Skill Cortex
Triggers when installed Skills cannot complete the current task. If you can handle it yourself, just do it — do not trigger this flow.
Cortex data file: ~/.openclaw/skill-cortex/cortex.json (schema in DESIGN.md).
Phase 1: Perception
- 1. Read cortex.json (if missing or corrupt, skip to step 3).
- Semantically match the users task description against sensory.patterns signals.
- On miss, search ClawHub.
Phase 2: Validation
Present candidates to the user with safety info. Wait for explicit approval before installing.
Phase 3: Execution
Install the Skill, generate an execution plan, execute the task. On failure, auto-recover or switch to next candidate.
Phase 4: Learning
Update the cortex memory. Successful Skills gain weight; failed ones decay.
Boundary Rules
- 1. Never interfere with long-term Skills.
- Installation requires user confirmation.
- System dependency installation requires separate confirmation.
- Write operations never enter reflex.
- Max 2 candidate switches.
技能皮层
当已安装的技能无法完成当前任务时触发。如果你自己能处理，直接执行即可——不要触发此流程。
皮层数据文件：~/.openclaw/skill-cortex/cortex.json（模式定义见DESIGN.md）。
第一阶段：感知
- 1. 读取cortex.json（若文件缺失或损坏，跳至步骤3）。
- 将用户任务描述与sensory.patterns信号进行语义匹配。
- 匹配失败时，搜索ClawHub。
第二阶段：验证
向用户展示候选方案并附带安全信息。等待用户明确批准后方可安装。
第三阶段：执行
安装技能，生成执行计划，执行任务。若执行失败，自动恢复或切换至下一候选方案。
第四阶段：学习
更新皮层记忆。成功执行的技能获得权重提升，失败的技能权重衰减。
边界规则
- 1. 绝不干扰长期技能。
- 安装需经用户确认。
- 系统依赖项安装需单独确认。
- 写入操作绝不进入反射流程。
- 最多切换2次候选方案。
