跳到正文
TakoAPI
返回技能列表

metacognition

由 meimakes 提供

AI & LLMs
—暂无评分
你的评分

简介

Self-reflection engine for AI agents.

描述

该技能的功能

Extracts patterns from AI agent session transcripts into a weighted knowledge graph. Repeated insights strengthen over time through Hebbian reinforcement, while unused ones decay. Compiles a token-budgeted summary called the metacognition lens for use in future sessions.

Persists cross-session learning with weighted decay, avoiding the loss of accumulated context that comes with static system prompts or per-session memory alone.

何时使用

  • Identifying recurring mistakes an agent makes across sessions
  • Tracking user communication preferences over time
  • Automatically pruning outdated or weakened beliefs via decay
  • Discovering higher-level principles from specific session events
  • Running scheduled self-reflection cycles on a cron timer

示例工作流

输入

User asks: run the metacognition integration cycle

智能体
  1. 1

    Run python3 scripts/metacognition.py decay to prune weak entries

  2. 2

    Read recent session transcripts using sessions_list and sessions_history

  3. 3

    Analyze conversation for recurring patterns, relationship signals, and confidence mismatches

  4. 4

    Add 1-3 principle-level insights with typed categories such as overrides, decisions, or curiosities

  5. 5

    Run reweave then compile to rebuild graph connections and regenerate the metacognition lens

输出

Updated metacognition-lens.md with reinforced insights and newly extracted principles, ready for injection into the next session context

安装

clawhub install meimakes/metacognition

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接