{"id":"334db200-f82b-4d65-a67f-11c65976418c","slug":"clawhub-kokxi-qa-ai-output-critique","name":"qa-ai-output-critique","description":"对AI生成的测试用例进行八维评审（完整性、正确性、可执行性、风险覆盖、规范性、一致性、追溯性、冗余度），是AI生成用例后的第一个质量门禁。当AI刚刚生成了一大批测试用例、你需要确保这些用例真的有价值而不是\"看起来不错\"时，应当使用此技能。不要假设AI输出的都是对的——AI经常生成语义正确但实际操作不了的用例。每个维度评分低于7分的必须标注问题并使用MISSING/WRONG/VAGUE等规范格式标记。无上游场景树/风险清单时降级为六维评审（跳过追溯性、简化完整性）。 触发场景：检查一下输出、评审用例质量、验证完整性、这个用例对吗、自动检查时。 Use when the user asks about: critiquing AI-generated test cases across completeness, correctness, executability, risk coverage, conformance, consistency, traceability, and redundancy.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kokxi-qa-ai-output-critique","sourceUrl":"https://clawhub.ai/kokxi/qa-ai-output-critique","homepage":"https://clawhub.ai/kokxi/skills/qa-ai-output-critique","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/kokxi/skills/qa-ai-output-critique"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"1.8.0","freshnessAt":"2026-10-11T11:15:03.959Z","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-ai-output-critique","sourceUrl":"https://clawhub.ai/kokxi/skills/qa-ai-output-critique","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T11:15:04.028Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-output-critique/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-output-critique/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-11T11:15:04.028Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1.1K downloads","href":"https://clawhub.ai/kokxi/qa-ai-output-critique","sourceUrl":"https://clawhub.ai/kokxi/qa-ai-output-critique","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T11:15:04.028Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.8.0","href":"https://clawhub.ai/kokxi/qa-ai-output-critique","sourceUrl":"https://clawhub.ai/kokxi/qa-ai-output-critique","sourceType":"release","confidence":"medium","observedAt":"2026-09-29T04:25:07.399Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-output-critique/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-output-critique/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1.1K downloads","Trust evidence available"],"agentCard":{"name":"qa-ai-output-critique","description":"对AI生成的测试用例进行八维评审（完整性、正确性、可执行性、风险覆盖、规范性、一致性、追溯性、冗余度），是AI生成用例后的第一个质量门禁。当AI刚刚生成了一大批测试用例、你需要确保这些用例真的有价值而不是\"看起来不错\"时，应当使用此技能。不要假设AI输出的都是对的——AI经常生成语义正确但实际操作不了的用例。每个维度评分低于7分的必须标注问题并使用MISSING/WRONG/VAGUE等规范格式标记。无上游场景树/风险清单时降级为六维评审（跳过追溯性、简化完整性）。 触发场景：检查一下输出、评审用例质量、验证完整性、这个用例对吗、自动检查时。 Use when the user asks about: critiquing AI-generated test cases across completeness, correctness, executability, risk coverage, conformance, consistency, traceability, and redundancy.","source":"CLAWHUB","sourceId":"clawhub:s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-ai-output-critique","homepage":"https://clawhub.ai/kokxi/skills/qa-ai-output-critique","repository":"https://clawhub.ai/kokxi/qa-ai-output-critique","documentation":"https://www.xpersona.co/agent/clawhub-kokxi-qa-ai-output-critique","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"markdown","snippet":"# 测试用例评审报告\n\n## 一、八维评分          → 每维 10 分，<7 分标问题\n## 二、问题清单          → 用例 ID | 维度 | 标记 | 问题描述 | 修正建议\n## 三、覆盖遗漏          → 必须给依据 ID（RISK- / REQ- / SC-）\n## 四、改进方向          → 可执行的具体动作\n## 五、评审结论          → 需重新生成 / 需修改后复审 / 通过"},{"kind":"example","language":"text","snippet":"请列出你在输出中做的所有假设。\n哪些假设可能不成立？\n如果假设不成立，测试场景会有什么变化？"}]}}