{
  "schemaVersion": "1.0",
  "item": {
    "slug": "quality-driven-dev",
    "name": "Quality-Driven Development (QDD)",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/kimky1122/quality-driven-dev",
    "canonicalUrl": "https://clawhub.ai/kimky1122/quality-driven-dev",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/quality-driven-dev",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=quality-driven-dev",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/ddd-patterns.md",
      "references/tdd-patterns.md",
      "references/trust5-checklist.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/quality-driven-dev"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/quality-driven-dev",
    "agentPageUrl": "https://openagent3.xyz/skills/quality-driven-dev/agent",
    "manifestUrl": "https://openagent3.xyz/skills/quality-driven-dev/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/quality-driven-dev/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Quality-Driven Development",
        "body": "Structured development methodology inspired by MoAI-ADK's TRUST 5 framework. Automatically selects TDD or DDD based on project state, enforces quality gates, and produces tested, documented code."
      },
      {
        "title": "Core Philosophy",
        "body": "\"바이브 코딩의 목적은 빠른 생산성이 아니라 코드 품질이다.\""
      },
      {
        "title": "Logging Strategy",
        "body": "All code must include meaningful logs. Logs are the first line of defense for debugging production issues."
      },
      {
        "title": "Log Levels",
        "body": "LevelPurposeExamples운영(PRD)개발(DEV)ERROR예외, 실패, 복구 불가 상황catch 블록, DB 연결 실패, 필수값 누락✅✅WARN예상 밖 상황, 복구 가능fallback 사용, 재시도, deprecated 호출✅✅INFO핵심 흐름만 간결하게API 호출/응답, 상태 변경, 트랜잭션 시작/완료✅✅DEBUG상세 디버깅, 자유롭게함수 진입/종료, 변수값, 조건 분기, 쿼리 파라미터❌✅"
      },
      {
        "title": "Log Placement Rules",
        "body": "반드시 로그를 넣어야 하는 곳:\n\nAPI 엔드포인트 진입 (INFO: 요청 파라미터 요약)\n외부 서비스 호출 전/후 (INFO: 호출 대상, 응답 상태)\n에러/예외 catch 블록 (ERROR: 에러 메시지 + 컨텍스트)\n비즈니스 로직 분기점 (DEBUG: 어떤 분기로 갔는지)\n상태 변경 (INFO: before → after)\n배치/스케줄러 시작/완료 (INFO: 처리 건수, 소요 시간)\n\n로그 작성 원칙:\n\n운영에서 INFO만으로 흐름 추적이 가능해야 한다\nDEBUG는 부담 없이 자유롭게 — 운영에선 출력 안 됨\n민감 정보(비밀번호, 토큰, 개인정보) 절대 로그에 포함 금지\n로그 메시지에 컨텍스트 포함 (ID, 파라미터 등) — \"처리 실패\" ❌ → \"주문 처리 실패 [orderId=123, reason=재고부족]\" ✅"
      },
      {
        "title": "Phase 0: Project Analysis",
        "body": "Before any coding, analyze the project:\n\nCheck if test framework exists (jest, vitest, pytest, go test, etc.)\nMeasure current test coverage (run coverage command if available)\nDetect language, framework, and project structure\nIdentify logging framework (slf4j, winston, pino, logback, print/console.log etc.) — if none exists, recommend and set up one\nSelect methodology automatically:\n\nCoverage >= 10% OR new project → TDD (default)\nCoverage < 10% AND existing project → DDD\n\nReport the analysis result and selected methodology to the user before proceeding."
      },
      {
        "title": "Phase 1: SPEC Document",
        "body": "Create a SPEC document before implementation:\n\n# SPEC-{ID}: {Title}\n\n## Goal\nOne sentence describing what this change achieves.\n\n## Acceptance Criteria\n- [ ] Criterion 1 (testable)\n- [ ] Criterion 2 (testable)\n- [ ] Criterion 3 (testable)\n\n## Scope\n- **In scope:** What will be changed\n- **Out of scope:** What will NOT be changed\n\n## Technical Approach\nBrief description of implementation strategy.\n\n## Log Points\nKey locations where logs will be added (level + message summary).\n\n## TRUST 5 Checklist\n- [ ] **Tested:** All acceptance criteria have corresponding tests\n- [ ] **Readable:** Code is self-documenting with clear naming\n- [ ] **Unified:** Follows existing project conventions\n- [ ] **Secured:** No new vulnerabilities introduced\n- [ ] **Trackable:** Changes are documented and linked to this SPEC"
      },
      {
        "title": "Phase 2A: TDD Execution (New Projects / Coverage >= 10%)",
        "body": "Follow RED → GREEN → REFACTOR strictly:\n\nRED — Write failing tests first\n\nWrite test for first acceptance criterion\nRun test — confirm it FAILS\nReport: \"🔴 RED: Test written and failing as expected\"\n\nGREEN — Minimal implementation\n\nWrite minimum code to pass the test\nAdd appropriate logs at key points (API calls, error handling, state changes)\nRun test — confirm it PASSES\nReport: \"🟢 GREEN: Test passing\"\n\nREFACTOR — Clean up\n\nImprove code quality while keeping tests green\nReview log quality — ensure levels are correct, messages are clear with context\nRun all tests — confirm everything still passes\nReport: \"♻️ REFACTOR: Code cleaned, all tests green\"\n\nRepeat for each acceptance criterion."
      },
      {
        "title": "Phase 2B: DDD Execution (Existing Projects / Coverage < 10%)",
        "body": "Follow ANALYZE → PRESERVE → IMPROVE:\n\nANALYZE — Understand existing code\n\nRead existing code and identify dependencies\nMap domain boundaries and side effects\nCheck existing logging — identify gaps where logs are missing\nReport: \"🔍 ANALYZE: Current behavior documented\"\n\nPRESERVE — Capture current behavior\n\nWrite characterization tests for existing behavior\nRun tests — confirm they pass against current code\nReport: \"🛡️ PRESERVE: Characterization tests in place\"\n\nIMPROVE — Change under test protection\n\nMake changes incrementally\nAdd/improve logs at changed code paths\nRun tests after each change\nReport: \"📈 IMPROVE: Changes verified by tests\""
      },
      {
        "title": "Phase 3: TRUST 5 Quality Gate",
        "body": "Before declaring work complete, verify all 5 principles:\n\nPrincipleCheckActionTestedRun full test suiteAll tests pass, coverage maintained or improvedReadableReview naming, comments, log messagesFix unclear names, ensure log messages have contextUnifiedCheck style consistency, log format consistencyMatch existing patterns (indent, naming, log format)SecuredSecurity review, log content reviewNo hardcoded secrets, no sensitive data in logsTrackableDocumentation, log coverageChanges described, key paths have appropriate logs\n\nOnly proceed to completion when ALL 5 checks pass."
      },
      {
        "title": "Phase 4: Completion Report",
        "body": "## ✅ SPEC-{ID} Complete\n\n### Methodology: {TDD|DDD}\n### Changes:\n- {file1}: {what changed}\n- {file2}: {what changed}\n\n### Log Points Added:\n- {file1:line}: {level} - {description}\n- {file2:line}: {level} - {description}\n\n### Test Results:\n- Tests: {passed}/{total}\n- Coverage: {before}% → {after}%\n\n### TRUST 5:\n- ✅ Tested | ✅ Readable | ✅ Unified | ✅ Secured | ✅ Trackable"
      },
      {
        "title": "Agent Roles",
        "body": "When working on complex tasks, delegate to specialized perspectives:\n\nRoleFocusWhen to ActivateArchitectSystem design, API contractsNew feature, structural changeBackendAPI, DB, business logicServer-side workFrontendUI, UX, componentsClient-side workSecurityVulnerabilities, auth, input validationAuth features, data handlingTesterTest strategy, edge cases, coverageAlways (TRUST 5 - Tested)PerformanceOptimization, profilingLoad-sensitive features\n\nFor each task, identify which roles are relevant and apply their perspective during review."
      },
      {
        "title": "Reference Guides",
        "body": "TopicReferenceLoad WhenTDD Patternsreferences/tdd-patterns.mdTDD methodology selectedDDD Patternsreferences/ddd-patterns.mdDDD methodology selectedTRUST 5 Detailreferences/trust5-checklist.mdQuality gate phaseLanguage-specificreferences/lang-{language}.mdLanguage-specific patterns needed"
      },
      {
        "title": "Constraints",
        "body": "MUST DO:\n\nAlways analyze project before choosing methodology\nAlways create SPEC before coding\nAlways write tests (TDD: before code, DDD: before changes)\nAlways run TRUST 5 gate before completion\nReport progress at each phase transition\nAlways add meaningful logs with appropriate levels at key code points\nAlways ensure tests are actually executed (not just written) — run the test suite and confirm results before proceeding\n\nMUST NOT:\n\nSkip test writing for any reason\nWrite implementation before tests (TDD mode)\nModify untested code without characterization tests first (DDD mode)\nDeclare complete without all 5 TRUST checks passing\nChange code outside the SPEC scope\nLog sensitive data (passwords, tokens, personal info)\nSkip logging at error/catch blocks"
      }
    ],
    "body": "Quality-Driven Development\n\nStructured development methodology inspired by MoAI-ADK's TRUST 5 framework. Automatically selects TDD or DDD based on project state, enforces quality gates, and produces tested, documented code.\n\nCore Philosophy\n\n\"바이브 코딩의 목적은 빠른 생산성이 아니라 코드 품질이다.\"\n\nLogging Strategy\n\nAll code must include meaningful logs. Logs are the first line of defense for debugging production issues.\n\nLog Levels\nLevel\tPurpose\tExamples\t운영(PRD)\t개발(DEV)\nERROR\t예외, 실패, 복구 불가 상황\tcatch 블록, DB 연결 실패, 필수값 누락\t✅\t✅\nWARN\t예상 밖 상황, 복구 가능\tfallback 사용, 재시도, deprecated 호출\t✅\t✅\nINFO\t핵심 흐름만 간결하게\tAPI 호출/응답, 상태 변경, 트랜잭션 시작/완료\t✅\t✅\nDEBUG\t상세 디버깅, 자유롭게\t함수 진입/종료, 변수값, 조건 분기, 쿼리 파라미터\t❌\t✅\nLog Placement Rules\n\n반드시 로그를 넣어야 하는 곳:\n\nAPI 엔드포인트 진입 (INFO: 요청 파라미터 요약)\n외부 서비스 호출 전/후 (INFO: 호출 대상, 응답 상태)\n에러/예외 catch 블록 (ERROR: 에러 메시지 + 컨텍스트)\n비즈니스 로직 분기점 (DEBUG: 어떤 분기로 갔는지)\n상태 변경 (INFO: before → after)\n배치/스케줄러 시작/완료 (INFO: 처리 건수, 소요 시간)\n\n로그 작성 원칙:\n\n운영에서 INFO만으로 흐름 추적이 가능해야 한다\nDEBUG는 부담 없이 자유롭게 — 운영에선 출력 안 됨\n민감 정보(비밀번호, 토큰, 개인정보) 절대 로그에 포함 금지\n로그 메시지에 컨텍스트 포함 (ID, 파라미터 등) — \"처리 실패\" ❌ → \"주문 처리 실패 [orderId=123, reason=재고부족]\" ✅\nWorkflow\nPhase 0: Project Analysis\n\nBefore any coding, analyze the project:\n\nCheck if test framework exists (jest, vitest, pytest, go test, etc.)\nMeasure current test coverage (run coverage command if available)\nDetect language, framework, and project structure\nIdentify logging framework (slf4j, winston, pino, logback, print/console.log etc.) — if none exists, recommend and set up one\nSelect methodology automatically:\nCoverage >= 10% OR new project → TDD (default)\nCoverage < 10% AND existing project → DDD\n\n\nReport the analysis result and selected methodology to the user before proceeding.\n\nPhase 1: SPEC Document\n\nCreate a SPEC document before implementation:\n\n# SPEC-{ID}: {Title}\n\n## Goal\nOne sentence describing what this change achieves.\n\n## Acceptance Criteria\n- [ ] Criterion 1 (testable)\n- [ ] Criterion 2 (testable)\n- [ ] Criterion 3 (testable)\n\n## Scope\n- **In scope:** What will be changed\n- **Out of scope:** What will NOT be changed\n\n## Technical Approach\nBrief description of implementation strategy.\n\n## Log Points\nKey locations where logs will be added (level + message summary).\n\n## TRUST 5 Checklist\n- [ ] **Tested:** All acceptance criteria have corresponding tests\n- [ ] **Readable:** Code is self-documenting with clear naming\n- [ ] **Unified:** Follows existing project conventions\n- [ ] **Secured:** No new vulnerabilities introduced\n- [ ] **Trackable:** Changes are documented and linked to this SPEC\n\nPhase 2A: TDD Execution (New Projects / Coverage >= 10%)\n\nFollow RED → GREEN → REFACTOR strictly:\n\nRED — Write failing tests first\n\nWrite test for first acceptance criterion\nRun test — confirm it FAILS\nReport: \"🔴 RED: Test written and failing as expected\"\n\nGREEN — Minimal implementation\n\nWrite minimum code to pass the test\nAdd appropriate logs at key points (API calls, error handling, state changes)\nRun test — confirm it PASSES\nReport: \"🟢 GREEN: Test passing\"\n\nREFACTOR — Clean up\n\nImprove code quality while keeping tests green\nReview log quality — ensure levels are correct, messages are clear with context\nRun all tests — confirm everything still passes\nReport: \"♻️ REFACTOR: Code cleaned, all tests green\"\n\nRepeat for each acceptance criterion.\n\nPhase 2B: DDD Execution (Existing Projects / Coverage < 10%)\n\nFollow ANALYZE → PRESERVE → IMPROVE:\n\nANALYZE — Understand existing code\n\nRead existing code and identify dependencies\nMap domain boundaries and side effects\nCheck existing logging — identify gaps where logs are missing\nReport: \"🔍 ANALYZE: Current behavior documented\"\n\nPRESERVE — Capture current behavior\n\nWrite characterization tests for existing behavior\nRun tests — confirm they pass against current code\nReport: \"🛡️ PRESERVE: Characterization tests in place\"\n\nIMPROVE — Change under test protection\n\nMake changes incrementally\nAdd/improve logs at changed code paths\nRun tests after each change\nReport: \"📈 IMPROVE: Changes verified by tests\"\nPhase 3: TRUST 5 Quality Gate\n\nBefore declaring work complete, verify all 5 principles:\n\nPrinciple\tCheck\tAction\nTested\tRun full test suite\tAll tests pass, coverage maintained or improved\nReadable\tReview naming, comments, log messages\tFix unclear names, ensure log messages have context\nUnified\tCheck style consistency, log format consistency\tMatch existing patterns (indent, naming, log format)\nSecured\tSecurity review, log content review\tNo hardcoded secrets, no sensitive data in logs\nTrackable\tDocumentation, log coverage\tChanges described, key paths have appropriate logs\n\nOnly proceed to completion when ALL 5 checks pass.\n\nPhase 4: Completion Report\n## ✅ SPEC-{ID} Complete\n\n### Methodology: {TDD|DDD}\n### Changes:\n- {file1}: {what changed}\n- {file2}: {what changed}\n\n### Log Points Added:\n- {file1:line}: {level} - {description}\n- {file2:line}: {level} - {description}\n\n### Test Results:\n- Tests: {passed}/{total}\n- Coverage: {before}% → {after}%\n\n### TRUST 5:\n- ✅ Tested | ✅ Readable | ✅ Unified | ✅ Secured | ✅ Trackable\n\nAgent Roles\n\nWhen working on complex tasks, delegate to specialized perspectives:\n\nRole\tFocus\tWhen to Activate\nArchitect\tSystem design, API contracts\tNew feature, structural change\nBackend\tAPI, DB, business logic\tServer-side work\nFrontend\tUI, UX, components\tClient-side work\nSecurity\tVulnerabilities, auth, input validation\tAuth features, data handling\nTester\tTest strategy, edge cases, coverage\tAlways (TRUST 5 - Tested)\nPerformance\tOptimization, profiling\tLoad-sensitive features\n\nFor each task, identify which roles are relevant and apply their perspective during review.\n\nReference Guides\nTopic\tReference\tLoad When\nTDD Patterns\treferences/tdd-patterns.md\tTDD methodology selected\nDDD Patterns\treferences/ddd-patterns.md\tDDD methodology selected\nTRUST 5 Detail\treferences/trust5-checklist.md\tQuality gate phase\nLanguage-specific\treferences/lang-{language}.md\tLanguage-specific patterns needed\nConstraints\n\nMUST DO:\n\nAlways analyze project before choosing methodology\nAlways create SPEC before coding\nAlways write tests (TDD: before code, DDD: before changes)\nAlways run TRUST 5 gate before completion\nReport progress at each phase transition\nAlways add meaningful logs with appropriate levels at key code points\nAlways ensure tests are actually executed (not just written) — run the test suite and confirm results before proceeding\n\nMUST NOT:\n\nSkip test writing for any reason\nWrite implementation before tests (TDD mode)\nModify untested code without characterization tests first (DDD mode)\nDeclare complete without all 5 TRUST checks passing\nChange code outside the SPEC scope\nLog sensitive data (passwords, tokens, personal info)\nSkip logging at error/catch blocks"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/kimky1122/quality-driven-dev",
    "publisherUrl": "https://clawhub.ai/kimky1122/quality-driven-dev",
    "owner": "kimky1122",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/quality-driven-dev",
    "downloadUrl": "https://openagent3.xyz/downloads/quality-driven-dev",
    "agentUrl": "https://openagent3.xyz/skills/quality-driven-dev/agent",
    "manifestUrl": "https://openagent3.xyz/skills/quality-driven-dev/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/quality-driven-dev/agent.md"
  }
}