{"id":"f8b34f94-6fda-4a97-b8a5-8d727ca4e86a","slug":"clawhub-kokxi-qa-expert-review","name":"qa-expert-review","description":"当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验，从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题（比如遗漏了某个关键模块），需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式——发现的问题必须闭环。 触发场景：专家评审、用例审查、校正反馈、评审用例、检查用例、终审、用例上线前需要终审时。 Use when the user asks about: final human-style review of AI-generated test cases before shipping, sampling for business validity, scenario completeness, and executability.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kokxi-qa-expert-review","sourceUrl":"https://clawhub.ai/kokxi/qa-expert-review","homepage":"https://clawhub.ai/kokxi/skills/qa-expert-review","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/kokxi/skills/qa-expert-review"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"1.8.0","freshnessAt":"2026-10-11T11:52:17.197Z","freshnessLabel":"Oct 11, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 11, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"1.8.0"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/kokxi/skills/qa-expert-review","sourceUrl":"https://clawhub.ai/kokxi/skills/qa-expert-review","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T11:52:17.276Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-expert-review/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-expert-review/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-11T11:52:17.276Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1.1K downloads","href":"https://clawhub.ai/kokxi/qa-expert-review","sourceUrl":"https://clawhub.ai/kokxi/qa-expert-review","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T11:52:17.276Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.8.0","href":"https://clawhub.ai/kokxi/qa-expert-review","sourceUrl":"https://clawhub.ai/kokxi/qa-expert-review","sourceType":"release","confidence":"medium","observedAt":"2026-09-29T04:26:35.102Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-expert-review/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-expert-review/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1.1K downloads","Trust evidence available"],"agentCard":{"name":"qa-expert-review","description":"当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验，从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题（比如遗漏了某个关键模块），需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式——发现的问题必须闭环。 触发场景：专家评审、用例审查、校正反馈、评审用例、检查用例、终审、用例上线前需要终审时。 Use when the user asks about: final human-style review of AI-generated test cases before shipping, sampling for business validity, scenario completeness, and executability.","source":"CLAWHUB","sourceId":"clawhub:s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-expert-review","homepage":"https://clawhub.ai/kokxi/skills/qa-expert-review","repository":"https://clawhub.ai/kokxi/qa-expert-review","documentation":"https://www.xpersona.co/agent/clawhub-kokxi-qa-expert-review","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"text","snippet":"抽样方法：\n├─ 随机抽样：10-20%的用例\n├─ 分层抽样：P0用例100%覆盖，P1抽样50%，P2抽样20%\n├─ 风险抽样：高风险用例100%覆盖\n└─ 新功能抽样：新功能用例100%覆盖\n\n抽样公式：\n总用例数 < 50 → 全量评审\n总用例数 50-200 → 20%抽样\n总用例数 > 200 → 10%抽样 + P0全量"},{"kind":"example","language":"text","snippet":"校正标记格式：\n├─ [C-001] 问题类型：描述问题\n├─ [C-002] 问题类型：描述问题\n└─ ...\n\n问题类型：\n├─ MISSING：缺失场景\n├─ WRONG：步骤/预期错误\n├─ VAGUE：描述模糊\n├─ REDUNDANT：冗余用例\n├─ RISK：风险覆盖不足\n└─ FORMAT：格式不规范"}]}}