cognitive-forge
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.
Best for knowledge workersWorks with GitHubLow risk
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·Extracts mental models from books
- ·Writes individual pattern files
- ·F.A.C.E.T. analysis for learning
- ·Breadth/depth modes
- ·Configurable topic mapping
- ·Multi-source book selection
Use Cases
- →A developer reading a book on system design and wanting to extract reusable mental models for future projects
- →A team building a shared knowledge base of cognitive patterns from multiple books
- →A learner using F.A.C.E.T. analysis to deepen understanding of a complex topic
Best for
- ✓knowledge workers
- ✓lifelong learners
- ✓teams curating mental models
Not ideal for
- !quick one-off note-taking
- !non-book sources
- !users without book-scout and mental-model-forge
FAQs
name
cognitive-forge
description
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.
dependencies:["book-scout","mental-model-forge"]
permissions:{"filesystem":{"read":["USER.md","memory/reading-history.json","HEARTBEAT-reading.md"],"write":["memory/knowledge-base/patterns/*.md","memory/knowledge-base/concepts.md","memory/reading-history.json"]},"env":["FEISHU_APP_TOKEN","FEISHU_TABLE_ID","NOTION_API_KEY","NOTION_DATABASE_ID"]}
config:{"reads":["USER.md","memory/reading-history.json","HEARTBEAT-reading.md"],"writes":["memory/knowledge-base/patterns/*.md","memory/knowledge-base/concepts.md","memory/reading-history.json"],"env":["FEISHU_APP_TOKEN","FEISHU_TABLE_ID","NOTION_API_KEY","NOTION_DATABASE_ID"]}
Cognitive Forge (认知锻造)
One run, dual value — 每次运行同时产出两个价值：
- 用户获得 F.A.C.E.T. 深度分析，提取可立即应用的思维模型
- AI 获得 永久写入
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。
Path Convention
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 |
Routing (路由分支)
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：
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill cognitive-forgeSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.