360 Secure SkillHub
360 安全技能中心

Skill Cortex Pub

当已安装 Skill 无法完成任务时触发:读取本地 cortex 记忆并做语义匹配,未命中则检索 ClawHub 候选;向用户展示安全信息并等待明确确认后安装、生成执行计划并执行,失败时自动恢复或切换候选(最多 2 次);随后更新记忆,成功加权、失败衰减。仅管理短期能力记忆,不干预长期 Skill。

ankwu001
ankwu001
热度 63.86
最近更新 2026-05-11 17:27:40
分类:自动化依赖:读写文件 / 第三方 API应用场景:工作流 / 任务管理

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add skill-cortex-pub
Metadata
name
skill-cortex
description
Skill Cortex is the system's capability cortex. When lacking ability, it autonomously acquires Skills from ClawHub or GitHub, then releases them after use. Every invocation is learned and reinforced by the cortex — future identical tasks fire as reflexes, bypassing search. Manages only short-term capability memory; never interferes with long-term Skills. Continuously restructures its own capability architecture through reinforcement and decay, achieving ongoing evolution.

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).
  2. Semantically match the users task description against sensory.patterns signals.
  3. 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.
  2. Installation requires user confirmation.
  3. System dependency installation requires separate confirmation.
  4. Write operations never enter reflex.
  5. Max 2 candidate switches.