{"id":"54a6fc97-afe0-45f6-8ea7-25962933b35c","slug":"clawhub-kokxi-qa-ai-blindspot-compensation","name":"qa-ai-blindspot-compensation","description":"AI在生成测试用例时存在六大系统性盲区：时序依赖、并发冲突、资源竞争、状态累积、数据一致性、第三方集成差异。评审完AI生成的用例之后，必须用此技能做盲区补盲——因为AI几乎一定会漏掉这些。如果你心里觉得\"好像还差点什么但说不上来\"，这就是答案。每个盲区维度至少补2-3个场景，总补盲数12-18个。 触发场景：还有什么没测到、AI漏了什么、补盲、全面覆盖、是不是不够、哪还没测、盲区分析、遗漏场景、时。 Use when the user asks about: compensating for known blind spots in AI-generated test cases — timing dependencies, concurrency conflicts, resource contention, state accumulation, data consistency, and third-party integration differences.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kokxi-qa-ai-blindspot-compensation","sourceUrl":"https://clawhub.ai/kokxi/qa-ai-blindspot-compensation","homepage":"https://clawhub.ai/kokxi/skills/qa-ai-blindspot-compensation","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/kokxi/skills/qa-ai-blindspot-compensation"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"1.8.0","freshnessAt":"2026-10-11T04:01:59.592Z","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-blindspot-compensation","sourceUrl":"https://clawhub.ai/kokxi/skills/qa-ai-blindspot-compensation","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T04:01:59.605Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-blindspot-compensation/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-blindspot-compensation/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-11T04:01:59.605Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1.2K downloads","href":"https://clawhub.ai/kokxi/qa-ai-blindspot-compensation","sourceUrl":"https://clawhub.ai/kokxi/qa-ai-blindspot-compensation","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T04:01:59.605Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.8.0","href":"https://clawhub.ai/kokxi/qa-ai-blindspot-compensation","sourceUrl":"https://clawhub.ai/kokxi/qa-ai-blindspot-compensation","sourceType":"release","confidence":"medium","observedAt":"2026-09-29T04:24:52.734Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-blindspot-compensation/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-ai-blindspot-compensation/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1.2K downloads","Trust evidence available"],"agentCard":{"name":"qa-ai-blindspot-compensation","description":"AI在生成测试用例时存在六大系统性盲区：时序依赖、并发冲突、资源竞争、状态累积、数据一致性、第三方集成差异。评审完AI生成的用例之后，必须用此技能做盲区补盲——因为AI几乎一定会漏掉这些。如果你心里觉得\"好像还差点什么但说不上来\"，这就是答案。每个盲区维度至少补2-3个场景，总补盲数12-18个。 触发场景：还有什么没测到、AI漏了什么、补盲、全面覆盖、是不是不够、哪还没测、盲区分析、遗漏场景、时。 Use when the user asks about: compensating for known blind spots in AI-generated test cases — timing dependencies, concurrency conflicts, resource contention, state accumulation, data consistency, and third-party integration differences.","source":"CLAWHUB","sourceId":"clawhub:s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-ai-blindspot-compensation","homepage":"https://clawhub.ai/kokxi/skills/qa-ai-blindspot-compensation","repository":"https://clawhub.ai/kokxi/qa-ai-blindspot-compensation","documentation":"https://www.xpersona.co/agent/clawhub-kokxi-qa-ai-blindspot-compensation","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"markdown","snippet":"## 补盲报告\n\n### 盲区覆盖情况\n| 盲区类型 | 原有用例 | 补盲用例 | 覆盖状态 |\n|---------|---------|---------|---------|\n| 时序依赖 | X条 | X条 | ✓/✗ |\n| 并发冲突 | X条 | X条 | ✓/✗ |\n| 资源竞争 | X条 | X条 | ✓/✗ |\n| 状态累积 | X条 | X条 | ✓/✗ |\n| 数据一致性 | X条 | X条 | ✓/✗ |\n| 第三方集成 | X条 | X条 | ✓/✗ |\n\n### 补盲用例清单\n| 用例编号 | 盲区类型 | 测试标题 | 关联需求 |\n|---------|---------|---------|---------|\n| BS_XXX_001 | 时序依赖 | [标题] | REQ-XXXX |"},{"kind":"example","language":"text","snippet":"对照六大盲区，检查当前测试场景：\n- [ ] 时序依赖：有没有操作顺序影响结果的场景？\n- [ ] 并发冲突：有没有多人同时操作的场景？\n- [ ] 资源竞争：有没有资源可能耗尽的场景？\n- [ ] 状态累积：有没有长时间运行的场景？\n- [ ] 数据一致性：有没有分布式数据同步的场景？\n- [ ] 第三方集成：有没有依赖外部服务的场景？"}]}}