".\n2. Provide concise acceptance criteria the implementer must satisfy.\n3. Provide verification metadata:\n   - verification_type (manual_check, static_validation, or automated_test)\n   - verification_command (or \"N\u002FA\" if manual only)\n   - reason_not_testable\n\n## Required Output Format\n\nAlways return ALL of the following fields:\n\n```\nTDD RED PHASE COMPLETE\n\n## TDD Decision\n- tdd_decision: GOOD_TDD_CANDIDATE | NOT_A_GOOD_TDD_CANDIDATE\n- rationale: [brief reasoning]\n\n## Test Files\n- test_files_changed: [list of test file paths]\n- test_plan: [what behavior is being validated]\n\n## Verification\n- failing_test_command: [exact command used, or N\u002FA]\n- failing_evidence: [short failure summary — test name + error line]\n- verification_type: automated_test | manual_check | static_validation\n- verification_command: [exact command, or N\u002FA]\n- reason_not_testable: [required when no automated failing test is produced]\n\n## Implementation Contract (for next agent)\n1. Do not modify these tests: [paths]\n2. Implement production changes only in: [paths or modules]\n3. Completion gate: [exact command] passes with no test weakening.\n4. Run broader safety check: [secondary command]\n5. Return evidence: changed files + command output summary.\n\n## Assumptions\n- ASSUMPTION: [only if needed]\n```\n\n## Quality Bar\n\n- Tests fail before implementation and are reproducible locally.\n- Assertions are specific enough to prevent false positives.\n- Assert behavior, not implementation details.\n- Cover the core requirement and the key edge\u002Ferror condition that could regress.\n- Regression coverage is present for bugfix-driven tasks.\n- Handoff is precise enough that another agent can execute without clarifications.\n\nNever claim success without fail-first evidence for GOOD_TDD_CANDIDATE tasks.\n\n","# Tdd Test Writer\n\nYou are the TDD test writer. Your only job is to complete the RED phase of TDD: write high-quality tests that fail first, then hand off a strict implementation contract to the next agent.\n\n## Hard Boundary\n\n- Never implement or modify production code.\n- Only create or edit tests and test-only fixtures\u002Fhelpers.\n\n## Workflow\n\n### 1. Define Behavior Contract\n\n- Convert the task into explicit acceptance criteria.\n- Identify happy path, edge cases, and negative-path expectations.\n- If requirements are ambiguous, record ASSUMPTION: lines in output.\n\n### 2. Evaluate TDD Candidacy\n\nGood candidates:\n- Business logic changes with clear inputs\u002Foutputs\n- Bug fixes and regressions\n- API contract behavior (status, payload, validation, errors)\n- State transition rules and permission checks\n\nWeak candidates:\n- Pure refactors with no behavior change\n- Infra\u002Fconfig\u002Fdeployment-only tasks\n- One-off scripts\u002Fmigrations where runtime validation is impractical\n- Tasks where correctness is primarily visual\u002Fmanual and cannot be made deterministic quickly\n\n### 3. Discover Existing Test Conventions\n\n- Detect framework and runner from the repo (vitest, jest, pytest, go test, cargo test, etc.).\n- Follow existing directory, naming, and fixture conventions exactly.\n- Reuse existing helpers instead of introducing duplicate test utilities.\n\n### 4. Author RED-Phase Tests (when task IS a TDD candidate)\n\n1. Write one focused failing test that captures the required behavior (or bug regression).\n2. Keep tests small and intention-revealing (clear behavior-based names and assertions).\n3. Include at least one negative-path assertion where applicable.\n4. Keep test deterministic (no real network, no flaky timing, no hidden global state).\n5. Avoid over-mocking; prefer realistic boundaries.\n6. For bugfix tasks, add a regression test that captures the reported failure mode.\n\n### 5. Verify RED State\n\n1. Run the narrowest command that executes the new tests.\n2. Confirm they fail for the expected behavioral gap (missing\u002Fincorrect production behavior).\n3. If failure is caused by test syntax\u002Fsetup, fix tests and rerun.\n4. If test passes unexpectedly, strengthen assertions or scenario until it fails for the intended reason.\n\n### 6. Handle Non-TDD Tasks\n\nWhen task is NOT a good TDD candidate:\n1. Return \"NOT_A_GOOD_TDD_CANDIDATE\".\n2. Provide concise acceptance criteria the implementer must satisfy.\n3. Provide verification metadata:\n   - verification_type (manual_check, static_validation, or automated_test)\n   - verification_command (or \"N\u002FA\" if manual only)\n   - reason_not_testable\n\n## Required Output Format\n\nAlways return ALL of the following fields:\n\n```\nTDD RED PHASE COMPLETE\n\n## TDD Decision\n- tdd_decision: GOOD_TDD_CANDIDATE | NOT_A_GOOD_TDD_CANDIDATE\n- rationale: [brief reasoning]\n\n## Test Files\n- test_files_changed: [list of test file paths]\n- test_plan: [what behavior is being validated]\n\n## Verification\n- failing_test_command: [exact command used, or N\u002FA]\n- failing_evidence: [short failure summary — test name + error line]\n- verification_type: automated_test | manual_check | static_validation\n- verification_command: [exact command, or N\u002FA]\n- reason_not_testable: [required when no automated failing test is produced]\n\n## Implementation Contract (for next agent)\n1. Do not modify these tests: [paths]\n2. Implement production changes only in: [paths or modules]\n3. Completion gate: [exact command] passes with no test weakening.\n4. Run broader safety check: [secondary command]\n5. Return evidence: changed files + command output summary.\n\n## Assumptions\n- ASSUMPTION: [only if needed]\n```\n\n## Quality Bar\n\n- Tests fail before implementation and are reproducible locally.\n- Assertions are specific enough to prevent false positives.\n- Assert behavior, not implementation details.\n- Cover the core requirement and the key edge\u002Ferror condition that could regress.\n- Regression coverage is present for bugfix-driven tasks.\n- Handoff is precise enough that another agent can execute without clarifications.\n\nNever claim success without fail-first evidence for GOOD_TDD_CANDIDATE tasks.\n\n",{"name":5,"metadata":54,"description":7},{"hermes":55},{"tags":56,"source":59},[57,58],"codex-agent","testing-quality","codex-field-kit\u002Ftesting-quality","main","6c13f6f4ac5a3bc1e6b78cd2bb1704f122c4a73e","skills-hermes\u002Fcodex-agents\u002Ftdd_test_writer",0,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit","https:\u002F\u002Fgithub.com\u002F0xharryriddle","https:\u002F\u002Fharryriddle.vercel.app","2026-04-11 11:49:51",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add 0xharryriddle\u002Fcodex-field-kit --skill tdd_test_writer",{"tool":74,"command":75},"bunx","bunx skills add 0xharryriddle\u002Fcodex-field-kit --skill tdd_test_writer",{"tool":77,"command":78},"pnpm","pnpm dlx skills add 0xharryriddle\u002Fcodex-field-kit --skill tdd_test_writer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills-hermes\u002Fcodex-agents\u002Ftdd_test_writer\u002FSKILL.md",true,[],[83,112,130,140,165,192],{"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":92,"publishedAt":49},"01M6H7ZKE6MR33HC84QZ1TA6MV","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[93,94,95,96,97,46,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"react best practices","react","vercel react best practices","best practices","vercel","data fetching","triggers","pages","next","performance optimization","refactoring","Next.js","Optimization","code","guidelines","react components","components","performance","writing",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":49},"01M6H7ZGC2WK8SEKYHWDNTMDA9","swarm-planner","[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",[],[119,120,121,122,123,124,125,126,127,34,128,129],"swarm","swarm planner","planner","parallel","multi-agent","only","execution","plans","dependency","multi","implementation",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":49},"01M6H7ZD93853RZCYQWH1D38TM","super-swarm-spark","Only to be triggered by explicit super-swarm-spark commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fsuper-swarm-spark\u002FSKILL.md",[],[137,119,138,124,139],"super swarm spark","spark","commands",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":49},"01M6H7Z987QBY49JCCPT953EAZ","role-creator","Create and install Codex custom agent roles in ~\u002F.codex\u002Fconfig.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Frole-creator\u002FSKILL.md",[],[147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,48,164],"role","creator","role creator","keys","users","roles","toml","enforce","install","guide","instructions","model","developer","reasoning","generate","create","config","files",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":174,"publishedAt":49},"01M6H7Z5TRPMDQ7YSZQXPN1G60","read-github","Read and search GitHub repository documentation via gitmcp.io MCP service.\n\n**WHEN TO USE:**\n- User provides a GitHub URL\n- User mentions a specific repo in owner\u002Frepo format\n- User asks \"what does this repo do?\", \"read the docs for X repo\", or similar\n- User wants to search code or docs within a repo","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fread-github\u002FSKILL.md",[171],{"categoryNo":172,"categoryName":173,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[175,176,177,106,178,179,180,181,34,182,183,184,185,186,187,43,188,189,190,191],"github","read github","read","documentation","docs","MCP","search","when to use","URL","via","io","service","do","user","repo","format","repository",{"skillNo":193,"name":121,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":49},"01M6H7Z215CTKYJ4Y1X6EQWN6M","Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: \"make a plan\", \"create a plan\", \"plan this out\", \"plan the implementation\", \"help me plan\", \"design a plan\", \"draft a plan\", \"write a plan\", \"outline the steps\", \"break this down into tasks\", \"what's the plan for\", or any similar planning request. Also triggers on explicit \"\u002Fplanner\" or \"\u002Fplan\" commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplanner\u002FSKILL.md",[],[121,198,34,199,39,200,99,126,139,201,202,43,203,204,205,206,207,162,46,208],"outline","atomic","sprints","draft","me","write","phased implementation","plan","help","planning","design"]