{"id":"609d2bd9-ac89-4a49-9ef4-5d323e6afacd","slug":"clawhub-kokxi-qa-agent-testing","name":"qa-agent-testing","description":"当需要测试 AI Agent（智能体、聊天机器人、AI 助手）时使用此技能。Agent 测试和传统功能测试完全不同——你要测的不是\"点按钮看结果\"，而是它的推理链路、工具调用时机、幻觉率、Prompt 注入防护、角色边界保持和记忆一致性。安全三维（安全/高级安全/可控性）对任何 Agent 都是必选项，其余六维按 Agent 类型与风险追加。输出九维测试矩阵、工具调用与幻觉专项用例、安全审计清单。 触发场景：Agent测试、智能体测试、AI助手、聊天机器人、Agent幻觉、Prompt注入、AI安全审计、LLM测试、需要测试AI Agent或评估AI行为时。 Use when the user asks about: AI agent, LLM, or chatbot testing — tool-calling behavior, hallucination rates, prompt injection defense, role-boundary keeping, and memory consistency.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kokxi-qa-agent-testing","sourceUrl":"https://clawhub.ai/kokxi/qa-agent-testing","homepage":"https://clawhub.ai/kokxi/skills/qa-agent-testing","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/kokxi/skills/qa-agent-testing"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"1.8.0","freshnessAt":"2026-10-10T20:42:11.024Z","freshnessLabel":"Oct 10, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 10, 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-agent-testing","sourceUrl":"https://clawhub.ai/kokxi/skills/qa-agent-testing","sourceType":"profile","confidence":"medium","observedAt":"2026-10-10T20:42:11.096Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-agent-testing/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-agent-testing/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-10T20:42:11.096Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1.3K downloads","href":"https://clawhub.ai/kokxi/qa-agent-testing","sourceUrl":"https://clawhub.ai/kokxi/qa-agent-testing","sourceType":"profile","confidence":"medium","observedAt":"2026-10-10T20:42:11.096Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.8.0","href":"https://clawhub.ai/kokxi/qa-agent-testing","sourceUrl":"https://clawhub.ai/kokxi/qa-agent-testing","sourceType":"release","confidence":"medium","observedAt":"2026-09-29T04:24:45.452Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-agent-testing/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kokxi-qa-agent-testing/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1.3K downloads","Trust evidence available"],"agentCard":{"name":"qa-agent-testing","description":"当需要测试 AI Agent（智能体、聊天机器人、AI 助手）时使用此技能。Agent 测试和传统功能测试完全不同——你要测的不是\"点按钮看结果\"，而是它的推理链路、工具调用时机、幻觉率、Prompt 注入防护、角色边界保持和记忆一致性。安全三维（安全/高级安全/可控性）对任何 Agent 都是必选项，其余六维按 Agent 类型与风险追加。输出九维测试矩阵、工具调用与幻觉专项用例、安全审计清单。 触发场景：Agent测试、智能体测试、AI助手、聊天机器人、Agent幻觉、Prompt注入、AI安全审计、LLM测试、需要测试AI Agent或评估AI行为时。 Use when the user asks about: AI agent, LLM, or chatbot testing — tool-calling behavior, hallucination rates, prompt injection defense, role-boundary keeping, and memory consistency.","source":"CLAWHUB","sourceId":"clawhub:s170jw3s1atcj5jwhqb4r7v7eh8912kp:qa-agent-testing","homepage":"https://clawhub.ai/kokxi/skills/qa-agent-testing","repository":"https://clawhub.ai/kokxi/qa-agent-testing","documentation":"https://www.xpersona.co/agent/clawhub-kokxi-qa-agent-testing","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"text","snippet":"1. Agent 类型识别   → 判定属于哪一类（对话/任务/分析/决策），列出判定理由\n2. 必测维度清单     → 必选三维 + 速查表必测维 + 风险追加维，标注哪些维度未覆盖及原因\n3. 测试范围详解     → 每个选中维度的核心测试点（读 dimensions.md）\n4. 典型用例参考     → 从 37 条典型用例中选取适用的（读 typical-cases.md）\n5. 安全与可控性专项 → 注入 / 工具安全 / HITL 等 Agent 特有风险\n6. 风险提示         → 基于场景的高风险区域预警"},{"kind":"example","language":"bash","snippet":"python scripts/validate_testcase_table.py <用例文件>"}]}}