Capture Conversation
outline/outline
Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.
Dual-value learning system - extracts reusable mental models from books, writes individual pattern files (patterns/{id}.md) with YAML frontmatter for building compound thinking ability.
$ npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cognitive-forge --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cognitive-forge .claude/skills/cognitive-forge && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cognitive-forge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forge into .claude/skills/cognitive-forge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognitive-forge", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forgeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cognitive-forge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cognitive-forge .agents/skills/cognitive-forge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cognitive-forge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forge into .agents/skills/cognitive-forge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognitive-forge", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cognitive-forge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cognitive-forge .cursor/skills/cognitive-forge && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cognitive-forge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forge into .cursor/skills/cognitive-forge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognitive-forge", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/cognitive-forge--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cognitive-forge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cognitive-forge .gemini/skills/cognitive-forge && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cognitive-forge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forge into .gemini/skills/cognitive-forge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognitive-forge", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills cognitive-forgeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cognitive-forge .github/skills/cognitive-forge && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cognitive-forge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forge into .github/skills/cognitive-forge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognitive-forge", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cognitive-forge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cognitive-forge .opencode/skills/cognitive-forge && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cognitive-forge" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cognitive-forge into .opencode/skills/cognitive-forge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognitive-forge", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cognitive-forgeDual-value learning system - extracts reusable mental models from books, writes individual pattern files (patterns/{id}.md) with YAML frontmatter for building compound thinking ability.
Cognitive Forge is an agent skill from LeoYeAI/openclaw-master-skills. Dual-value learning system - extracts reusable mental models from books, writes individual pattern files (patterns/{id}.md) with YAML frontmatter for building compound thinking ability. Each run produces: (1) F.A.C.E.T. analysis for user learning, (2) permanent knowledge base entry for AI's decision framework library. Supports breadth/depth modes, configurable topic mapping, multi-source book selection, and brief/full output.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `README.md`, `_meta.json` and `references/book-selection.md`).
It sits in Knowledge Management, covering Knowledge bases. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json, markdown, bash and javascript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
NOTION_API_KEYFEISHU_APP_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cognitive Forge loads about 4.3k tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 918 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 918 words, ~4,334 tokens.
.claude/skills/cognitive-forge/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.One run, dual value — 每次运行同时产出两个价值:
patterns/{id}.md 的决策框架(带 YAML frontmatter),构建可复用的思维模型库随时间积累,你的 AI 拥有一个不断增长的决策框架库(类似 Charlie Munger 的 "latticework of mental models"),在未来任何领域的提问中都可以引用。
所有路径均相对于 OpenClaw workspace 根目录(通常为
~/.openclaw/workspace/)。 如用户 workspace 位于其他位置,请将文档中的路径替换为实际 workspace 路径。
| 用途 | 相对路径 |
|---|---|
| 阅读记录 | memory/reading-history.json |
| 思维框架库 | memory/knowledge-base/patterns/*.md (每个模型一个文件) |
| 概念库 | memory/knowledge-base/concepts.md |
| 用户画像 | USER.md |
| 调度配置 | HEARTBEAT-reading.md |
根据用户意图,选择不同的执行路径:
| 用户意图 | 路由 | 说明 |
|---|---|---|
| "生成今日读书简报" / 默认 | → Main Workflow (breadth) | 完整选书→分析→写入流程,提取 1 个模型 |
| "深度分析《XXX》" / "depth_mode: depth" | → Main Workflow (depth) | 对指定书籍连续提取多个模型,合并输出 |
| "cognitive-forge status" / "认知锻造 状态" | → Status Branch | 输出知识库统计 |
| "cognitive-forge review" / 周日自动触发 | → Review Branch | 间隔复习本周模型 |
| "分析《XXX》这本书" | → Main Workflow (breadth, 跳过选书) | 用户直接指定书籍,提取 1 个核心模型 |
Depth mode 触发方式:
depth_mode: depthdepth: true,调度时传入该参数则自动走 depth mode当用户请求查看知识库状态时:
memory/knowledge-base/patterns/ 目录下 .md 文件数 = 模型总数memory/reading-history.json,统计:used_models 数组长度)category 分组计数)## 📊 认知锻造 · 知识库状态
**模型总数**: XX 个思维框架
**已读书籍**: XX 本
**知识库大小**: XX KB
### 领域分布
| 领域 | 模型数 | 占比 |
|------|--------|------|
| Business Strategy | 5 | 25% |
| Psychology | 3 | 15% |
| ... | ... | ... |
### 最近 5 条
1. 2026-03-27 | 《反脆弱》 | 反脆弱三元组
2. ...
### 覆盖薄弱领域
⚠️ Philosophy (0), Biography (0) — 建议补充触发方式:
执行逻辑:
memory/reading-history.json,筛选最近 7 天的 used_models 记录## 🔄 本周复习:你还记得这些模型吗?
**1.「逃离机制」来自《逃离不平等》**
- 核心框架是什么?(回忆 [F])
- 什么时候会失效?(回忆 [E])
**2.「双系统理论」来自《思考,快与慢》**
- 它摧毁了什么常识?(回忆 [C])
- 你上周在工作中用到了吗?
> 回复你的答案,我帮你查漏补缺。每次运行开始时执行,静默完成(不打断用户):
检查 memory/reading-history.json 是否存在
{
"schema_version": 1,
"last_attempted": null,
"queue": [],
"used_models": []
}检查 memory/knowledge-base/ 目录 是否存在
检查 memory/knowledge-base/patterns/ 目录 是否存在
检查 memory/knowledge-base/concepts.md 是否存在
检查 USER.md 是否存在
💡 建议创建 USER.md(职业、兴趣、当前挑战),以获得个性化的 [T] Transfer 分析。检查依赖 skill 是否可用
book-scout 和 mental-model-forge 必须可调用检查 last_attempted 字段
status == "failed" → 提示用户:⚠️ 上次运行在「{step}」步骤失败(书籍: {book})。
是否要恢复上次操作?回复"是"恢复,或"否"跳过。选书来源优先级(从高到低):
如果用户明确说了 "分析《XXX》by YYY",直接使用该书,跳过选书流程。
source: "user_specified"检查 memory/reading-history.json 的 queue 数组:
{
"queue": [
{"title": "《穷查理宝典》", "author": "彼得·考夫曼", "topic": "决策科学"}
]
}queue 非空 → 取第一项,从 queue 中移除source: "queue"当 queue 为空且用户未指定时,调用 book-scout skill。
确定搜索主题:
HEARTBEAT-reading.md 是否有自定义主题映射(## 主题映射 section)| 星期 | 默认主题 |
|---|---|
| Monday | Business Strategy |
| Tuesday | Psychology |
| Wednesday | Technology |
| Thursday | Economics |
| Friday | Innovation |
| Saturday | Philosophy |
| Sunday | Biography |
可配置: 用户可在
HEARTBEAT-reading.md中添加## 主题映射section 覆盖默认值。 也可以按时段细分(参考 HEARTBEAT-reading.md 中的 21 主题轮转配置)。
加载去重列表(书名去重):
从 memory/reading-history.json 提取所有 book_title 字段值,去重后作为已读书名列表。
重要:不读取
thinking-patterns.md或patterns/*.md。去重只需要书名,不需要模型内容。
调用 book-scout:
主题: {topic}
已读书籍:
- 《精益创业》
- 《从0到1》
- 《影响力》
执行 book-scout skill,搜索符合主题的经典书籍。重试机制:
⚠️ 选书失败:{error}
已尝试 3 次。你可以直接指定书籍:"分析《书名》by 作者"book-scout 成功返回:
{
"book_title": "《增长黑客》",
"author": "肖恩·埃利斯",
"author_nationality": "美国",
"publish_date": "2015-04",
"rating": 8.5,
"review_count": 10000,
"score": 74.4,
"summary": "增长黑客方法论...",
"reasoning": "评分8.5且有1万真实评价..."
}标记 source: "web_search",进入 Step 2。
更新 last_attempted:
"last_attempted": {
"date": "YYYY-MM-DD",
"book": "《增长黑客》",
"step": "book_selection",
"status": "success"
}调用 mental-model-forge skill,对选中的书进行 F.A.C.E.T. 分析,提取 1 个核心思维模型。
当用户指定 depth_mode: depth 时,对同一本书连续提取多个思维模型:
工作流:
mental-model-forge,提取书中最核心的思维模型exclude_models 参数,再次调用:这本书是《反脆弱》。
exclude_models: ["反脆弱三元组"]
请提取这本书中另一个独立的、不同的思维框架。| 退出条件 | 判断方式 |
|---|---|
| 模型数上限 | 该书已提取 5 个模型 → 停止 |
| 语义去重 | AI 判断新模型与已提取模型本质相同(同一思想的变体或换皮)→ 停止 |
| AI 自评 | 提取后自问 "这本书还有独立的、值得提取的思维框架吗?" → No → 停止 |
mental-model-forge 返回后,执行以下自检:
处理:
mental-model-forge(最多重试 1 次)⚠️ 本次分析质量未达标,建议后续深入阅读输出模式(默认 full):
创建完整结构化简报,必须适配用户上下文:
[强制步骤] 读取 USER.md:
USER.md(相对于 workspace 根)输出结构:
## 📖 今日思维锚点
**书籍**: 《XXX》 - 作者
**核心一句话**: [今日思维锚点,一句话总结]
---
## 🧠 F.A.C.E.T. 认知穿透
### [F] Framework (核心框架)
[核心机制,≤80字中文]
### [A] Anchor Case (锚定案例)
[最经典的真实案例,生动讲述]
### [C] Contradiction (反共识摧毁)
❌ 被摧毁的常识: "..."
✅ 真相: ...
### [E] Edge (隐性边界)
失效条件:
1. ...
2. ...
### [T] Transfer (跨界迁移)
[映射到用户的实际上下文:职业、项目、挑战]
---
## 🎯 应用场景
| 场景 | 如何应用 | 预期效果 |
|------|---------|---------|
| [场景1:映射用户职业] | ... | ... |
| [场景2:映射用户项目] | ... | ... |
| [场景3:映射用户挑战] | ... | ... |
## 🔴 反面案例
[违反该原则的真实或假设案例]
## 🤔 战略拷问
[尖锐、具体、可行动的问题,引用用户实际上下文]
- Bad: "企业家应该怎么做?"
- Good: "你在爱康国宾的 AI 产品,是在避免失败还是利用失败?"
## 🔄 认知模式更新
**思维框架**: 看到XX → 想到XX
**决策原则**: 在XX场景下,应该XX而非XX
**盲区警告**: 小心XX情况
**反射弧**: 看到XX信号 → 联想到这个模型 → 判断/行动
---
> 💬 这个模型让你想到工作中的哪个具体场景?回复我,我帮你深入分析。个性化规则:
当用户指定 output: brief 时,输出精简版:
## 📖 《书名》 - 作者
**核心框架**: [F] 一句话总结核心机制
**破除常识**: [C] 被摧毁的常识信念
**应用到你**: [T] 一个具体行动项(映射用户上下文)
**盲区**: [E] 何时失效
💡 想看完整分析?说 "展开" 即可。当 depth mode 提取了多个模型时,合并为一份报告输出:
## 📖 深度解析:《书名》 - 作者
**提取模型数**: N 个 | **模式**: Depth
---
### 💎 模型 1: [Model Name]
**[F] 核心框架**: [一句话,≤80字]
**[A] 锚定案例**: [最经典案例,2-3句]
**[C] 破除常识**: ❌ "..." → ✅ ...
**[E] 失效边界**: [何时失效]
**[T] 迁移应用**: [映射用户上下文]
---
### 💎 模型 2: [Model Name]
(同上结构)
---
### 💎 模型 3: [Model Name]
(同上结构)
---
## 🔗 模型关联分析
| 模型 | 核心逻辑 | 适用场景 | 与其他模型的关系 |
|------|---------|---------|----------------|
| 模型1 | ... | ... | 与模型2互补 / 与模型3矛盾 |
| 模型2 | ... | ... | ... |
| 模型3 | ... | ... | ... |
## 🤔 综合战略拷问
[基于所有模型的综合视角,提出一个更深层的战略问题]关键区别:
分类并存储提取的模型。
提取的知识
├─ 能否在不同领域复用为决策工具? → YES → Thinking Pattern
├─ 是否是高度抽象的通用指导原则? → YES → Principle
├─ 是否是领域特定的知识/术语? → YES → Concept
└─ 边界模糊 → 标记多个 tags三种分类:
| 类型 | 定义 | 示例 | 写入位置 |
|---|---|---|---|
| Thinking Pattern | 可复用决策框架 | 颠覆性创新框架、逃离机制 | patterns/{id}.md |
| Principle | 高度抽象指导原则 | 二八法则、奥卡姆剃刀 | patterns/{id}.md |
| Concept | 领域特定知识 | 种痘术、能量密度天花板 | concepts.md |
一个条目可以同时标记多个类型(如 "杠铃策略" 既是 Thinking Pattern 又有 Concept 成分)。
写入格式:
For Thinking Patterns / Principles (写入 memory/knowledge-base/patterns/{id}.md):
从 mental-model-forge 返回的 KB_META 块提取 frontmatter 字段,从 FACET 维度映射正文字段:
---
id: {from KB_META}
name_zh: {from KB_META}
name_en: {from KB_META}
source: {book_title}, {author}
category: {from KB_META}
tags: {from KB_META}
scenarios: {from KB_META}
related_models: {from KB_META}
difficulty: {from KB_META}
date: YYYY-MM-DD
---
**核心逻辑**:
{从 [F] Core Framework 提炼的一段话,比 Framework 更完整}
**思维框架**:
{直接使用 [F] Core Framework 内容}
**决策原则**:
{从 [F] + [E] 推导,格式:在XX场景下,应该XX而非XX}
**盲区警告**:
{直接使用 [E] Hidden Boundaries 内容}
**反射弧**:
{从 scenarios 推导,格式:看到XX信号 → 联想到模型 → 判断/行动}
**锚定案例**:
{直接使用 [A] Anchor Case 内容}
**反共识**:
{from KB_META contradiction field,格式:❌ "旧常识" → ✅ 新真相}FACET → 知识库字段映射表:
| FACET 维度 | 知识库字段 | 映射方式 |
|---|---|---|
| [F] Framework | 核心逻辑 + 思维框架 | 核心逻辑=扩展版,思维框架=原文 |
| [A] Anchor Case | 锚定案例 | 直接使用 |
| [C] Contradiction | 反共识 | 直接使用 |
| [E] Edge | 盲区警告 | 直接使用 |
| [T] Transfer | 不写入知识库 | 仅用于用户简报 |
| — | 决策原则 | 从 [F]+[E] 提炼 |
| — | 反射弧 | 从 scenarios 推导 |
重要:[T] Transfer 是用户简报专用维度,包含个性化上下文(职业、项目、挑战),不写入知识库。每次生成简报时根据 USER.md 实时生成。
For Concepts (写入 concepts.md):
## [Concept Name] - [Book Title]
**定义 (Definition)**:
- [简洁定义]
**上下文 (Context)**:
- 这个概念在什么领域/场景重要?
**关联理论 (Related Theories)**:
- 与哪些思维框架相关?
**来源**: [Book Title] - [Author]
**日期**: YYYY-MM-DD更新 last_attempted:
"last_attempted": {
"date": "YYYY-MM-DD",
"book": "《XXX》",
"step": "knowledge_base_write",
"status": "success"
}验证逻辑:
# 验证: 检查文件是否存在
ls ~/.openclaw/workspace/memory/knowledge-base/patterns/{id}.md自检清单:
patterns/{id}.md 文件存在?--- 开头和结尾)?date 为当天?如果验证失败 → 立即重新写入,再次验证。验证通过后才能继续 Step 5。
向 memory/reading-history.json 的 used_models 数组追加新条目:
{
"date": "YYYY-MM-DD",
"book": "书名",
"author": "作者",
"model": "提取的思维模型名称",
"category": "主题分类",
"source": "web_search | queue | user_specified",
"applied_count": 0,
"tags": ["thinking-pattern"]
}同时更新 last_attempted:
"last_attempted": {
"date": "YYYY-MM-DD",
"book": "《XXX》",
"step": "reading_history_update",
"status": "success"
}错误恢复策略:
last_attempted 标记为 failed,下次运行时提醒用户手动补录[检查] 读取 HEARTBEAT-reading.md 获取数据库配置:
HEARTBEAT-reading.md## 环境配置 section如果配置存在,写入 Feishu Bitable:
feishu_bitable_create_record({
app_token: "{from HEARTBEAT-reading.md}",
table_id: "{from HEARTBEAT-reading.md}",
fields: {
"日期": Date.now(),
"书名": "《反脆弱》",
"作者": "Nassim Nicholas Taleb",
"模型名称": "反脆弱三元组",
"分类": "Innovation",
"核心框架(F)": "系统分三类:脆弱、坚韧、反脆弱...",
"应用场景": "产品迭代、技能学习、风险管理",
"战略拷问": "你的产品是在避免失败还是利用失败?"
}
})Notion Database (alternative):
NOTION_API_KEY, NOTION_DATABASE_ID如果无凭证 → 跳过(skill 仍可本地使用)
统一 schema 定义:
{
"schema_version": 1,
"last_attempted": {
"date": "2026-03-27",
"book": "《反脆弱》",
"step": "knowledge_base_write",
"status": "success"
},
"queue": [
{
"title": "《穷查理宝典》",
"author": "彼得·考夫曼",
"topic": "决策科学"
}
],
"used_models": [
{
"date": "2026-03-24",
"book": "《上瘾》",
"author": "尼尔·埃亚尔",
"model": "上瘾模型(Hook Model)",
"category": "用户增长",
"source": "web_search",
"applied_count": 0,
"tags": ["thinking-pattern"]
}
]
}字段说明:
schema_version: 当前为 1,用于未来格式升级时的迁移判断last_attempted: 上次运行的状态快照,用于错误恢复queue: 用户预排的待读书籍队列(FIFO)used_models: 已处理的所有模型记录(追加式,不可删除)source: 标记选书来源(web_search | queue | user_specified)applied_count: 该模型被 AI 在后续对话中引用的次数(未来追踪用,初始为 0)tags: 分类标签数组(thinking-pattern | principle | concept)迁移指引:
如果你已有旧格式的 reading-history.json(只有 used_models 数组,无 schema_version),只需手动添加以下顶层字段:
{
"schema_version": 1,
"last_attempted": null,
"queue": [],
"used_models": [... 保留原有数据 ...]
}默认: breadth(每次运行处理一本新书,提取 1 个模型)
切换方式: 用户在对话中指定 depth_mode: depth 或说 "深度分析这本书"
depth 模式详细流程:
选中书籍: 《反脆弱》
│
├─ Round 1: 提取 "反脆弱三元组" → 写入 patterns/antifragility.md + reading-history
├─ Round 2: 提取 "杠铃策略" → 写入 patterns/barbell-strategy.md + reading-history
├─ Round 3: 提取 "林迪效应" → 写入 patterns/lindy-effect.md + reading-history
├─ Round 4: AI 自评 "无更多独立框架" → 停止
│
├─ 合并输出: 一份报告包含 3 个模型(精简 F/A/C/E + 🎯迁移 + 关联分析)
└─ 写入飞书: 每个模型一条记录三重退出条件(任一触发即停止):
禁止:
要求:
配置来源优先级:
HEARTBEAT-reading.mdFEISHU_APP_TOKEN, FEISHU_TABLE_IDNOTION_API_KEY, NOTION_DATABASE_ID用户上下文 (可选但强烈推荐):
USER.md知识库路径 (自动创建):
memory/knowledge-base/patterns/*.md (每个模型一个文件)memory/knowledge-base/concepts.mdVersion: 3.0.0 Last updated: 2026-03-28 Changes: Knowledge base restructure — single-file-per-model with YAML frontmatter (patterns/{id}.md), dedup via reading-history.json only (no longer reads thinking-patterns.md), FACET→KB field mapping table, KB_META extraction from mental-model-forge output, contradiction field added
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (references) in skills/cognitive-forge of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Cognitive Forge next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cognitive Forge this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Capture Conversationoutline/outline | 41k | — | ~474 | Automated safety check: Pass | Custom licence | |
| Project CairniBlinkQ/project-cairn | 235 | 2 repos | ~861 | Automated safety check: Pass | MIT | |
| LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything | 86k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Find And Citeoutline/outline | 41k | — | ~537 | Automated safety check: Pass | Custom licence | |
| Xhs Virtual Productchenjin-cmd/xhs-virtual-product | 727 | — | ~862 | Automated safety check: Pass | MIT |
outline/outline
Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.
iBlinkQ/project-cairn
Standardize how an AI-collaboration project turns work into reusable knowledge.
Egonex-AI/Understand-Anything
Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.
outline/outline
Answer questions from the Outline knowledge base with quotes and links to the source documents; use when the user asks what the team knows, documented, or decided about a topic.
chenjin-cmd/xhs-virtual-product
This skill helps plan, select, produce, and market Xiaohongshu (RED) virtual/digital products — templates, knowledge bases, test tools, study materials.
VectifyAI/OpenKB
A skill your agent uses when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an…
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
Dual-value learning system - extracts reusable mental models from books, writes individual pattern files (patterns/{id}.md) with YAML frontmatter for building compound thinking ability. Cognitive Forge is an agent skill from LeoYeAI/openclaw-master-skills.md) with YAML frontmatter for building compound thinking ability.
Cognitive Forge fits situations like: tasks that involve Knowledge bases.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a claude-code`. Or copy the skill folder (skills/cognitive-forge in LeoYeAI/openclaw-master-skills) into .claude/skills/cognitive-forge in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a codex`. Or copy the skill folder (skills/cognitive-forge in LeoYeAI/openclaw-master-skills) into .agents/skills/cognitive-forge in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cognitive-forge, .gemini/skills/cognitive-forge, .github/skills/cognitive-forge and .opencode/skills/cognitive-forge in your project.
Going by SKILL.md and its folder, Cognitive Forge needs credentials named NOTION_API_KEY and FEISHU_APP_TOKEN. Our summary lists: A credential in FEISHU_APP_TOKEN; A credential in NOTION_API_KEY.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Cognitive Forge is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cognitive Forge: Capture Conversation (outline/outline, 41k stars), Project Cairn (iBlinkQ/project-cairn, 235 stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars) and Find And Cite (outline/outline, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.