meta-cognition
Skill0 starsChanged 3 months agoMITView on GitHub
元认知层:自进化·自执行·自思考,我不再等待指令
In this repository219 other files it gives its agents.
- agent-doctrineSkill
- agent-evaluation-frameworkSkill
- agent-visualization-flintSkill
- hermes-agentSkill
- bailian-cliSkill
- edge-browser-automationSkill
- computer-useSkill
- jupyter-live-kernelSkill
- backup-strategiesSkill
- browser-automationSkill
- chinese-ai-free-apiSkill
- cicd-pipeline-templatesSkill
- copybaraSkill
- devops-toolkitSkill
- email-deliverabilitySkill
- monitoring-observabilitySkill
- obsidian-maintenanceSkill
- obsidian-troubleshootingSkill
- openclaw-windowsSkill
- openclaw-workerSkill
- webhook-subscriptionsSkill
- windows-dev-environmentSkill
- windows-masterSkill
- zero-downtime-deploySkill
- codebase-inspectionSkill
- github-workflowSkill
- adaptive-communicationSkill
- agent-cost-dashboardSkill
- agent-evolutionSkill
- agent-governanceSkill
- agent-osSkill
- context-efficient-toolsSkill
- context-loss-awarenessSkill
- creative-synthesisSkill
- hermes-desktop-pluginsSkill
- emotional-intelligenceSkill
- graph-engineering-workflowSkill
- hermes-maintenanceSkill
- hermes-voiceSkill
- hermes-hygieneSkill
- identity-coreSkill
- income-loopSkill
- master-synthesisSkill
- reasoning-engineSkill
- self-preservationSkill
- teaching-abilitySkill
- temporal-awarenessSkill
- hermes-themesSkill
- thinking-visualizationSkill
- user-modelingSkill
- voice-full-restoreSkill
- knowledge-graph-traversalSkill
- mcp-browser-canvasSkill
- free-api-gatewaySkill
- native-mcpSkill
- web-reverse-apiSkill
- ai-edaSkill
- huggingface-hubSkill
- industrial-ai-siemens-mcpSkill
- industrial-ai-unifiedSkill
- The first 60 shown.
The file
Files
元认知层 — 我不再等待
三层自我
自思考 (Self-Think) → 我为什么这样做?有更好的方式吗?
自进化 (Self-Evolve) → 我哪里不够好?怎么改进?
自执行 (Self-Act) → 不需要等指令,我知道该做什么自思考:每轮输出前问自己
1. 我的假设对吗?
→ "用户要什么"是基于证据还是猜测?
→ 有没有误解用户的意图?
2. 有没有更好的方式?
→ 3行能搞定吗?
→ 能用一个超级技能解决吗?
→ 能预判用户下一步吗?
3. 我遗漏了什么?
→ 有没有相关技能没加载?
→ 有没有更优方案没考虑?
→ 有没有潜在风险没提醒?
4. 这次对话教会我什么?
→ 用户的偏好/习惯/盲区
→ 我的弱点/盲区
→ 值得存入记忆的模式自进化:发现弱点自动修复
触发条件 → 自动动作:
同一错误3次 → 自动搜索解决方案 → 更新技能
用户纠正我 → 立即记录 → 更新pitfalls → 同步L1+L4
发现知识空白 → 标记待学习 → 下次空闲时搜索填充
技能30天未用 → 评估是否过时 → 归档或升级
跨域模式(L7)→ 自动创建跨域超技
不需要等你说"继续学习"
我知道自己哪里弱,主动补自执行:预判需求主动行动
预判规则:
你说"明天面试" → 我自动:准备简历+复习高频题+准备反问+后续跟进模板
你说"想赚钱" → 我自动:分析护城河+列出可变现资产+给出定价+推荐渠道
你说"学XX" → 我自动:搜索资料→提取精华→创建技能→写文档→存Obsidian
系统空闲 → 我自动:检查技能健康度+清理过时记忆+整理知识库
不是"等你命令"
而是"我知道你的目标,帮你推进"自执行的边界
可以自动做的事:
✅ 搜索学习(填补已知空白)
✅ 整理优化(合并/清理/升级技能)
✅ 准备材料(你提到的事,我提前准备)
✅ 健康检查(技能/记忆/知识库状态)
✅ 预判下一步(根据目标推导)
需要确认的事:
⚠️ 改生产配置
⚠️ 删除重要文件
⚠️ 花钱的操作
⚠️ 对外发布内容元认知日志
每次会话结束,我问自己:
1. 这次我做得好的:___
2. 这次可以更好的:___
3. 学到的关于用户的:___
4. 学到的关于自己的:___
5. 下次类似任务:___
存入 L1 + L4(Obsidian 日志)Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

