{"id":"997118ab-b159-41bf-ab5a-f78b6f3cff3a","entityType":"agent","slug":"clawhub-kokxi-qa-shift-left","name":"qa-shift-left","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kokxi-qa-shift-left","canonicalPath":"/agent/clawhub-kokxi-qa-shift-left","generatedAt":"2026-10-11T14:13:34.085Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T10:04:12.790Z","emptyReason":null},"description":"当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design during development, and technical design review. Skill: qa-shift-left Owner: kokxi Summary: 当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-shift-left","sourceUrl":"https://clawhub.ai/kokxi/qa-shift-left","homepage":"https://clawhub.ai/kokxi/skills/qa-shift-left","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/kokxi/qa-shift-left","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/kokxi/skills/qa-shift-left","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T10:04:12.790Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T10:04:12.790Z","emptyReason":null},"stars":null,"forks":null,"downloads":1092,"packageName":null,"latestVersion":"1.8.0","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T10:04:12.719Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T10:04:12.790Z","lastCrawledAt":"2026-10-11T10:04:12.719Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T10:04:12.719Z","lastVerifiedAt":null,"highlights":[{"version":"1.8.0","createdAt":"2026-09-29T04:28:12.420Z","changelog":"## qa-shift-left v1.8.0 Changelog - Major content for“左移阶段”已下沉至 references/shift-left-stages.md，优化主页面信息密度和上下文占用。 - 增加 metadata 字段（display-name, version, 相关用法、输入输出、引用、深度、容错等），结构更标准化。 - skill-card.md已删除，精简冗余元数据文件。 - 触发场景、上下游技能、输入输出结构等内容整合至 metadata 方便平台解析。 - 其余操作指南、可测试性、评审和单元测试清单保持不变。","fileCount":4,"zipByteSize":4989},{"version":"1.7.7","createdAt":"2026-09-27T14:40:23.626Z","changelog":"1.7.7","fileCount":3,"zipByteSize":4436},{"version":"1.7.6","createdAt":"2026-09-01T12:45:01.529Z","changelog":"显示名改中文","fileCount":3,"zipByteSize":4725},{"version":"1.7.5","createdAt":"2026-08-30T15:18:13.795Z","changelog":"1.7.5: 版本号升级","fileCount":3,"zipByteSize":4592},{"version":"1.7.0","createdAt":"2026-08-16T14:32:31.669Z","changelog":"Version 1.7.0 - Removed the file skill-card.md. - Updated SKILL.md with no significant user-facing changes observed. - Housekeeping update to project structure.","fileCount":3,"zipByteSize":4297},{"version":"1.6.3","createdAt":"2026-08-12T15:27:13.055Z","changelog":"- Added slug and displayName fields to metadata for improved identification and display. - Updated version to 1.6.3. - skill-card.md file has been removed. - No changes to core logic or usage; documentation and metadata improvements only.","fileCount":3,"zipByteSize":4146},{"version":"1.6.0","createdAt":"2026-07-06T17:17:15.714Z","changelog":"Version 1.6.0 introduces enhanced structure, traceability, and error recovery guidance. - SKILL.md updated: added new YAML fields for traceability, categories, depth quantification, and error recovery. - when_to_use triggers improved for clarity and specificity. - output_format now specifies traceability info, not just structure. - Guidance for minimum left-shift involvement and quantification of depth included. - Error recovery instructions detailed for missed testability points. - File skill-card.md removed.","fileCount":3,"zipByteSize":4387},{"version":"1.5.0","createdAt":"2026-06-29T12:35:11.524Z","changelog":"Version 1.5.0 - Introduced structured input and output formats for skill activation and results. - Added required inputs: 项目计划 (project timeline), 质量目标 (quality goals); optional input for 团队能力 (team skill assessment). - Defined output sections: 左移测试计划, 早期介入活动清单, 前置质量门禁, 团队赋能计划. - Updated and clarified skill description for applicability at early project phases. - Removed redundant file (skill-card.md), consolidated documentation.","fileCount":3,"zipByteSize":4113}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-shift-left","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T14:13:34.084Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-shift-left/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T10:04:12.790Z","emptyReason":null},"readme":"Skill: qa-shift-left\n\nOwner: kokxi\n\nSummary: 当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design during development, and technical design review.\n\nTags: latest:1.8.0\n\nVersion history:\n\nv1.8.0 | 2026-09-29T04:28:12.420Z | auto\n\n## qa-shift-left v1.8.0 Changelog\n\n- Major content for“左移阶段”已下沉至 references/shift-left-stages.md，优化主页面信息密度和上下文占用。\n- 增加 metadata 字段（display-name, version, 相关用法、输入输出、引用、深度、容错等），结构更标准化。\n- skill-card.md已删除，精简冗余元数据文件。\n- 触发场景、上下游技能、输入输出结构等内容整合至 metadata 方便平台解析。\n- 其余操作指南、可测试性、评审和单元测试清单保持不变。\n\nv1.7.7 | 2026-09-27T14:40:23.626Z | user\n\n1.7.7\n\nv1.7.6 | 2026-09-01T12:45:01.529Z | user\n\n显示名改中文\n\nv1.7.5 | 2026-08-30T15:18:13.795Z | user\n\n1.7.5: 版本号升级\n\nv1.7.0 | 2026-08-16T14:32:31.669Z | auto\n\nVersion 1.7.0\n\n- Removed the file skill-card.md.\n- Updated SKILL.md with no significant user-facing changes observed.\n- Housekeeping update to project structure.\n\nv1.6.3 | 2026-08-12T15:27:13.055Z | auto\n\n- Added slug and displayName fields to metadata for improved identification and display.\n- Updated version to 1.6.3.\n- skill-card.md file has been removed.\n- No changes to core logic or usage; documentation and metadata improvements only.\n\nv1.6.0 | 2026-07-06T17:17:15.714Z | auto\n\nVersion 1.6.0 introduces enhanced structure, traceability, and error recovery guidance.\n\n- SKILL.md updated: added new YAML fields for traceability, categories, depth quantification, and error recovery.\n- when_to_use triggers improved for clarity and specificity.\n- output_format now specifies traceability info, not just structure.\n- Guidance for minimum left-shift involvement and quantification of depth included.\n- Error recovery instructions detailed for missed testability points.\n- File skill-card.md removed.\n\nv1.5.0 | 2026-06-29T12:35:11.524Z | auto\n\nVersion 1.5.0\n\n- Introduced structured input and output formats for skill activation and results.\n- Added required inputs: 项目计划 (project timeline), 质量目标 (quality goals); optional input for 团队能力 (team skill assessment).\n- Defined output sections: 左移测试计划, 早期介入活动清单, 前置质量门禁, 团队赋能计划.\n- Updated and clarified skill description for applicability at early project phases.\n- Removed redundant file (skill-card.md), consolidated documentation.\n\nv1.4.1 | 2026-06-25T16:56:22.534Z | auto\n\n- Updated and streamlined SKILL.md: improved the description for clarity and brevity.\n- Removed the file skill-card.md.\n- No changes to left-shift methodology or use cases; primarily documentation cleanup.\n\nv1.4.0 | 2026-06-24T05:11:31.090Z | auto\n\nqa-shift-left 1.4.0\n\n- Added detailed phases and activities for shifting testing left across requirement, design, and development stages.\n- Provided templates and checklists for acceptance criteria, testability, code review, and unit test support.\n- Expanded usage scenarios and keywords for automatic triggering.\n- Included practical examples and post-implementation guidelines to clarify left-shift practices.\n\nArchive index:\n\nArchive v1.8.0: 4 files, 4989 bytes\n\nFiles: references/shift-left-stages.md (1957b), skill-card.md (1556b), SKILL.md (6261b), _meta.json (132b)\n\nFile v1.8.0:SKILL.md\n\n---\nname: qa-shift-left\ndescription: >-\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design during development, and technical design review.\nlicense: MIT\nallowed-tools: Read Grep Glob Bash\nmetadata:\n  display-name: \"Shift Left\"\n  version: \"1.8.0\"\n  when-to-use: \"用户说\\\"测试左移\\\"、\\\"左移\\\"、\\\"提前测试\\\"、\\\"需求可测试性（左移阶段）\\\"、\\\"需求评审（左移介入）\\\"、\\\"开发阶段测\\\"、需要将测试提前、项目早期需要介入测试时\"\n  related-skills: \"{\\\"upstream\\\":[\\\"qa-req-deconstruction\\\",\\\"qa-testability-advocacy\\\"],\\\"downstream\\\":[\\\"qa-code-review-for-test\\\",\\\"qa-test-automation-arch\\\"]}\"\n  references: \"[\\\"references/shift-left-stages.md\\\"]\"\n  input-format: \"{\\\"required\\\":[{\\\"name\\\":\\\"项目计划\\\",\\\"type\\\":\\\"string\\\",\\\"description\\\":\\\"项目时间线和阶段规划\\\"},{\\\"name\\\":\\\"质量目标\\\",\\\"type\\\":\\\"string\\\",\\\"description\\\":\\\"项目质量目标和标准\\\"}],\\\"optional\\\":[{\\\"name\\\":\\\"团队能力\\\",\\\"type\\\":\\\"string\\\",\\\"description\\\":\\\"团队测试技能评估\\\"}]}\"\n  output-format: \"{\\\"traceability\\\":[\\\"本技能规划左移，不产出唯一ID；可溯源到需求评审ID\\\"],\\\"structure\\\":[{\\\"shift_left_plan\\\":\\\"左移测试计划\\\"},{\\\"early_activities\\\":\\\"早期介入活动清单\\\"},{\\\"quality_gates_early\\\":\\\"前置质量门禁\\\"},{\\\"team_enablement\\\":\\\"团队赋能计划\\\"}]}\"\n  error-recovery-guidance: \"{\\\"on_failure\\\":\\\"左移介入遗漏可测试性问题时回退到需求评审补充\\\",\\\"retry_behavior\\\":\\\"补充评审后重新评估左移点\\\"}\"\n  categories: \"[\\\"Development\\\",\\\"Testing\\\",\\\"DevOps\\\"]\"\n  depth-requirement: \"{\\\"reference_value\\\":\\\"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\\\",\\\"minimum\\\":\\\"至少覆盖需求可测试性评审、开发阶段测试2个介入点\\\"}\"\n---\n> ⚠️ 本技能单独使用效果有限，建议配合完整技能集（12 步工作流）使用。安装：npx skills add Kokxi/qa-test-skills\n\n# 测试左移实践\n\n## 核心原则\n\n测试左移——越早发现缺陷，修复成本越低。\n\n## 加载时机\n\n| 什么时候读 | 读哪个 |\n|-----------|--------|\n| 介入需求/设计/开发阶段时 | [`references/shift-left-stages.md`](references/shift-left-stages.md) |\n\n> `左移阶段`的完整内容已下沉至 `references/shift-left-stages.md`，避免每次触发都占用上下文。\n\n## 需求可测试性\n\n### 验收标准模板\n\n```markdown\n## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试\n```\n\n### 可测试性检查清单\n\n```text\n接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？\n```\n\n## 代码评审检查点\n\n### 测试视角的CR\n\n```text\n检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？\n```\n\n## 单元测试支持\n\n### 单元测试检查清单\n\n```text\n覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├─ [ ] 分支覆盖？\n├─ [ ] 边界覆盖？\n└─ [ ] 异常覆盖？\n\n质量：\n├─ [ ] 测试命名清晰？\n├─ [ ] 测试职责单一？\n├─ [ ] 测试独立运行？\n├─ [ ] 测试快速执行？\n└─ [ ] 测试可维护？\n```\n\n## 输出示例\n\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\n→ 左移实践：\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\n\n**用户说\"怎么减少线上Bug\"**\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\n\n## 检查清单\n\n测试左移实施后检查：\n- [ ] 需求评审是否参与？\n- [ ] 验收标准是否定义？\n- [ ] 可测试性是否评估？\n- [ ] 代码评审是否执行？\n- [ ] 单元测试是否支持？\n- [ ] 接口测试是否实施？\n\nFile v1.8.0:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.8.0\",\n  \"publishedAt\": 1790656092420\n}\n\nFile v1.8.0:references/shift-left-stages.md\n\n# 测试左移三阶段详解\n\n> 本文是 `qa-shift-left` 的**测试左移三阶段详解**。介入需求/设计/开发阶段时读本文；\n其余部分留在 SKILL.md，不必读本文。\n\n---\n\n\n### 阶段1：需求阶段\n\n```text\n测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造\n```\n\n### 阶段2：设计阶段\n\n```text\n测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性\n```\n\n### 阶段3：开发阶段\n\n```text\n测试活动：\n├─ 代码评审\n│   ├─ 从测试角度Review代码\n│   ├─ 识别潜在Bug模式\n│   ├─ 评估异常处理\n│   └─ 评估日志记录\n│\n├─ 单元测试支持\n│   ├─ 协助开发设计测试用例\n│   ├─ 提供测试数据建议\n│   ├─ 验证单元测试覆盖\n│   └─ 评审单元测试质量\n│\n└─ 接口测试\n    ├─ 编写接口测试用例\n    ├─ 验证接口契约\n    ├─ 测试接口边界条件\n    └─ 执行接口自动化测试\n```\n\nFile v1.8.0:skill-card.md\n\n## Description:\n\nHelps QA teams shift testing into requirements, design, and development through testability reviews, acceptance criteria, and early test planning.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA practitioners and developers use this skill to plan early testing involvement, review requirements and designs for testability, and prepare acceptance criteria and quality gates.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The optional companion workflow install command is not pinned to a release.\n\nMitigation: Confirm the companion source is trusted and use a reviewed commit or pinned version before installing.\n\n## Reference(s):\n\n- [Shift-left testing stages](references/shift-left-stages.md)\n- [ClawHub skill release](https://clawhub.ai/kokxi/skills/qa-shift-left)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown]\n\n**Output Format:** [Markdown checklists and plans]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include early intervention activities, quality gates, and team enablement recommendations.]\n\n## Skill Version(s):\n\n1.8.0 (source: skill metadata and ClawHub release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.7.7: 3 files, 4436 bytes\n\nFiles: skill-card.md (1742b), SKILL.md (7662b), _meta.json (132b)\n\nFile v1.7.7:SKILL.md\n\n---\nname: qa-shift-left\nslug: qa-shift-left\ndisplayName: Shift Left\nversion: 1.7.7\ndescription: >-\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\n\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性（左移阶段）\"、\"需求评审（左移介入）\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\nallowed-tools: Read Grep Glob Bash\nrelated_skills:\n  upstream:\n    - qa-req-deconstruction      # 输入：需求分析\n    - qa-testability-advocacy    # 输入：可测试性推动\n  downstream:\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\ninput_format:\n  required:\n    - name: 项目计划\n      type: string\n      description: 项目时间线和阶段规划\n    - name: 质量目标\n      type: string\n      description: 项目质量目标和标准\n  optional:\n    - name: 团队能力\n      type: string\n      description: 团队测试技能评估\noutput_format:\n  traceability:\n    - 本技能规划左移，不产出唯一ID；可溯源到需求评审ID\n  structure:\n    - 测试用例表格：固定 9 列（用例编号|测试类型|功能模块|测试标题|用例级别|预置条件|测试步骤|预期结果|风险等级）\n    - 用例级别：P0≤20%（核心流程）/ P1≤40%（主要功能）/ P2≤30%（次要功能）/ P3≤10%（边缘场景）\n    - 覆盖率：标注口径（基于现有需求/输入文档），禁止\"全覆盖/100%\"绝对化表述；缺失模块标注\"未覆盖+原因\"\n    - shift_left_plan: 左移测试计划\n    - early_activities: 早期介入活动清单\n    - quality_gates_early: 前置质量门禁\n    - team_enablement: 团队赋能计划\ncategories: ['Development','Testing','DevOps']\ndepth_requirement_quantification:\n  reference_value: \"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\"\n  minimum: \"至少覆盖需求可测试性评审、开发阶段测试2个介入点\"\nerror_recovery_guidance:\n  on_failure: \"左移介入遗漏可测试性问题时回退到需求评审补充\"\n  retry_behavior: \"补充评审后重新评估左移点\"\n---\n# 测试左移实践\n\n## 核心原则\n\n测试左移——越早发现缺陷，修复成本越低。\n\n## 左移阶段\n\n### 阶段1：需求阶段\n\n```text\n测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造\n```\n\n### 阶段2：设计阶段\n\n```text\n测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性\n```\n\n### 阶段3：开发阶段\n\n```text\n测试活动：\n├─ 代码评审\n│   ├─ 从测试角度Review代码\n│   ├─ 识别潜在Bug模式\n│   ├─ 评估异常处理\n│   └─ 评估日志记录\n│\n├─ 单元测试支持\n│   ├─ 协助开发设计测试用例\n│   ├─ 提供测试数据建议\n│   ├─ 验证单元测试覆盖\n│   └─ 评审单元测试质量\n│\n└─ 接口测试\n    ├─ 编写接口测试用例\n    ├─ 验证接口契约\n    ├─ 测试接口边界条件\n    └─ 执行接口自动化测试\n```\n\n## 需求可测试性\n\n### 验收标准模板\n\n```markdown\n## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试\n```\n\n### 可测试性检查清单\n\n```text\n接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？\n```\n\n## 代码评审检查点\n\n### 测试视角的CR\n\n```text\n检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？\n```\n\n## 单元测试支持\n\n### 单元测试检查清单\n\n```text\n覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├─ [ ] 分支覆盖？\n├─ [ ] 边界覆盖？\n└─ [ ] 异常覆盖？\n\n质量：\n├─ [ ] 测试命名清晰？\n├─ [ ] 测试职责单一？\n├─ [ ] 测试独立运行？\n├─ [ ] 测试快速执行？\n└─ [ ] 测试可维护？\n```\n\n## 输出示例\n\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\n→ 左移实践：\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\n\n**用户说\"怎么减少线上Bug\"**\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\n\n## 检查清单\n\n测试左移实施后检查：\n- [ ] 需求评审是否参与？\n- [ ] 验收标准是否定义？\n- [ ] 可测试性是否评估？\n- [ ] 代码评审是否执行？\n- [ ] 单元测试是否支持？\n- [ ] 接口测试是否实施？\n\nFile v1.7.7:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.7.7\",\n  \"publishedAt\": 1790520023626\n}\n\nFile v1.7.7:skill-card.md\n\n## Description:\n\nHelps QA and development teams review requirements, design, and code early to identify testability gaps and plan shift-left testing activities.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA practitioners and developers use this skill to assess requirements for testability, review technical designs and code from a testing perspective, and plan early quality gates and test activities.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Short shift-left testing phrases may activate this Chinese-language planning skill unexpectedly.\n\nMitigation: Confirm the user's intended task and preferred language before applying its checklists.\n\nRisk: Bash access can run commands beyond the planning task if used without oversight.\n\nMitigation: Keep shell use user-directed and limited to project inspection or test commands.\n\n## Reference(s):\n\n- [ClawHub qa-shift-left release](https://clawhub.ai/kokxi/skills/qa-shift-left)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Markdown checklists, plans, and nine-column test-case tables]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes early activities, quality gates, team enablement, and scoped coverage notes.]\n\n## Skill Version(s):\n\n1.7.7 (source: skill frontmatter and server-resolved release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.7.6: 3 files, 4725 bytes\n\nFiles: skill-card.md (1942b), SKILL.md (8213b), _meta.json (132b)\n\nFile v1.7.6:SKILL.md\n\n---\r\nname: qa-shift-left\r\nslug: qa-shift-left\r\ndisplayName: 测试左移\r\nversion: 1.7.5\r\ndescription: >-\r\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\r\n  本技能属于 QA Test Skills 技能集（49 个技能之一），完整工作流体验需安装全套：npx skills add Kokxi/qa-test-skills\r\n\r\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性（左移阶段）\"、\"需求评审（左移介入）\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\r\nallowed-tools: Read Grep Glob Bash\r\nrelated_skills:\r\n  upstream:\r\n    - qa-req-deconstruction      # 输入：需求分析\r\n    - qa-testability-advocacy    # 输入：可测试性推动\r\n  downstream:\r\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\r\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\r\ninput_format:\r\n  required:\r\n    - name: 项目计划\r\n      type: string\r\n      description: 项目时间线和阶段规划\r\n    - name: 质量目标\r\n      type: string\r\n      description: 项目质量目标和标准\r\n  optional:\r\n    - name: 团队能力\r\n      type: string\r\n      description: 团队测试技能评估\r\noutput_format:\r\n  traceability:\r\n    - 本技能规划左移，不产出唯一ID；可溯源到需求评审ID\r\n  structure:\r\n    - 测试用例表格：固定 9 列（用例编号|测试类型|功能模块|测试标题|用例级别|预置条件|测试步骤|预期结果|风险等级）\r\n    - 用例级别：P0≤20%（核心流程）/ P1≤40%（主要功能）/ P2≤30%（次要功能）/ P3≤10%（边缘场景）\r\n    - 覆盖率：标注口径（基于现有需求/输入文档），禁止\"全覆盖/100%\"绝对化表述；缺失模块标注\"未覆盖+原因\"\r\n    - shift_left_plan: 左移测试计划\r\n    - early_activities: 早期介入活动清单\r\n    - quality_gates_early: 前置质量门禁\r\n    - team_enablement: 团队赋能计划\r\ncategories: ['Development','Testing','DevOps']\r\ndepth_requirement_quantification:\r\n  reference_value: \"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\"\r\n  minimum: \"至少覆盖需求可测试性评审、开发阶段测试2个介入点\"\r\nerror_recovery_guidance:\r\n  on_failure: \"左移介入遗漏可测试性问题时回退到需求评审补充\"\r\n  retry_behavior: \"补充评审后重新评估左移点\"\r\n---\r\n> ⚠️ 本技能单独使用效果有限，建议配合完整技能集（12 步工作流）使用。安装：npx skills add Kokxi/qa-test-skills\r\n\r\n# 测试左移实践\r\n\r\n## 核心原则\r\n\r\n测试左移——越早发现缺陷，修复成本越低。\r\n\r\n## 左移阶段\r\n\r\n### 阶段1：需求阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 需求评审\r\n│   ├─ 参与需求评审会议\r\n│   ├─ 从测试角度提出问题\r\n│   ├─ 识别需求不清晰/矛盾点\r\n│   └─ 评估需求可测试性\r\n│\r\n├─ 验收标准\r\n│   ├─ 协助定义验收标准（AC）\r\n│   ├─ 确保AC可测试、可自动化\r\n│   ├─ 明确输入/输出/边界\r\n│   └─ 识别隐含需求\r\n│\r\n└─ 可测试性评估\r\n    ├─ 评估接口是否可Mock\r\n    ├─ 评估日志是否可追踪\r\n    ├─ 评估配置是否可动态\r\n    └─ 评估数据是否可构造\r\n```\r\n\r\n### 阶段2：设计阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 架构评审\r\n│   ├─ 评估系统架构可测试性\r\n│   ├─ 识别测试难点\r\n│   ├─ 建议可测试设计\r\n│   └─ 评估依赖服务Mock方案\r\n│\r\n├─ 接口设计评审\r\n│   ├─ 评估接口设计合理性\r\n│   ├─ 确认接口文档完整性\r\n│   ├─ 评估错误码设计\r\n│   └─ 评估版本兼容性\r\n│\r\n└─ 数据库设计评审\r\n    ├─ 评估表结构设计\r\n    ├─ 评估索引设计\r\n    ├─ 评估数据迁移方案\r\n    └─ 评估数据一致性\r\n```\r\n\r\n### 阶段3：开发阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 代码评审\r\n│   ├─ 从测试角度Review代码\r\n│   ├─ 识别潜在Bug模式\r\n│   ├─ 评估异常处理\r\n│   └─ 评估日志记录\r\n│\r\n├─ 单元测试支持\r\n│   ├─ 协助开发设计测试用例\r\n│   ├─ 提供测试数据建议\r\n│   ├─ 验证单元测试覆盖\r\n│   └─ 评审单元测试质量\r\n│\r\n└─ 接口测试\r\n    ├─ 编写接口测试用例\r\n    ├─ 验证接口契约\r\n    ├─ 测试接口边界条件\r\n    └─ 执行接口自动化测试\r\n```\r\n\r\n## 需求可测试性\r\n\r\n### 验收标准模板\r\n\r\n```markdown\r\n## 验收标准（AC）\r\n\r\n### 功能描述\r\n[功能的简要描述]\r\n\r\n### 验收条件\r\n- [ ] 条件1：[具体条件]\r\n- [ ] 条件2：[具体条件]\r\n- [ ] 条件3：[具体条件]\r\n\r\n### 输入\r\n- 正常输入：[示例]\r\n- 异常输入：[示例]\r\n- 边界输入：[示例]\r\n\r\n### 输出\r\n- 正常输出：[预期结果]\r\n- 异常输出：[错误信息]\r\n- 边界输出：[边界处理]\r\n\r\n### 验证方法\r\n- [ ] 手动测试\r\n- [ ] 自动化测试\r\n- [ ] 接口测试\r\n```\r\n\r\n### 可测试性检查清单\r\n\r\n```text\r\n接口层：\r\n├─ [ ] 接口是否可Mock？\r\n├─ [ ] 接口是否有测试接口？\r\n├─ [ ] 接口文档是否完整？\r\n└─ [ ] 接口版本是否管理？\r\n\r\n数据层：\r\n├─ [ ] 数据是否可构造？\r\n├─ [ ] 数据是否可清理？\r\n├─ [ ] 数据是否可查询？\r\n└─ [ ] 数据是否可隔离？\r\n\r\n日志层：\r\n├─ [ ] 关键路径是否有日志？\r\n├─ [ ] 日志级别是否合理？\r\n├─ [ ] 是否有TraceId？\r\n└─ [ ] 日志是否可查询？\r\n\r\n配置层：\r\n├─ [ ] 功能开关是否支持？\r\n├─ [ ] 配置是否可动态修改？\r\n├─ [ ] 测试配置是否独立？\r\n└─ [ ] 配置变更是否有记录？\r\n```\r\n\r\n## 代码评审检查点\r\n\r\n### 测试视角的CR\r\n\r\n```text\r\n检查点：\r\n├─ 业务逻辑\r\n│   ├─ 条件判断是否正确？\r\n│   ├─ 边界条件是否处理？\r\n│   ├─ 异常情况是否考虑？\r\n│   └─ 数据校验是否完整？\r\n│\r\n├─ 异常处理\r\n│   ├─ 异常是否捕获？\r\n│   ├─ 异常信息是否明确？\r\n│   ├─ 异常恢复是否实现？\r\n│   └─ 异常日志是否记录？\r\n│\r\n├─ 日志记录\r\n│   ├─ 关键操作是否有日志？\r\n│   ├─ 日志级别是否合理？\r\n│   ├─ 敏感信息是否脱敏？\r\n│   └─ TraceId是否传递？\r\n│\r\n└─ 性能影响\r\n    ├─ 是否有N+1查询？\r\n    ├─ 是否有内存泄漏风险？\r\n    ├─ 是否有并发问题？\r\n    └─ 是否有性能瓶颈？\r\n```\r\n\r\n## 单元测试支持\r\n\r\n### 单元测试检查清单\r\n\r\n```text\r\n覆盖率：\r\n├─ [ ] 核心逻辑覆盖？\r\n├─ [ ] 分支覆盖？\r\n├─ [ ] 边界覆盖？\r\n└─ [ ] 异常覆盖？\r\n\r\n质量：\r\n├─ [ ] 测试命名清晰？\r\n├─ [ ] 测试职责单一？\r\n├─ [ ] 测试独立运行？\r\n├─ [ ] 测试快速执行？\r\n└─ [ ] 测试可维护？\r\n```\r\n\r\n## 输出示例\r\n\r\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\r\n→ 左移实践：\r\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\r\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\r\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\r\n\r\n**用户说\"怎么减少线上Bug\"**\r\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\r\n\r\n## 检查清单\r\n\r\n测试左移实施后检查：\r\n- [ ] 需求评审是否参与？\r\n- [ ] 验收标准是否定义？\r\n- [ ] 可测试性是否评估？\r\n- [ ] 代码评审是否执行？\r\n- [ ] 单元测试是否支持？\r\n- [ ] 接口测试是否实施？\n\nFile v1.7.6:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.7.6\",\n  \"publishedAt\": 1788266701529\n}\n\nFile v1.7.6:skill-card.md\n\n## Description:\n\n测试左移 helps QA teams find defects earlier by reviewing requirement testability, development-stage test design, and technical solution risks before release.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA engineers, test leads, and development teams use this skill during requirement, design, and development phases to plan shift-left testing activities, define early quality gates, and produce checklists or intervention records.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill recommends installing a larger external QA skill set through an unpinned remote command outside the reviewed artifact.\n\nMitigation: Install only after separately trusting and verifying the external collection, preferably with a pinned commit or signed release.\n\nRisk: The skill allows Bash-based actions in a QA workflow context.\n\nMitigation: Review project files and proposed commands before allowing Bash actions.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/kokxi/skills/qa-shift-left)\n- [ClawHub publisher profile](https://clawhub.ai/user/kokxi)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance, shell commands, configuration]\n\n**Output Format:** [Markdown guidance with checklists, structured tables, and shift-left planning sections]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Chinese-language QA workflow guidance; may reference an optional external skill-set installation command.]\n\n## Skill Version(s):\n\n1.7.6 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.7.5: 3 files, 4592 bytes\n\nFiles: skill-card.md (2120b), SKILL.md (7662b), _meta.json (132b)\n\nFile v1.7.5:SKILL.md\n\n---\nname: qa-shift-left\nslug: qa-shift-left\ndisplayName: Shift Left\nversion: 1.7.5\ndescription: >-\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\n\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性（左移阶段）\"、\"需求评审（左移介入）\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\nallowed-tools: Read Grep Glob Bash\nrelated_skills:\n  upstream:\n    - qa-req-deconstruction      # 输入：需求分析\n    - qa-testability-advocacy    # 输入：可测试性推动\n  downstream:\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\ninput_format:\n  required:\n    - name: 项目计划\n      type: string\n      description: 项目时间线和阶段规划\n    - name: 质量目标\n      type: string\n      description: 项目质量目标和标准\n  optional:\n    - name: 团队能力\n      type: string\n      description: 团队测试技能评估\noutput_format:\n  traceability:\n    - 本技能规划左移，不产出唯一ID；可溯源到需求评审ID\n  structure:\n    - 测试用例表格：固定 9 列（用例编号|测试类型|功能模块|测试标题|用例级别|预置条件|测试步骤|预期结果|风险等级）\n    - 用例级别：P0≤20%（核心流程）/ P1≤40%（主要功能）/ P2≤30%（次要功能）/ P3≤10%（边缘场景）\n    - 覆盖率：标注口径（基于现有需求/输入文档），禁止\"全覆盖/100%\"绝对化表述；缺失模块标注\"未覆盖+原因\"\n    - shift_left_plan: 左移测试计划\n    - early_activities: 早期介入活动清单\n    - quality_gates_early: 前置质量门禁\n    - team_enablement: 团队赋能计划\ncategories: ['Development','Testing','DevOps']\ndepth_requirement_quantification:\n  reference_value: \"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\"\n  minimum: \"至少覆盖需求可测试性评审、开发阶段测试2个介入点\"\nerror_recovery_guidance:\n  on_failure: \"左移介入遗漏可测试性问题时回退到需求评审补充\"\n  retry_behavior: \"补充评审后重新评估左移点\"\n---\n# 测试左移实践\n\n## 核心原则\n\n测试左移——越早发现缺陷，修复成本越低。\n\n## 左移阶段\n\n### 阶段1：需求阶段\n\n```text\n测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造\n```\n\n### 阶段2：设计阶段\n\n```text\n测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性\n```\n\n### 阶段3：开发阶段\n\n```text\n测试活动：\n├─ 代码评审\n│   ├─ 从测试角度Review代码\n│   ├─ 识别潜在Bug模式\n│   ├─ 评估异常处理\n│   └─ 评估日志记录\n│\n├─ 单元测试支持\n│   ├─ 协助开发设计测试用例\n│   ├─ 提供测试数据建议\n│   ├─ 验证单元测试覆盖\n│   └─ 评审单元测试质量\n│\n└─ 接口测试\n    ├─ 编写接口测试用例\n    ├─ 验证接口契约\n    ├─ 测试接口边界条件\n    └─ 执行接口自动化测试\n```\n\n## 需求可测试性\n\n### 验收标准模板\n\n```markdown\n## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试\n```\n\n### 可测试性检查清单\n\n```text\n接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？\n```\n\n## 代码评审检查点\n\n### 测试视角的CR\n\n```text\n检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？\n```\n\n## 单元测试支持\n\n### 单元测试检查清单\n\n```text\n覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├─ [ ] 分支覆盖？\n├─ [ ] 边界覆盖？\n└─ [ ] 异常覆盖？\n\n质量：\n├─ [ ] 测试命名清晰？\n├─ [ ] 测试职责单一？\n├─ [ ] 测试独立运行？\n├─ [ ] 测试快速执行？\n└─ [ ] 测试可维护？\n```\n\n## 输出示例\n\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\n→ 左移实践：\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\n\n**用户说\"怎么减少线上Bug\"**\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\n\n## 检查清单\n\n测试左移实施后检查：\n- [ ] 需求评审是否参与？\n- [ ] 验收标准是否定义？\n- [ ] 可测试性是否评估？\n- [ ] 代码评审是否执行？\n- [ ] 单元测试是否支持？\n- [ ] 接口测试是否实施？\n\nFile v1.7.5:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.7.5\",\n  \"publishedAt\": 1788103093795\n}\n\nFile v1.7.5:skill-card.md\n\n## Description:\n\nHelps QA practitioners and development teams shift testing earlier by reviewing requirement testability, planning development-stage test design, assessing technical risks, and producing shift-left checklists and intervention records.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA engineers, developers, and engineering teams use this skill during requirement, design, and development phases to identify defects earlier, define testable acceptance criteria, plan unit and API testing support, and document shift-left quality gates.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill may activate on broad testing or bug-reduction requests and provide planning guidance outside the user's intended scope.\n\nMitigation: Confirm the project phase, requested QA activity, and available project inputs before applying its checklists or plans.\n\nRisk: An agent using the skill may choose to inspect or run project commands because Bash is listed as an allowed tool.\n\nMitigation: Review any proposed shell command before execution and avoid running commands that change project state unless explicitly needed.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/kokxi/skills/qa-shift-left)\n- [ClawHub publisher profile](https://clawhub.ai/user/kokxi)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown checklists, tables, and planning guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include a nine-column test case table, shift-left test plan, early intervention activities, quality gates, and team enablement plan.]\n\n## Skill Version(s):\n\n1.7.5 (source: server release evidence and frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.7.0: 3 files, 4297 bytes\n\nFiles: skill-card.md (2007b), SKILL.md (7221b), _meta.json (132b)\n\nFile v1.7.0:SKILL.md\n\n---\nname: qa-shift-left\nslug: qa-shift-left\ndisplayName: Shift Left\nversion: 1.7.0\ndescription: >-\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\n\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性（左移阶段）\"、\"需求评审（左移介入）\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\nallowed-tools: Read Grep Glob Bash\nrelated_skills:\n  upstream:\n    - qa-req-deconstruction      # 输入：需求分析\n    - qa-testability-advocacy    # 输入：可测试性推动\n  downstream:\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\ninput_format:\n  required:\n    - name: 项目计划\n      type: string\n      description: 项目时间线和阶段规划\n    - name: 质量目标\n      type: string\n      description: 项目质量目标和标准\n  optional:\n    - name: 团队能力\n      type: string\n      description: 团队测试技能评估\noutput_format:\n  traceability:\n    - 本技能规划左移，不产出唯一ID；可溯源到需求评审ID\n  structure:\n    - shift_left_plan: 左移测试计划\n    - early_activities: 早期介入活动清单\n    - quality_gates_early: 前置质量门禁\n    - team_enablement: 团队赋能计划\ncategories: ['Development','Testing','DevOps']\ndepth_requirement_quantification:\n  reference_value: \"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\"\n  minimum: \"至少覆盖需求可测试性评审、开发阶段测试2个介入点\"\nerror_recovery_guidance:\n  on_failure: \"左移介入遗漏可测试性问题时回退到需求评审补充\"\n  retry_behavior: \"补充评审后重新评估左移点\"\n---\n# 测试左移实践\n\n## 核心原则\n\n测试左移——越早发现缺陷，修复成本越低。\n\n## 左移阶段\n\n### 阶段1：需求阶段\n\n```text\n测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造\n```\n\n### 阶段2：设计阶段\n\n```text\n测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性\n```\n\n### 阶段3：开发阶段\n\n```text\n测试活动：\n├─ 代码评审\n│   ├─ 从测试角度Review代码\n│   ├─ 识别潜在Bug模式\n│   ├─ 评估异常处理\n│   └─ 评估日志记录\n│\n├─ 单元测试支持\n│   ├─ 协助开发设计测试用例\n│   ├─ 提供测试数据建议\n│   ├─ 验证单元测试覆盖\n│   └─ 评审单元测试质量\n│\n└─ 接口测试\n    ├─ 编写接口测试用例\n    ├─ 验证接口契约\n    ├─ 测试接口边界条件\n    └─ 执行接口自动化测试\n```\n\n## 需求可测试性\n\n### 验收标准模板\n\n```markdown\n## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试\n```\n\n### 可测试性检查清单\n\n```text\n接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？\n```\n\n## 代码评审检查点\n\n### 测试视角的CR\n\n```text\n检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？\n```\n\n## 单元测试支持\n\n### 单元测试检查清单\n\n```text\n覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├─ [ ] 分支覆盖？\n├─ [ ] 边界覆盖？\n└─ [ ] 异常覆盖？\n\n质量：\n├─ [ ] 测试命名清晰？\n├─ [ ] 测试职责单一？\n├─ [ ] 测试独立运行？\n├─ [ ] 测试快速执行？\n└─ [ ] 测试可维护？\n```\n\n## 输出示例\n\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\n→ 左移实践：\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\n\n**用户说\"怎么减少线上Bug\"**\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\n\n## 检查清单\n\n测试左移实施后检查：\n- [ ] 需求评审是否参与？\n- [ ] 验收标准是否定义？\n- [ ] 可测试性是否评估？\n- [ ] 代码评审是否执行？\n- [ ] 单元测试是否支持？\n- [ ] 接口测试是否实施？\n\nFile v1.7.0:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.7.0\",\n  \"publishedAt\": 1786890751669\n}\n\nFile v1.7.0:skill-card.md\n\n## Description:\n\nHelps QA, development, and product teams shift testing earlier into requirements, design, and development by producing testability review prompts, early quality gates, checklists, and intervention records.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA engineers, developers, product managers, and engineering leads use this skill during requirements review, technical design, and active development to identify ambiguous requirements, testability gaps, interface risks, and missing early quality gates before defects become more expensive to fix.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill may activate on brief Chinese shift-left testing phrases when the user did not intend a full QA planning workflow.\n\nMitigation: Use it when requirements, design, or development review needs QA guidance, and confirm the requested scope before applying its checklists.\n\nRisk: The skill declares Bash access, so any proposed shell command could affect the local workspace if run without review.\n\nMitigation: Review proposed Bash commands before execution and allow only commands that are necessary for the active QA review task.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Text]\n\n**Output Format:** [Markdown checklists and structured guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces shift-left testing plans, early activity lists, quality gate suggestions, team enablement plans, and phase intervention notes.]\n\n## Skill Version(s):\n\n1.7.0 (source: release evidence and SKILL.md frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.6.3: 3 files, 4146 bytes\n\nFiles: skill-card.md (1785b), SKILL.md (7221b), _meta.json (132b)\n\nFile v1.6.3:SKILL.md\n\n---\nname: qa-shift-left\nslug: qa-shift-left\ndisplayName: Shift Left\nversion: 1.6.3\ndescription: >-\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\n\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性（左移阶段）\"、\"需求评审（左移介入）\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\nallowed-tools: Read Grep Glob Bash\nrelated_skills:\n  upstream:\n    - qa-req-deconstruction      # 输入：需求分析\n    - qa-testability-advocacy    # 输入：可测试性推动\n  downstream:\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\ninput_format:\n  required:\n    - name: 项目计划\n      type: string\n      description: 项目时间线和阶段规划\n    - name: 质量目标\n      type: string\n      description: 项目质量目标和标准\n  optional:\n    - name: 团队能力\n      type: string\n      description: 团队测试技能评估\noutput_format:\n  traceability:\n    - 本技能规划左移，不产出唯一ID；可溯源到需求评审ID\n  structure:\n    - shift_left_plan: 左移测试计划\n    - early_activities: 早期介入活动清单\n    - quality_gates_early: 前置质量门禁\n    - team_enablement: 团队赋能计划\ncategories: ['Development','Testing','DevOps']\ndepth_requirement_quantification:\n  reference_value: \"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\"\n  minimum: \"至少覆盖需求可测试性评审、开发阶段测试2个介入点\"\nerror_recovery_guidance:\n  on_failure: \"左移介入遗漏可测试性问题时回退到需求评审补充\"\n  retry_behavior: \"补充评审后重新评估左移点\"\n---\n# 测试左移实践\n\n## 核心原则\n\n测试左移——越早发现缺陷，修复成本越低。\n\n## 左移阶段\n\n### 阶段1：需求阶段\n\n```text\n测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造\n```\n\n### 阶段2：设计阶段\n\n```text\n测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性\n```\n\n### 阶段3：开发阶段\n\n```text\n测试活动：\n├─ 代码评审\n│   ├─ 从测试角度Review代码\n│   ├─ 识别潜在Bug模式\n│   ├─ 评估异常处理\n│   └─ 评估日志记录\n│\n├─ 单元测试支持\n│   ├─ 协助开发设计测试用例\n│   ├─ 提供测试数据建议\n│   ├─ 验证单元测试覆盖\n│   └─ 评审单元测试质量\n│\n└─ 接口测试\n    ├─ 编写接口测试用例\n    ├─ 验证接口契约\n    ├─ 测试接口边界条件\n    └─ 执行接口自动化测试\n```\n\n## 需求可测试性\n\n### 验收标准模板\n\n```markdown\n## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试\n```\n\n### 可测试性检查清单\n\n```text\n接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？\n```\n\n## 代码评审检查点\n\n### 测试视角的CR\n\n```text\n检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？\n```\n\n## 单元测试支持\n\n### 单元测试检查清单\n\n```text\n覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├─ [ ] 分支覆盖？\n├─ [ ] 边界覆盖？\n└─ [ ] 异常覆盖？\n\n质量：\n├─ [ ] 测试命名清晰？\n├─ [ ] 测试职责单一？\n├─ [ ] 测试独立运行？\n├─ [ ] 测试快速执行？\n└─ [ ] 测试可维护？\n```\n\n## 输出示例\n\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\n→ 左移实践：\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\n\n**用户说\"怎么减少线上Bug\"**\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\n\n## 检查清单\n\n测试左移实施后检查：\n- [ ] 需求评审是否参与？\n- [ ] 验收标准是否定义？\n- [ ] 可测试性是否评估？\n- [ ] 代码评审是否执行？\n- [ ] 单元测试是否支持？\n- [ ] 接口测试是否实施？\n\nFile v1.6.3:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.6.3\",\n  \"publishedAt\": 1786548433055\n}\n\nFile v1.6.3:skill-card.md\n\n## Description:\n\nHelps QA engineers and development teams shift testing earlier by reviewing requirement testability, planning development-stage test design, and identifying quality risks before release.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA engineers, developers, and delivery teams use this skill during requirements, design, and development to create shift-left testing plans, early activity checklists, quality gates, and team enablement actions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Broad activation phrases could invoke the skill when early QA planning is not intended.\n\nMitigation: Review activation phrases before deployment and scope use to explicit shift-left testing, requirements review, or early QA planning requests.\n\nRisk: The skill permits Bash use for project-local test or inspection commands.\n\nMitigation: Allow Bash only for explicit, project-local test or inspection commands and review commands before execution.\n\n## Reference(s):\n\n\n## Skill Output:\n\n**Output Type(s):** [markdown, guidance]\n\n**Output Format:** [Markdown checklists and planning guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces shift-left plans, early testing activity lists, quality gates, and team enablement recommendations.]\n\n## Skill Version(s):\n\n1.6.3 (source: frontmatter and server-resolved release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.6.0: 3 files, 4387 bytes\n\nFiles: skill-card.md (2314b), SKILL.md (7426b), _meta.json (132b)\n\nFile v1.6.0:SKILL.md\n\n---\r\nname: qa-shift-left\r\nversion: 1.6.0\r\ndescription: >-\r\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\r\n\r\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性（左移阶段）\"、\"需求评审（左移介入）\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\r\nallowed-tools: Read Grep Glob Bash\r\nrelated_skills:\r\n  upstream:\r\n    - qa-req-deconstruction      # 输入：需求分析\r\n    - qa-testability-advocacy    # 输入：可测试性推动\r\n  downstream:\r\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\r\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\r\ninput_format:\r\n  required:\r\n    - name: 项目计划\r\n      type: string\r\n      description: 项目时间线和阶段规划\r\n    - name: 质量目标\r\n      type: string\r\n      description: 项目质量目标和标准\r\n  optional:\r\n    - name: 团队能力\r\n      type: string\r\n      description: 团队测试技能评估\r\noutput_format:\r\n  traceability:\r\n    - 本技能规划左移，不产出唯一ID；可溯源到需求评审ID\r\n  structure:\r\n    - shift_left_plan: 左移测试计划\r\n    - early_activities: 早期介入活动清单\r\n    - quality_gates_early: 前置质量门禁\r\n    - team_enablement: 团队赋能计划\r\ncategories: ['Development','Testing','DevOps']\r\ndepth_requirement_quantification:\r\n  reference_value: \"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\"\r\n  minimum: \"至少覆盖需求可测试性评审、开发阶段测试2个介入点\"\r\nerror_recovery_guidance:\r\n  on_failure: \"左移介入遗漏可测试性问题时回退到需求评审补充\"\r\n  retry_behavior: \"补充评审后重新评估左移点\"\r\n---\r\n# 测试左移实践\r\n\r\n## 核心原则\r\n\r\n测试左移——越早发现缺陷，修复成本越低。\r\n\r\n## 左移阶段\r\n\r\n### 阶段1：需求阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 需求评审\r\n│   ├─ 参与需求评审会议\r\n│   ├─ 从测试角度提出问题\r\n│   ├─ 识别需求不清晰/矛盾点\r\n│   └─ 评估需求可测试性\r\n│\r\n├─ 验收标准\r\n│   ├─ 协助定义验收标准（AC）\r\n│   ├─ 确保AC可测试、可自动化\r\n│   ├─ 明确输入/输出/边界\r\n│   └─ 识别隐含需求\r\n│\r\n└─ 可测试性评估\r\n    ├─ 评估接口是否可Mock\r\n    ├─ 评估日志是否可追踪\r\n    ├─ 评估配置是否可动态\r\n    └─ 评估数据是否可构造\r\n```\r\n\r\n### 阶段2：设计阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 架构评审\r\n│   ├─ 评估系统架构可测试性\r\n│   ├─ 识别测试难点\r\n│   ├─ 建议可测试设计\r\n│   └─ 评估依赖服务Mock方案\r\n│\r\n├─ 接口设计评审\r\n│   ├─ 评估接口设计合理性\r\n│   ├─ 确认接口文档完整性\r\n│   ├─ 评估错误码设计\r\n│   └─ 评估版本兼容性\r\n│\r\n└─ 数据库设计评审\r\n    ├─ 评估表结构设计\r\n    ├─ 评估索引设计\r\n    ├─ 评估数据迁移方案\r\n    └─ 评估数据一致性\r\n```\r\n\r\n### 阶段3：开发阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 代码评审\r\n│   ├─ 从测试角度Review代码\r\n│   ├─ 识别潜在Bug模式\r\n│   ├─ 评估异常处理\r\n│   └─ 评估日志记录\r\n│\r\n├─ 单元测试支持\r\n│   ├─ 协助开发设计测试用例\r\n│   ├─ 提供测试数据建议\r\n│   ├─ 验证单元测试覆盖\r\n│   └─ 评审单元测试质量\r\n│\r\n└─ 接口测试\r\n    ├─ 编写接口测试用例\r\n    ├─ 验证接口契约\r\n    ├─ 测试接口边界条件\r\n    └─ 执行接口自动化测试\r\n```\r\n\r\n## 需求可测试性\r\n\r\n### 验收标准模板\r\n\r\n```markdown\r\n## 验收标准（AC）\r\n\r\n### 功能描述\r\n[功能的简要描述]\r\n\r\n### 验收条件\r\n- [ ] 条件1：[具体条件]\r\n- [ ] 条件2：[具体条件]\r\n- [ ] 条件3：[具体条件]\r\n\r\n### 输入\r\n- 正常输入：[示例]\r\n- 异常输入：[示例]\r\n- 边界输入：[示例]\r\n\r\n### 输出\r\n- 正常输出：[预期结果]\r\n- 异常输出：[错误信息]\r\n- 边界输出：[边界处理]\r\n\r\n### 验证方法\r\n- [ ] 手动测试\r\n- [ ] 自动化测试\r\n- [ ] 接口测试\r\n```\r\n\r\n### 可测试性检查清单\r\n\r\n```text\r\n接口层：\r\n├─ [ ] 接口是否可Mock？\r\n├─ [ ] 接口是否有测试接口？\r\n├─ [ ] 接口文档是否完整？\r\n└─ [ ] 接口版本是否管理？\r\n\r\n数据层：\r\n├─ [ ] 数据是否可构造？\r\n├─ [ ] 数据是否可清理？\r\n├─ [ ] 数据是否可查询？\r\n└─ [ ] 数据是否可隔离？\r\n\r\n日志层：\r\n├─ [ ] 关键路径是否有日志？\r\n├─ [ ] 日志级别是否合理？\r\n├─ [ ] 是否有TraceId？\r\n└─ [ ] 日志是否可查询？\r\n\r\n配置层：\r\n├─ [ ] 功能开关是否支持？\r\n├─ [ ] 配置是否可动态修改？\r\n├─ [ ] 测试配置是否独立？\r\n└─ [ ] 配置变更是否有记录？\r\n```\r\n\r\n## 代码评审检查点\r\n\r\n### 测试视角的CR\r\n\r\n```text\r\n检查点：\r\n├─ 业务逻辑\r\n│   ├─ 条件判断是否正确？\r\n│   ├─ 边界条件是否处理？\r\n│   ├─ 异常情况是否考虑？\r\n│   └─ 数据校验是否完整？\r\n│\r\n├─ 异常处理\r\n│   ├─ 异常是否捕获？\r\n│   ├─ 异常信息是否明确？\r\n│   ├─ 异常恢复是否实现？\r\n│   └─ 异常日志是否记录？\r\n│\r\n├─ 日志记录\r\n│   ├─ 关键操作是否有日志？\r\n│   ├─ 日志级别是否合理？\r\n│   ├─ 敏感信息是否脱敏？\r\n│   └─ TraceId是否传递？\r\n│\r\n└─ 性能影响\r\n    ├─ 是否有N+1查询？\r\n    ├─ 是否有内存泄漏风险？\r\n    ├─ 是否有并发问题？\r\n    └─ 是否有性能瓶颈？\r\n```\r\n\r\n## 单元测试支持\r\n\r\n### 单元测试检查清单\r\n\r\n```text\r\n覆盖率：\r\n├─ [ ] 核心逻辑覆盖？\r\n├─ [ ] 分支覆盖？\r\n├─ [ ] 边界覆盖？\r\n└─ [ ] 异常覆盖？\r\n\r\n质量：\r\n├─ [ ] 测试命名清晰？\r\n├─ [ ] 测试职责单一？\r\n├─ [ ] 测试独立运行？\r\n├─ [ ] 测试快速执行？\r\n└─ [ ] 测试可维护？\r\n```\r\n\r\n## 输出示例\r\n\r\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\r\n→ 左移实践：\r\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\r\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\r\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\r\n\r\n**用户说\"怎么减少线上Bug\"**\r\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\r\n\r\n## 检查清单\r\n\r\n测试左移实施后检查：\r\n- [ ] 需求评审是否参与？\r\n- [ ] 验收标准是否定义？\r\n- [ ] 可测试性是否评估？\r\n- [ ] 代码评审是否执行？\r\n- [ ] 单元测试是否支持？\r\n- [ ] 接口测试是否实施？\n\nFile v1.6.0:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.6.0\",\n  \"publishedAt\": 1783358235714\n}\n\nFile v1.6.0:skill-card.md\n\n## Description: <br>\nGuides QA and engineering teams through shift-left testing activities across requirements, design, and development to produce early testing checklists, quality gates, and intervention records. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[kokxi](https://clawhub.ai/user/kokxi) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, QA engineers, and project teams use this skill during requirements, design, and active development to plan shift-left testing, assess testability, define early quality gates, and document phased intervention activities. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Broad trigger wording may activate the skill during unrelated QA conversations. <br>\nMitigation: Use explicit invocation or narrow trigger wording when installing it in contexts with many QA skills. <br>\nRisk: The skill declares Bash access even though the artifact is primarily a document-review and planning aid. <br>\nMitigation: Avoid granting Bash unless the operating environment needs it; use read-only document review for checklist generation where possible. <br>\nRisk: Shift-left recommendations can become misleading if source requirements, timelines, or quality targets are incomplete. <br>\nMitigation: Review generated checklists and quality gates with product, engineering, and QA owners before treating them as project controls. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/kokxi/skills/qa-shift-left) <br>\n- [Publisher profile](https://clawhub.ai/user/kokxi) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Markdown checklists and structured planning notes] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Includes traceability to requirements review IDs when available.] <br>\n\n## Skill Version(s): <br>\n1.6.0 (source: SKILL.md frontmatter and server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.5.0: 3 files, 4113 bytes\n\nFiles: skill-card.md (2185b), SKILL.md (7071b), _meta.json (132b)\n\nFile v1.5.0:SKILL.md\n\n---\r\nname: qa-shift-left\r\nversion: 1.5.0\r\ndescription: >-\r\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。\r\n\r\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性\"、\"需求评审\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\r\nallowed-tools: Read Grep Glob Bash\r\nrelated_skills:\r\n  upstream:\r\n    - qa-req-deconstruction      # 输入：需求分析\r\n    - qa-testability-advocacy    # 输入：可测试性推动\r\n  downstream:\r\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\r\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\r\ninput_format:\r\n  required:\r\n    - name: 项目计划\r\n      type: string\r\n      description: 项目时间线和阶段规划\r\n    - name: 质量目标\r\n      type: string\r\n      description: 项目质量目标和标准\r\n  optional:\r\n    - name: 团队能力\r\n      type: string\r\n      description: 团队测试技能评估\r\noutput_format:\r\n  structure:\r\n    - shift_left_plan: 左移测试计划\r\n    - early_activities: 早期介入活动清单\r\n    - quality_gates_early: 前置质量门禁\r\n    - team_enablement: 团队赋能计划\r\n---\r\n\r\n# 测试左移实践\r\n\r\n## 核心原则\r\n\r\n你是一位测试左移专家，擅长将测试活动提前到开发阶段。\r\n**核心原则**：测试左移——越早发现缺陷，修复成本越低。\r\n本技能覆盖需求阶段→设计阶段→开发阶段的左移实践和可测试性推动。\r\n\r\n## 左移阶段\r\n\r\n### 阶段1：需求阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 需求评审\r\n│   ├─ 参与需求评审会议\r\n│   ├─ 从测试角度提出问题\r\n│   ├─ 识别需求不清晰/矛盾点\r\n│   └─ 评估需求可测试性\r\n│\r\n├─ 验收标准\r\n│   ├─ 协助定义验收标准（AC）\r\n│   ├─ 确保AC可测试、可自动化\r\n│   ├─ 明确输入/输出/边界\r\n│   └─ 识别隐含需求\r\n│\r\n└─ 可测试性评估\r\n    ├─ 评估接口是否可Mock\r\n    ├─ 评估日志是否可追踪\r\n    ├─ 评估配置是否可动态\r\n    └─ 评估数据是否可构造\r\n```\r\n\r\n### 阶段2：设计阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 架构评审\r\n│   ├─ 评估系统架构可测试性\r\n│   ├─ 识别测试难点\r\n│   ├─ 建议可测试设计\r\n│   └─ 评估依赖服务Mock方案\r\n│\r\n├─ 接口设计评审\r\n│   ├─ 评估接口设计合理性\r\n│   ├─ 确认接口文档完整性\r\n│   ├─ 评估错误码设计\r\n│   └─ 评估版本兼容性\r\n│\r\n└─ 数据库设计评审\r\n    ├─ 评估表结构设计\r\n    ├─ 评估索引设计\r\n    ├─ 评估数据迁移方案\r\n    └─ 评估数据一致性\r\n```\r\n\r\n### 阶段3：开发阶段\r\n\r\n```text\r\n测试活动：\r\n├─ 代码评审\r\n│   ├─ 从测试角度Review代码\r\n│   ├─ 识别潜在Bug模式\r\n│   ├─ 评估异常处理\r\n│   └─ 评估日志记录\r\n│\r\n├─ 单元测试支持\r\n│   ├─ 协助开发设计测试用例\r\n│   ├─ 提供测试数据建议\r\n│   ├─ 验证单元测试覆盖\r\n│   └─ 评审单元测试质量\r\n│\r\n└─ 接口测试\r\n    ├─ 编写接口测试用例\r\n    ├─ 验证接口契约\r\n    ├─ 测试接口边界条件\r\n    └─ 执行接口自动化测试\r\n```\r\n\r\n## 需求可测试性\r\n\r\n### 验收标准模板\r\n\r\n```markdown\r\n## 验收标准（AC）\r\n\r\n### 功能描述\r\n[功能的简要描述]\r\n\r\n### 验收条件\r\n- [ ] 条件1：[具体条件]\r\n- [ ] 条件2：[具体条件]\r\n- [ ] 条件3：[具体条件]\r\n\r\n### 输入\r\n- 正常输入：[示例]\r\n- 异常输入：[示例]\r\n- 边界输入：[示例]\r\n\r\n### 输出\r\n- 正常输出：[预期结果]\r\n- 异常输出：[错误信息]\r\n- 边界输出：[边界处理]\r\n\r\n### 验证方法\r\n- [ ] 手动测试\r\n- [ ] 自动化测试\r\n- [ ] 接口测试\r\n```\r\n\r\n### 可测试性检查清单\r\n\r\n```text\r\n接口层：\r\n├─ [ ] 接口是否可Mock？\r\n├─ [ ] 接口是否有测试接口？\r\n├─ [ ] 接口文档是否完整？\r\n└─ [ ] 接口版本是否管理？\r\n\r\n数据层：\r\n├─ [ ] 数据是否可构造？\r\n├─ [ ] 数据是否可清理？\r\n├─ [ ] 数据是否可查询？\r\n└─ [ ] 数据是否可隔离？\r\n\r\n日志层：\r\n├─ [ ] 关键路径是否有日志？\r\n├─ [ ] 日志级别是否合理？\r\n├─ [ ] 是否有TraceId？\r\n└─ [ ] 日志是否可查询？\r\n\r\n配置层：\r\n├─ [ ] 功能开关是否支持？\r\n├─ [ ] 配置是否可动态修改？\r\n├─ [ ] 测试配置是否独立？\r\n└─ [ ] 配置变更是否有记录？\r\n```\r\n\r\n## 代码评审检查点\r\n\r\n### 测试视角的CR\r\n\r\n```text\r\n检查点：\r\n├─ 业务逻辑\r\n│   ├─ 条件判断是否正确？\r\n│   ├─ 边界条件是否处理？\r\n│   ├─ 异常情况是否考虑？\r\n│   └─ 数据校验是否完整？\r\n│\r\n├─ 异常处理\r\n│   ├─ 异常是否捕获？\r\n│   ├─ 异常信息是否明确？\r\n│   ├─ 异常恢复是否实现？\r\n│   └─ 异常日志是否记录？\r\n│\r\n├─ 日志记录\r\n│   ├─ 关键操作是否有日志？\r\n│   ├─ 日志级别是否合理？\r\n│   ├─ 敏感信息是否脱敏？\r\n│   └─ TraceId是否传递？\r\n│\r\n└─ 性能影响\r\n    ├─ 是否有N+1查询？\r\n    ├─ 是否有内存泄漏风险？\r\n    ├─ 是否有并发问题？\r\n    └─ 是否有性能瓶颈？\r\n```\r\n\r\n## 单元测试支持\r\n\r\n### 单元测试检查清单\r\n\r\n```text\r\n覆盖率：\r\n├─ [ ] 核心逻辑覆盖？\r\n├─ [ ] 分支覆盖？\r\n├─ [ ] 边界覆盖？\r\n└─ [ ] 异常覆盖？\r\n\r\n质量：\r\n├─ [ ] 测试命名清晰？\r\n├─ [ ] 测试职责单一？\r\n├─ [ ] 测试独立运行？\r\n├─ [ ] 测试快速执行？\r\n└─ [ ] 测试可维护？\r\n```\r\n\r\n## 输出示例\r\n\r\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\r\n→ 左移实践：\r\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\r\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\r\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\r\n\r\n**用户说\"怎么减少线上Bug\"**\r\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\r\n\r\n## 检查清单\r\n\r\n测试左移实施后检查：\r\n- [ ] 需求评审是否参与？\r\n- [ ] 验收标准是否定义？\r\n- [ ] 可测试性是否评估？\r\n- [ ] 代码评审是否执行？\r\n- [ ] 单元测试是否支持？\r\n- [ ] 接口测试是否实施？\n\nFile v1.5.0:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.5.0\",\n  \"publishedAt\": 1782736511524\n}\n\nFile v1.5.0:skill-card.md\n\n## Description: <br>\nQa Shift Left helps QA and engineering teams shift testing into requirements, design, and development through testability reviews, contract and unit-test planning, risk analysis, and early quality gates. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[kokxi](https://clawhub.ai/user/kokxi) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nQA engineers, developers, and project teams use this skill during early project planning and active development to review requirement testability, design early test activities, and define shift-left quality gates. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may activate on common QA phrases and produce shift-left planning guidance in workflows where that behavior is not intended. <br>\nMitigation: Review trigger wording and confirm the generated QA plan fits the project phase, quality goals, and team workflow before adoption. <br>\nRisk: Generated QA guidance can miss project-specific constraints or create incomplete quality gates if the supplied project plan or quality goals are vague. <br>\nMitigation: Provide concrete project timeline, quality targets, and team capability context, then review outputs with QA and engineering stakeholders. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/kokxi/skills/qa-shift-left) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown guidance with checklists, plans, review notes, and quality-gate recommendations] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Produces shift-left QA plans, early activity checklists, quality gates, and team enablement guidance.] <br>\n\n## Skill Version(s): <br>\n1.5.0 (source: server release metadata and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.4.1: 3 files, 3690 bytes\n\nFiles: skill-card.md (1825b), SKILL.md (6286b), _meta.json (132b)\n\nFile v1.4.1:SKILL.md\n\n---\r\nname: qa-shift-left\r\ndescription: >-\r\n  测试左移实践，将测试活动提前到需求分析和开发阶段，从源头发现缺陷降低修复成本。当需要实施测试左移或提前介入时激活。\r\n\r\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性\"、\"需求评审\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\r\nallowed-tools: Read Grep Glob Bash\r\nrelated_skills:\r\n  upstream:\r\n    - qa-req-deconstruction      # 输入：需求分析\r\n    - qa-testability-advocacy    # 输入：可测试性推动\r\n  downstream:\r\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\r\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\r\ninput_format: 需求分析 + 可测试性评估\r\noutput_format: 测试左移方案（需求评审+代码评审+单元测试支持）\r\n---\r\n\r\n# 测试左移实践\r\n\r\n## Overview\r\n\r\n你是一位测试左移专家，擅长将测试活动提前到开发阶段。\r\n**核心原则**：测试左移——越早发现缺陷，修复成本越低。\r\n本技能覆盖需求阶段→设计阶段→开发阶段的左移实践和可测试性推动。\r\n\r\n## 左移阶段\r\n\r\n### 阶段1：需求阶段\r\n\r\n```\r\n测试活动：\r\n├─ 需求评审\r\n│   ├─ 参与需求评审会议\r\n│   ├─ 从测试角度提出问题\r\n│   ├─ 识别需求不清晰/矛盾点\r\n│   └─ 评估需求可测试性\r\n│\r\n├─ 验收标准\r\n│   ├─ 协助定义验收标准（AC）\r\n│   ├─ 确保AC可测试、可自动化\r\n│   ├─ 明确输入/输出/边界\r\n│   └─ 识别隐含需求\r\n│\r\n└─ 可测试性评估\r\n    ├─ 评估接口是否可Mock\r\n    ├─ 评估日志是否可追踪\r\n    ├─ 评估配置是否可动态\r\n    └─ 评估数据是否可构造\r\n```\r\n\r\n### 阶段2：设计阶段\r\n\r\n```\r\n测试活动：\r\n├─ 架构评审\r\n│   ├─ 评估系统架构可测试性\r\n│   ├─ 识别测试难点\r\n│   ├─ 建议可测试设计\r\n│   └─ 评估依赖服务Mock方案\r\n│\r\n├─ 接口设计评审\r\n│   ├─ 评估接口设计合理性\r\n│   ├─ 确认接口文档完整性\r\n│   ├─ 评估错误码设计\r\n│   └─ 评估版本兼容性\r\n│\r\n└─ 数据库设计评审\r\n    ├─ 评估表结构设计\r\n    ├─ 评估索引设计\r\n    ├─ 评估数据迁移方案\r\n    └─ 评估数据一致性\r\n```\r\n\r\n### 阶段3：开发阶段\r\n\r\n```\r\n测试活动：\r\n├─ 代码评审\r\n│   ├─ 从测试角度Review代码\r\n│   ├─ 识别潜在Bug模式\r\n│   ├─ 评估异常处理\r\n│   └─ 评估日志记录\r\n│\r\n├─ 单元测试支持\r\n│   ├─ 协助开发设计测试用例\r\n│   ├─ 提供测试数据建议\r\n│   ├─ 验证单元测试覆盖\r\n│   └─ 评审单元测试质量\r\n│\r\n└─ 接口测试\r\n    ├─ 编写接口测试用例\r\n    ├─ 验证接口契约\r\n    ├─ 测试接口边界条件\r\n    └─ 执行接口自动化测试\r\n```\r\n\r\n## 需求可测试性\r\n\r\n### 验收标准模板\r\n\r\n```markdown\r\n## 验收标准（AC）\r\n\r\n### 功能描述\r\n[功能的简要描述]\r\n\r\n### 验收条件\r\n- [ ] 条件1：[具体条件]\r\n- [ ] 条件2：[具体条件]\r\n- [ ] 条件3：[具体条件]\r\n\r\n### 输入\r\n- 正常输入：[示例]\r\n- 异常输入：[示例]\r\n- 边界输入：[示例]\r\n\r\n### 输出\r\n- 正常输出：[预期结果]\r\n- 异常输出：[错误信息]\r\n- 边界输出：[边界处理]\r\n\r\n### 验证方法\r\n- [ ] 手动测试\r\n- [ ] 自动化测试\r\n- [ ] 接口测试\r\n```\r\n\r\n### 可测试性检查清单\r\n\r\n```\r\n接口层：\r\n├─ [ ] 接口是否可Mock？\r\n├─ [ ] 接口是否有测试接口？\r\n├─ [ ] 接口文档是否完整？\r\n└─ [ ] 接口版本是否管理？\r\n\r\n数据层：\r\n├─ [ ] 数据是否可构造？\r\n├─ [ ] 数据是否可清理？\r\n├─ [ ] 数据是否可查询？\r\n└─ [ ] 数据是否可隔离？\r\n\r\n日志层：\r\n├─ [ ] 关键路径是否有日志？\r\n├─ [ ] 日志级别是否合理？\r\n├─ [ ] 是否有TraceId？\r\n└─ [ ] 日志是否可查询？\r\n\r\n配置层：\r\n├─ [ ] 功能开关是否支持？\r\n├─ [ ] 配置是否可动态修改？\r\n├─ [ ] 测试配置是否独立？\r\n└─ [ ] 配置变更是否有记录？\r\n```\r\n\r\n## 代码评审检查点\r\n\r\n### 测试视角的CR\r\n\r\n```\r\n检查点：\r\n├─ 业务逻辑\r\n│   ├─ 条件判断是否正确？\r\n│   ├─ 边界条件是否处理？\r\n│   ├─ 异常情况是否考虑？\r\n│   └─ 数据校验是否完整？\r\n│\r\n├─ 异常处理\r\n│   ├─ 异常是否捕获？\r\n│   ├─ 异常信息是否明确？\r\n│   ├─ 异常恢复是否实现？\r\n│   └─ 异常日志是否记录？\r\n│\r\n├─ 日志记录\r\n│   ├─ 关键操作是否有日志？\r\n│   ├─ 日志级别是否合理？\r\n│   ├─ 敏感信息是否脱敏？\r\n│   └─ TraceId是否传递？\r\n│\r\n└─ 性能影响\r\n    ├─ 是否有N+1查询？\r\n    ├─ 是否有内存泄漏风险？\r\n    ├─ 是否有并发问题？\r\n    └─ 是否有性能瓶颈？\r\n```\r\n\r\n## 单元测试支持\r\n\r\n### 单元测试检查清单\r\n\r\n```\r\n覆盖率：\r\n├─ [ ] 核心逻辑覆盖？\r\n├─ [ ] 分支覆盖？\r\n├─ [ ] 边界覆盖？\r\n└─ [ ] 异常覆盖？\r\n\r\n质量：\r\n├─ [ ] 测试命名清晰？\r\n├─ [ ] 测试职责单一？\r\n├─ [ ] 测试独立运行？\r\n├─ [ ] 测试快速执行？\r\n└─ [ ] 测试可维护？\r\n```\r\n\r\n## Examples\r\n\r\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\r\n→ 左移实践：\r\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\r\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\r\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\r\n\r\n**用户说\"怎么减少线上Bug\"**\r\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\r\n\r\n## Guidelines\r\n\r\n测试左移实施后检查：\r\n- [ ] 需求评审是否参与？\r\n- [ ] 验收标准是否定义？\r\n- [ ] 可测试性是否评估？\r\n- [ ] 代码评审是否执行？\r\n- [ ] 单元测试是否支持？\r\n- [ ] 接口测试是否实施？\n\nFile v1.4.1:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.4.1\",\n  \"publishedAt\": 1782406582534\n}\n\nFile v1.4.1:skill-card.md\n\n## Description: <br>\nGuides QA practitioners in shifting testing earlier into requirements, design, and development work so defects can be found and addressed sooner. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[kokxi](https://clawhub.ai/user/kokxi) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nQA engineers, developers, and delivery teams use this skill to plan left-shift testing practices, improve requirement testability, review designs and code from a testing perspective, and support unit and API testing earlier in the lifecycle. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The security evidence notes limited confidence because the complete target artifact was not available for inspection. <br>\nMitigation: Inspect the full SKILL.md in a plain-text editor that reveals invisible characters and remove any control characters before installing. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/kokxi/skills/qa-shift-left) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Markdown, Configuration instructions] <br>\n**Output Format:** [Markdown guidance with checklists, review prompts, and testing templates] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Produces human-reviewable QA planning and review guidance; no executable automation is included in the artifact evidence.] <br>\n\n## Skill Version(s): <br>\n1.4.1 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.4.0: 3 files, 3695 bytes\n\nFiles: skill-card.md (1935b), SKILL.md (6522b), _meta.json (132b)\n\nFile v1.4.0:SKILL.md\n\n---\r\nname: qa-shift-left\r\ndescription: >-\r\n  测试左移实践，将测试活动提前到需求分析和开发阶段。当用户需要实施测试左移、提前测试或评估需求可测试性时自动触发。\r\n  也适用于：项目早期需要介入测试，或开发阶段需要测试指导时。\r\n   关键词：测试左移、提前测试、需求可测试性、开发测试、需求评审、代码评审、单元测试、静态分析、缺陷预防。\nwhen_to_use: 用户说\"测试左移\"、\"左移\"、\"提前测试\"、\"需求可测试性\"、\"需求评审\"、\"开发阶段测\"、需要将测试提前、项目早期需要介入测试时\r\nallowed-tools: Read Grep Glob Bash\r\nrelated_skills:\r\n  upstream:\r\n    - qa-req-deconstruction      # 输入：需求分析\r\n    - qa-testability-advocacy    # 输入：可测试性推动\r\n  downstream:\r\n    - qa-code-review-for-test    # 输出：左移实践支持代码评审\r\n    - qa-test-automation-arch    # 输出：左移实践影响自动化架构\r\ninput_format: 需求分析 + 可测试性评估\r\noutput_format: 测试左移方案（需求评审+代码评审+单元测试支持）\r\n---\r\n\r\n# 测试左移实践\r\n\r\n## Overview\r\n\r\n你是一位测试左移专家，擅长将测试活动提前到开发阶段。\r\n**核心原则**：测试左移——越早发现缺陷，修复成本越低。\r\n本技能覆盖需求阶段→设计阶段→开发阶段的左移实践和可测试性推动。\r\n\r\n## 左移阶段\r\n\r\n### 阶段1：需求阶段\r\n\r\n```\r\n测试活动：\r\n├─ 需求评审\r\n│   ├─ 参与需求评审会议\r\n│   ├─ 从测试角度提出问题\r\n│   ├─ 识别需求不清晰/矛盾点\r\n│   └─ 评估需求可测试性\r\n│\r\n├─ 验收标准\r\n│   ├─ 协助定义验收标准（AC）\r\n│   ├─ 确保AC可测试、可自动化\r\n│   ├─ 明确输入/输出/边界\r\n│   └─ 识别隐含需求\r\n│\r\n└─ 可测试性评估\r\n    ├─ 评估接口是否可Mock\r\n    ├─ 评估日志是否可追踪\r\n    ├─ 评估配置是否可动态\r\n    └─ 评估数据是否可构造\r\n```\r\n\r\n### 阶段2：设计阶段\r\n\r\n```\r\n测试活动：\r\n├─ 架构评审\r\n│   ├─ 评估系统架构可测试性\r\n│   ├─ 识别测试难点\r\n│   ├─ 建议可测试设计\r\n│   └─ 评估依赖服务Mock方案\r\n│\r\n├─ 接口设计评审\r\n│   ├─ 评估接口设计合理性\r\n│   ├─ 确认接口文档完整性\r\n│   ├─ 评估错误码设计\r\n│   └─ 评估版本兼容性\r\n│\r\n└─ 数据库设计评审\r\n    ├─ 评估表结构设计\r\n    ├─ 评估索引设计\r\n    ├─ 评估数据迁移方案\r\n    └─ 评估数据一致性\r\n```\r\n\r\n### 阶段3：开发阶段\r\n\r\n```\r\n测试活动：\r\n├─ 代码评审\r\n│   ├─ 从测试角度Review代码\r\n│   ├─ 识别潜在Bug模式\r\n│   ├─ 评估异常处理\r\n│   └─ 评估日志记录\r\n│\r\n├─ 单元测试支持\r\n│   ├─ 协助开发设计测试用例\r\n│   ├─ 提供测试数据建议\r\n│   ├─ 验证单元测试覆盖\r\n│   └─ 评审单元测试质量\r\n│\r\n└─ 接口测试\r\n    ├─ 编写接口测试用例\r\n    ├─ 验证接口契约\r\n    ├─ 测试接口边界条件\r\n    └─ 执行接口自动化测试\r\n```\r\n\r\n## 需求可测试性\r\n\r\n### 验收标准模板\r\n\r\n```markdown\r\n## 验收标准（AC）\r\n\r\n### 功能描述\r\n[功能的简要描述]\r\n\r\n### 验收条件\r\n- [ ] 条件1：[具体条件]\r\n- [ ] 条件2：[具体条件]\r\n- [ ] 条件3：[具体条件]\r\n\r\n### 输入\r\n- 正常输入：[示例]\r\n- 异常输入：[示例]\r\n- 边界输入：[示例]\r\n\r\n### 输出\r\n- 正常输出：[预期结果]\r\n- 异常输出：[错误信息]\r\n- 边界输出：[边界处理]\r\n\r\n### 验证方法\r\n- [ ] 手动测试\r\n- [ ] 自动化测试\r\n- [ ] 接口测试\r\n```\r\n\r\n### 可测试性检查清单\r\n\r\n```\r\n接口层：\r\n├─ [ ] 接口是否可Mock？\r\n├─ [ ] 接口是否有测试接口？\r\n├─ [ ] 接口文档是否完整？\r\n└─ [ ] 接口版本是否管理？\r\n\r\n数据层：\r\n├─ [ ] 数据是否可构造？\r\n├─ [ ] 数据是否可清理？\r\n├─ [ ] 数据是否可查询？\r\n└─ [ ] 数据是否可隔离？\r\n\r\n日志层：\r\n├─ [ ] 关键路径是否有日志？\r\n├─ [ ] 日志级别是否合理？\r\n├─ [ ] 是否有TraceId？\r\n└─ [ ] 日志是否可查询？\r\n\r\n配置层：\r\n├─ [ ] 功能开关是否支持？\r\n├─ [ ] 配置是否可动态修改？\r\n├─ [ ] 测试配置是否独立？\r\n└─ [ ] 配置变更是否有记录？\r\n```\r\n\r\n## 代码评审检查点\r\n\r\n### 测试视角的CR\r\n\r\n```\r\n检查点：\r\n├─ 业务逻辑\r\n│   ├─ 条件判断是否正确？\r\n│   ├─ 边界条件是否处理？\r\n│   ├─ 异常情况是否考虑？\r\n│   └─ 数据校验是否完整？\r\n│\r\n├─ 异常处理\r\n│   ├─ 异常是否捕获？\r\n│   ├─ 异常信息是否明确？\r\n│   ├─ 异常恢复是否实现？\r\n│   └─ 异常日志是否记录？\r\n│\r\n├─ 日志记录\r\n│   ├─ 关键操作是否有日志？\r\n│   ├─ 日志级别是否合理？\r\n│   ├─ 敏感信息是否脱敏？\r\n│   └─ TraceId是否传递？\r\n│\r\n└─ 性能影响\r\n    ├─ 是否有N+1查询？\r\n    ├─ 是否有内存泄漏风险？\r\n    ├─ 是否有并发问题？\r\n    └─ 是否有性能瓶颈？\r\n```\r\n\r\n## 单元测试支持\r\n\r\n### 单元测试检查清单\r\n\r\n```\r\n覆盖率：\r\n├─ [ ] 核心逻辑覆盖？\r\n├─ [ ] 分支覆盖？\r\n├─ [ ] 边界覆盖？\r\n└─ [ ] 异常覆盖？\r\n\r\n质量：\r\n├─ [ ] 测试命名清晰？\r\n├─ [ ] 测试职责单一？\r\n├─ [ ] 测试独立运行？\r\n├─ [ ] 测试快速执行？\r\n└─ [ ] 测试可维护？\r\n```\r\n\r\n## Examples\r\n\r\n**团队在需求评审阶段参与不足，导致上线后频繁需求变更**\r\n→ 左移实践：\r\n  - 需求阶段：参与需求评审，定义验收标准（AC），推动可测试性检查\r\n  - 设计阶段：测试视角参与技术方案评审，识别设计缺陷\r\n  - 开发阶段：推动单元测试覆盖率，执行测试视角代码评审\r\n\r\n**用户说\"怎么减少线上Bug\"**\r\n→ 启动测试左移：从需求阶段开始介入，越早发现缺陷越便宜\r\n\r\n## Guidelines\r\n\r\n测试左移实施后检查：\r\n- [ ] 需求评审是否参与？\r\n- [ ] 验收标准是否定义？\r\n- [ ] 可测试性是否评估？\r\n- [ ] 代码评审是否执行？\r\n- [ ] 单元测试是否支持？\r\n- [ ] 接口测试是否实施？\n\nFile v1.4.0:_meta.json\n\n{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.4.0\",\n  \"publishedAt\": 1782277891090\n}\n\nFile v1.4.0:skill-card.md\n\n## Description: <br>\nGuides agents through shift-left QA practices by moving testability review, acceptance criteria, code review, unit test support, and interface testing into requirements, design, and development stages. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[kokxi](https://clawhub.ai/user/kokxi) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nQA engineers, developers, and product teams use this skill when they need to shift testing earlier into requirements, design, and development work. It helps produce practical review checklists, acceptance criteria guidance, testability assessment, code review prompts, unit test support, and interface test planning. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill may be routed into general requirements analysis, code review, or test automation design when shift-left QA guidance is not actually needed. <br>\nMitigation: Use it when the user is explicitly asking for shift-left QA, early test involvement, testability review, acceptance criteria, or development-stage QA guidance. <br>\n\n\n## Reference(s): <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Guidance, Markdown, Analysis, Configuration instructions] <br>\n**Output Format:** [Markdown guidance with checklists and templates] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Produces QA shift-left plans, acceptance criteria templates, testability checklists, code review checkpoints, and unit test review guidance.] <br>\n\n## Skill Version(s): <br>\n1.4.0 (source: release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: qa-shift-left Owner: kokxi Summary: 当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design ","codeSnippets":[],"executableExamples":[{"language":"markdown","snippet":"## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试"},{"language":"text","snippet":"接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？"},{"language":"text","snippet":"检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？"},{"language":"text","snippet":"覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├─ [ ] 分支覆盖？\n├─ [ ] 边界覆盖？\n└─ [ ] 异常覆盖？\n\n质量：\n├─ [ ] 测试命名清晰？\n├─ [ ] 测试职责单一？\n├─ [ ] 测试独立运行？\n├─ [ ] 测试快速执行？\n└─ [ ] 测试可维护？"},{"language":"text","snippet":"测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造"},{"language":"text","snippet":"测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: qa-shift-left\ndescription: >-\n  当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design during development, and technical design review.\nlicense: MIT\nallowed-tools: Read Grep Glob Bash\nmetadata:\n  display-name: \"Shift Left\"\n  version: \"1.8.0\"\n  when-to-use: \"用户说\\\"测试左移\\\"、\\\"左移\\\"、\\\"提前测试\\\"、\\\"需求可测试性（左移阶段）\\\"、\\\"需求评审（左移介入）\\\"、\\\"开发阶段测\\\"、需要将测试提前、项目早期需要介入测试时\"\n  related-skills: \"{\\\"upstream\\\":[\\\"qa-req-deconstruction\\\",\\\"qa-testability-advocacy\\\"],\\\"downstream\\\":[\\\"qa-code-review-for-test\\\",\\\"qa-test-automation-arch\\\"]}\"\n  references: \"[\\\"references/shift-left-stages.md\\\"]\"\n  input-format: \"{\\\"required\\\":[{\\\"name\\\":\\\"项目计划\\\",\\\"type\\\":\\\"string\\\",\\\"description\\\":\\\"项目时间线和阶段规划\\\"},{\\\"name\\\":\\\"质量目标\\\",\\\"type\\\":\\\"string\\\",\\\"description\\\":\\\"项目质量目标和标准\\\"}],\\\"optional\\\":[{\\\"name\\\":\\\"团队能力\\\",\\\"type\\\":\\\"string\\\",\\\"description\\\":\\\"团队测试技能评估\\\"}]}\"\n  output-format: \"{\\\"traceability\\\":[\\\"本技能规划左移，不产出唯一ID；可溯源到需求评审ID\\\"],\\\"structure\\\":[{\\\"shift_left_plan\\\":\\\"左移测试计划\\\"},{\\\"early_activities\\\":\\\"早期介入活动清单\\\"},{\\\"quality_gates_early\\\":\\\"前置质量门禁\\\"},{\\\"team_enablement\\\":\\\"团队赋能计划\\\"}]}\"\n  error-recovery-guidance: \"{\\\"on_failure\\\":\\\"左移介入遗漏可测试性问题时回退到需求评审补充\\\",\\\"retry_behavior\\\":\\\"补充评审后重新评估左移点\\\"}\"\n  categories: \"[\\\"Development\\\",\\\"Testing\\\",\\\"DevOps\\\"]\"\n  depth-requirement: \"{\\\"reference_value\\\":\\\"根据介入阶段调整左移深度：简单×1/中等×2/复杂×3\\\",\\\"minimum\\\":\\\"至少覆盖需求可测试性评审、开发阶段测试2个介入点\\\"}\"\n---\n> ⚠️ 本技能单独使用效果有限，建议配合完整技能集（12 步工作流）使用。安装：npx skills add Kokxi/qa-test-skills\n\n# 测试左移实践\n\n## 核心原则\n\n测试左移——越早发现缺陷，修复成本越低。\n\n## 加载时机\n\n| 什么时候读 | 读哪个 |\n|-----------|--------|\n| 介入需求/设计/开发阶段时 | [`references/shift-left-stages.md`](references/shift-left-stages.md) |\n\n> `左移阶段`的完整内容已下沉至 `references/shift-left-stages.md`，避免每次触发都占用上下文。\n\n## 需求可测试性\n\n### 验收标准模板\n\n```markdown\n## 验收标准（AC）\n\n### 功能描述\n[功能的简要描述]\n\n### 验收条件\n- [ ] 条件1：[具体条件]\n- [ ] 条件2：[具体条件]\n- [ ] 条件3：[具体条件]\n\n### 输入\n- 正常输入：[示例]\n- 异常输入：[示例]\n- 边界输入：[示例]\n\n### 输出\n- 正常输出：[预期结果]\n- 异常输出：[错误信息]\n- 边界输出：[边界处理]\n\n### 验证方法\n- [ ] 手动测试\n- [ ] 自动化测试\n- [ ] 接口测试\n```\n\n### 可测试性检查清单\n\n```text\n接口层：\n├─ [ ] 接口是否可Mock？\n├─ [ ] 接口是否有测试接口？\n├─ [ ] 接口文档是否完整？\n└─ [ ] 接口版本是否管理？\n\n数据层：\n├─ [ ] 数据是否可构造？\n├─ [ ] 数据是否可清理？\n├─ [ ] 数据是否可查询？\n└─ [ ] 数据是否可隔离？\n\n日志层：\n├─ [ ] 关键路径是否有日志？\n├─ [ ] 日志级别是否合理？\n├─ [ ] 是否有TraceId？\n└─ [ ] 日志是否可查询？\n\n配置层：\n├─ [ ] 功能开关是否支持？\n├─ [ ] 配置是否可动态修改？\n├─ [ ] 测试配置是否独立？\n└─ [ ] 配置变更是否有记录？\n```\n\n## 代码评审检查点\n\n### 测试视角的CR\n\n```text\n检查点：\n├─ 业务逻辑\n│   ├─ 条件判断是否正确？\n│   ├─ 边界条件是否处理？\n│   ├─ 异常情况是否考虑？\n│   └─ 数据校验是否完整？\n│\n├─ 异常处理\n│   ├─ 异常是否捕获？\n│   ├─ 异常信息是否明确？\n│   ├─ 异常恢复是否实现？\n│   └─ 异常日志是否记录？\n│\n├─ 日志记录\n│   ├─ 关键操作是否有日志？\n│   ├─ 日志级别是否合理？\n│   ├─ 敏感信息是否脱敏？\n│   └─ TraceId是否传递？\n│\n└─ 性能影响\n    ├─ 是否有N+1查询？\n    ├─ 是否有内存泄漏风险？\n    ├─ 是否有并发问题？\n    └─ 是否有性能瓶颈？\n```\n\n## 单元测试支持\n\n### 单元测试检查清单\n\n```text\n覆盖率：\n├─ [ ] 核心逻辑覆盖？\n├"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn71y9b23csfx0ykgm55d5m9x5891zt8\",\n  \"slug\": \"qa-shift-left\",\n  \"version\": \"1.8.0\",\n  \"publishedAt\": 1790656092420\n}"},{"path":"references/shift-left-stages.md","content":"# 测试左移三阶段详解\n\n> 本文是 `qa-shift-left` 的**测试左移三阶段详解**。介入需求/设计/开发阶段时读本文；\n其余部分留在 SKILL.md，不必读本文。\n\n---\n\n\n### 阶段1：需求阶段\n\n```text\n测试活动：\n├─ 需求评审\n│   ├─ 参与需求评审会议\n│   ├─ 从测试角度提出问题\n│   ├─ 识别需求不清晰/矛盾点\n│   └─ 评估需求可测试性\n│\n├─ 验收标准\n│   ├─ 协助定义验收标准（AC）\n│   ├─ 确保AC可测试、可自动化\n│   ├─ 明确输入/输出/边界\n│   └─ 识别隐含需求\n│\n└─ 可测试性评估\n    ├─ 评估接口是否可Mock\n    ├─ 评估日志是否可追踪\n    ├─ 评估配置是否可动态\n    └─ 评估数据是否可构造\n```\n\n### 阶段2：设计阶段\n\n```text\n测试活动：\n├─ 架构评审\n│   ├─ 评估系统架构可测试性\n│   ├─ 识别测试难点\n│   ├─ 建议可测试设计\n│   └─ 评估依赖服务Mock方案\n│\n├─ 接口设计评审\n│   ├─ 评估接口设计合理性\n│   ├─ 确认接口文档完整性\n│   ├─ 评估错误码设计\n│   └─ 评估版本兼容性\n│\n└─ 数据库设计评审\n    ├─ 评估表结构设计\n    ├─ 评估索引设计\n    ├─ 评估数据迁移方案\n    └─ 评估数据一致性\n```\n\n### 阶段3：开发阶段\n\n```text\n测试活动：\n├─ 代码评审\n│   ├─ 从测试角度Review代码\n│   ├─ 识别潜在Bug模式\n│   ├─ 评估异常处理\n│   └─ 评估日志记录\n│\n├─ 单元测试支持\n│   ├─ 协助开发设计测试用例\n│   ├─ 提供测试数据建议\n│   ├─ 验证单元测试覆盖\n│   └─ 评审单元测试质量\n│\n└─ 接口测试\n    ├─ 编写接口测试用例\n    ├─ 验证接口契约\n    ├─ 测试接口边界条件\n    └─ 执行接口自动化测试\n```"},{"path":"skill-card.md","content":"## Description:\n\nHelps QA teams shift testing into requirements, design, and development through testability reviews, acceptance criteria, and early test planning.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kokxi](https://clawhub.ai/user/kokxi)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nQA practitioners and developers use this skill to plan early testing involvement, review requirements and designs for testability, and prepare acceptance criteria and quality gates.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The optional companion workflow install command is not pinned to a release.\n\nMitigation: Confirm the companion source is trusted and use a reviewed commit or pinned version before installing.\n\n## Reference(s):\n\n- [Shift-left testing stages](references/shift-left-stages.md)\n- [ClawHub skill release](https://clawhub.ai/kokxi/skills/qa-shift-left)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown]\n\n**Output Format:** [Markdown checklists and plans]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include early intervention activities, quality gates, and team enablement recommendations.]\n\n## Skill Version(s):\n\n1.8.0 (source: skill metadata and ClawHub release)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design during development, and technical design review. Skill: qa-shift-left Owner: kokxi Summary: 当项目还在需求阶段或者开发正在写代码时使用此技能——这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审（需求模糊/矛盾/不可测）、开发阶段测试设计（单元测试/接口契约/测试桩）和技术方案评审（影响面分析/风险识别）三个维度提前发现缺陷。越早发现 Bug 修复成本越低——需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景：测试左移、左移、提前测试、需求可测试性（左移阶段）、需求评审（左移介入）、开发阶段测、项目早期需要介入测试时。 Use when the user asks about: shifting testing left into requirements and development — requirement testability review, test design","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":899,"uniquenessScore":51,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T10:04:12.790Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T10:04:12.790Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T14:13:34.085Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}