Metacognition Control

Community

kangarooking

metacognition-control

通过元认知三阶段控制大脑信息处理流程。当你"知道该做什么但做不到"、情绪被绑架后无法理性思考、或需要系统性提高大脑信息处理质量时使用。三阶段：控制输入（注意力把关信息入口）→控制大脑（对信息丢弃/储存/处理）→控制输出（将思考结果高质量执行）。不适用于需要快速本能反应的紧急场景。关键触发信号："知道但做不到""我又情绪化了""脑子很乱""学了但用不出来"。

Overview

Publisher	kangarooking
Repository	`cognitive-dividend-skill`
Skill name	`metacognition-control`
Stars	54
Forks	13
Bundled files	1
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by kangarooking on GitHub. Read the source before you install it.

Installation

Install the Metacognition Control AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/kangarooking/cognitive-dividend-skill/tree/main/metacognition-control
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/kangarooking/cognitive-dividend-skill/tree/main/metacognition-control

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/kangarooking/cognitive-dividend-skill.git /tmp/cognitive-dividend-skill
mkdir -p .claude/skills
cp -r /tmp/cognitive-dividend-skill/metacognition-control .claude/skills/metacognition-control

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Metacognition Control in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Metacognition Control on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Metacognition Control is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

元认知三阶段控制

R — 原文 (Reading)

"元认知，就是你对自己思考过程的认知与理解……大脑只是你身体上的一个器官，和手和脚是一样的，你是可以使用'元认知'来控制的！元认知，就是控制你大脑的那个真正的大脑。"

"元认知，就是能让你清晰地看见这整个过程，并且由你自己来全权接管这三个环节：第一，控制输入……第二，控制大脑……启动元认知，按信息的不同，选择以下三种处理方式：1.对无用的信息：丢弃；2.对有益的信息：储存；3.对需要主动处理的信息：处理。"

—— 《认知红利》第7章

I — 方法论骨架 (Interpretation)

元认知的核心定义：对自己思考过程的认知与理解。即"你知道自己在想什么，并且能控制自己怎么想"。大脑是一个器官（如同手和脚），可以被你控制；你是站在大脑背后的那个"真正的大脑"
大脑的工作模型简化为三个阶段：信息输入 → 黑盒子（处理）→ 输出结果。没有元认知时，黑盒子是自动运行的；开启元认知后，你全权接管三个环节
三阶段控制法：
- 控制输入：注意力决定接收什么信息，信息决定思考什么，思考决定输出，输出决定人生。用元认知像杀毒软件一样把关，对不合格信息零容忍
- 控制大脑：对进入大脑的信息分三类处理：(1) 无用信息→丢弃（识别标准：建立正确认知基线后自然能辨别错误）；(2) 有益信息→储存（概念、价值观、思维方式、方法论四大类）；(3) 需要处理的信息→调取对应的思考方式/方法论进行处理
- 控制输出：将思考结果在行为层高质量执行。没有元认知，即使知道该做什么也可能做不好（拖延、情绪干扰、执行走样）
提高元认知能力的三种方法：读书（对比作者思维 vs 自己思维）、冥想（练习拉回注意力的控制力）、每日反思（复盘思考过程本身）

A1 — 书中应用 (Past Application)

用刷抖音的例子对比有无元认知的状态：无元认知时不知不觉3小时过去；有元认知时大脑会出现"纠错声音"："你为什么会不停地翻看？你的注意力是不是正在被别人收割？"然后主动关掉
用手机与使用者的关系类比：CPU是计算机的大脑，程序控制CPU，人控制程序；同理，大脑是器官，元认知是控制大脑的"人"
用110报警的类比说明信息处理：大脑里储存的"思维方式/方法论"像App，"概念"像通讯录，处理问题时先判断问题类型，再启动对应的App
用冥想练习的体验描述元认知锻炼的过程：一开始"元认知"和"大脑"反复拉锯，逐渐能控制更长时间

A2 — 触发场景 (Future Trigger)

何时使用此 skill：

知道该做什么但做不到（知道该学习但刷了手机、知道不该发脾气但发了）
情绪被负面信息/事件绑架，无法理性思考
学了很多知识但用不出来（输入了但输出不了）
脑子里很乱，无法集中精力处理复杂问题
需要提高决策质量（避免大脑自动驾驶模式）

语言信号：

"知道但做不到"
"我又情绪化了"
"脑子很乱"
"学了但用不出来"
"控制不住自己"
"我又被大脑绑架了"
"为什么我明知不对还是忍不住"

与相邻 skill 区分：

与 attention-management 的区别：本 skill 聚焦"如何控制大脑处理信息的完整流程（输入→处理→输出）"；attention-management 聚焦"注意力该投向哪些高回报方向"的宏观分配
与 nlp-levels 的区别：本 skill 是信息处理的操作层控制；nlp-levels 是理解层次的战略层定位
如果问题是"我不知道注意力该投向哪里"→ 用 attention-management
如果问题是"我不知道自己该成为什么样的人"→ 用 nlp-levels
如果问题是"我知道该做什么但控制不住自己的大脑"→ 用 metacognition-control

E — 可执行步骤 (Execution)

步骤1：启动元认知觉察

在一天中设置3个固定时间点（如9:00、14:00、21:00），用闹钟提醒自己做10秒元认知检查
检查内容：此刻我在想什么？我的大脑处于自动驾驶还是有意识控制？
如果发现自动驾驶（无目的刷手机、被情绪裹挟、脑中重复无效念头），立即暂停
完成标准：连续7天完成每日3次元认知检查，记录觉察到的"自动驾驶"次数

步骤2：建立三阶段控制流程

输入控制：列出你每天的主要信息来源，标注每个来源是"营养"还是"垃圾食品"。对垃圾来源设置物理阻断（取消关注、卸载、关闭通知）
大脑控制：面对每条进入大脑的信息，用3秒判断：丢弃？储存？处理？每周整理一次储存库（概念、价值观、思维方式、方法论四个分类）
输出控制：在执行重要任务前用1分钟预演：预期输出是什么？可能的干扰是什么？如何应对？
完成标准：信息来源清单（标注营养/垃圾）+ 四分类储存库初始版 + 执行前预演连续实践5次

步骤3：通过冥想强化元认知肌肉

每天花15分钟进行专注冥想：闭眼、专注呼吸、当走神时用元认知将注意力拉回
记录每次冥想中"拉回注意力"的次数，观察是否逐周增加
将冥想中练到的"觉察→拉回"能力迁移到日常工作：当大脑自动驾驶时，用同样的方式拉回
完成标准：连续14天完成15分钟冥想，记录拉回次数，观察到第2周比第1周有明显提升

B — 边界 (Boundary)

不要用的场景：

紧急情况需要快速本能反应时不要启动元认知分析（如刹车避险、火灾逃生），此时过度思考反而危险
在深度心流状态中不要中断去"检查元认知"——心流本身就是高质量的大脑运作状态
与伴侣或朋友进行情感交流时，不要用元认知的"分析模式"替代"感受模式"，否则对方会觉得你冷漠

失败模式：

把元认知变成"过度思考"——每个念头都要分析，导致决策瘫痪
过度控制输入，导致信息茧房——只看"有益"信息，隔绝了意外的灵感和趋势信号
储存了大量信息但从不处理和输出，大脑变成了仓库而非工厂
只在冥想时能控制注意力，日常生活中仍然自动驾驶（冥想与生活脱节）

作者盲点：

对元认知能力"强弱"的讨论过于笼统，缺乏可量化的评估标准
"丢弃/储存/处理"的三分类过于简化，现实中大量信息处于灰色地带（可能有用但不确定什么时候用）
三种提高方法的优先级不明确，读者可能三项都想做但精力不够
未讨论元认知过度活跃的负面影响（如焦虑症患者的过度自我监控）
对"如何判断一条信息是否有益"的操作标准不够具体

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

test-prompts.json2 KB

Frequently asked questions

What does the Metacognition Control AI skill do?

Why use Metacognition Control on TypingMind?

Because you install it once and use it with any model. Metacognition Control is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Metacognition Control in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/cognitive-dividend-skill/tree/main/metacognition-control. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Metacognition Control?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Metacognition Control?

As many as you like. As long as a model supports skills, you can use Metacognition Control with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Metacognition Control AI skill free?

Yes. It is published on GitHub by kangarooking under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Plan Change

ruvnet

CommunityPopular

Turn a feature request into a minimal, file-level implementation plan before any code.

Simplified English

Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the…

Archify Review

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

Adr Verify

Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles

Metacognition Control

Overview