{"id":"f4b99450-6ea0-4e42-ab8d-688e4742cf94","slug":"clawhub-robin-chen2025-autocraft","name":"AutoCraft","description":"AI-powered project execution platform. Non-technical product managers can drive complex software projects with 3-6x efficiency. 10-day case study: education platform with 71 tasks (99% success). One-click install.\nAI驱动的项目执行平台。不懂代码也能驱动复杂软件开发，效率提升3-6倍。10天案例：71个任务，99%成功率。一键安装，自动部署。","canonicalUrl":"https://www.xpersona.co/agent/clawhub-robin-chen2025-autocraft","sourceUrl":"https://clawhub.ai/robin-chen2025/autocraft","homepage":"https://clawhub.ai/robin-chen2025/skills/autocraft","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/robin-chen2025/skills/autocraft"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"2.1.0","freshnessAt":"2026-10-11T16:21:19.970Z","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":"2.1.0"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/robin-chen2025/skills/autocraft","sourceUrl":"https://clawhub.ai/robin-chen2025/skills/autocraft","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T16:21:20.051Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-robin-chen2025-autocraft/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-robin-chen2025-autocraft/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-11T16:21:20.051Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1K downloads","href":"https://clawhub.ai/robin-chen2025/autocraft","sourceUrl":"https://clawhub.ai/robin-chen2025/autocraft","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T16:21:20.051Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"2.1.0","href":"https://clawhub.ai/robin-chen2025/autocraft","sourceUrl":"https://clawhub.ai/robin-chen2025/autocraft","sourceType":"release","confidence":"medium","observedAt":"2026-05-20T02:32:11.115Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-robin-chen2025-autocraft/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-robin-chen2025-autocraft/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1K downloads","Trust evidence available"],"agentCard":{"name":"AutoCraft","description":"AI-powered project execution platform. Non-technical product managers can drive complex software projects with 3-6x efficiency. 10-day case study: education platform with 71 tasks (99% success). One-click install.\nAI驱动的项目执行平台。不懂代码也能驱动复杂软件开发，效率提升3-6倍。10天案例：71个任务，99%成功率。一键安装，自动部署。","source":"CLAWHUB","sourceId":"clawhub:s17egxbv37nwvez7zjabx4h56s870q2r:autocraft","homepage":"https://clawhub.ai/robin-chen2025/skills/autocraft","repository":"https://clawhub.ai/robin-chen2025/autocraft","documentation":"https://www.xpersona.co/agent/clawhub-robin-chen2025-autocraft","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"text","snippet":"BUILD-TEST（只写测试，不运行，不改程序代码）→ BUILD-CODE（写程序代码 + pytest验证）→ TEST-RUN（独立运行 + 深入分析根因）→\n  ├─ 全部通过 → 完成\n  └─ 有失败 → TEST-RUN分析根因并记录issues →\n       ├─ test_issue → 项目经理决定是否创建新BUILD-TEST修复\n       ├─ code_issue → 项目经理决定是否创建新BUILD-CODE修复\n       └─ env_issue → 项目经理决定是否修复环境"},{"kind":"example","language":"text","snippet":"1. 读取任务信息(忽略之前的会话上下文)\n2. 识别任务类型 → 选择对应行为模式\n3. 读取输入文件(设计文档、规范文件等)\n4. 执行任务 → 产出物写入项目目录(按任务指定的 deliverables 路径)\n5. 写JSON结果文件到 /tmp/autocraft_output/{task_id}_execution_result.json\n6. 结束"}]}}