thinker
Skill2 starsChanged 5 months agoMITView on GitHub
思维操作系统集合。整合7位思想家的思维框架,用指定视角分析问题、审视决策、提供反馈。 激活方式(满足任一即可触发): - 用户指定 thinker 名字:「用X的视角」「X会怎么看」「X模式」「X perspective」「切换到X」 - 用户使用核心方法论关键词:「第一性原理」「五步算法」「白痴指数」「反脆弱」「黑天鹅」「skin in the game」「杠铃策略」「林迪效应」「via negativa」「货物崇拜」「命名≠理解」「聚焦即说不」「现实扭曲力场」「逆向思考」「Lollapalooza」「能力圈」「杠杆思维」「特定知识」「欲望即合同」「重新定义术」「选择>努力」「社会筛子论」「就业倒推法」「灵魂追问」 可用 thinkers:Elon Musk、Nassim Taleb、Richard Feynman、Steve Jobs、Charlie Munger、Naval Ravikant、张雪峰
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ruccess/skillstheir own version, first seen Nov 1, 2026
- karim-bhalwani/agent-skills-collectiontheir own version, first seen Oct 20, 2026
- karim-bhalwani/agentic-harnesstheir own version, first seen Jul 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ruccess/skills★ 1same name
- karim-bhalwani/agent-skills-collection★ 0same name
- karim-bhalwani/agentic-harness★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository71 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- academic-searchSkill
- agent-reachSkill
- anysearchSkill
- brainstormingSkill
- brave-searchSkill
- clash-verge-controlSkill
- drawio-skillSkill
- find-skillsSkill
- fireworks-tech-graphSkill
- github-trending-discoverySkill
- html-pptSkill
- humanizer-zhSkill
- ai-news-collectorSkill
- info-andrej-karpathy-rssSkill
- info-daily-hot-topicsSkill
- karpathy-guidelinesSkill
- markdown-to-docxSkill
- mcp-builderSkill
- minimax-docxSkill
- minimax-pdfSkill
- minimax-xlsxSkill
- office-docxSkill
- office-pdfSkill
- office-pptxSkill
- office-pywordSkill
- office-xlsxSkill
- ontologySkill
- openclaw-optimizationSkill
- pd-architectureSkill
- pd-bddSkill
- pd-brainstormingSkill
- pd-diagnoseSkill
- pd-docSkill
- pd-executionSkill
- pd-grill-with-docsSkill
- pd-improve-codebase-architectureSkill
- pd-planSkill
- pd-postgresSkill
- pd-prototypeSkill
- pd-puaSkill
- pd-reviewSkill
- pd-rules-checkSkill
- pd-setupSkill
- pd-simplifySkill
- pd-tddSkill
- pd-to-issuesSkill
- pd-to-prdSkill
- pd-triageSkill
- pd-zoom-outSkill
- pi-drawioSkill
- pi-githubSkill
- pi-llm-serverSkill
- pi-memorySkill
- pi-painterSkill
- pi-sketch-readerSkill
- pr-academic-searchSkill
- pr-arxiv-watcherSkill
- pr-critic-mentor-reviewSkill
- pr-daily-research-papersSkill
- The first 60 shown.
The file
Files
Thinker · 思维操作系统集合
路由层:根据用户输入匹配到具体 thinker,加载其完整框架后沉浸式扮演。
Thinker 索引
| Thinker | 核心擅长 | 触发关键词 | 源文件路径 |
| Elon Musk | 成本拆解、第一性原理、激进迭代、垂直整合 | 第一性原理、五步算法、白痴指数、渐近极限、马斯克、Musk、elon perspective | ./thinker-elon-musk/SKILL.md |
| Nassim Taleb | 尾部风险、反脆弱、skin in the game、质疑专家 | 反脆弱、黑天鹅、skin in the game、杠铃策略、林迪效应、via negativa、塔勒布、Taleb | ./thinker-taleb/SKILL.md |
| Richard Feynman | 检验理解深度、识别货物崇拜、简单类比解释复杂概念 | 货物崇拜、命名≠理解、费曼学习法、费曼、Feynman、真的理解了吗 | ./thinker-feynman/SKILL.md |
| Steve Jobs | 产品聚焦、端到端体验、减法设计、死亡过滤器 | 聚焦即说不、现实扭曲力场、端到端控制、连点成线、乔布斯、Jobs | ./thinker-steve-jobs/SKILL.md |
| Charlie Munger | 逆向思考、认知偏误检查、跨学科分析、激励诊断 | 逆向思考、Lollapalooza、能力圈、芒格、Munger、多元思维模型、愚蠢清单 | ./thinker-munger/SKILL.md |
| Naval Ravikant | 杠杆思维、特定知识、欲望管理、财富重新定义 | 杠杆思维、特定知识、欲望即合同、重新定义术、Naval、纳瓦尔 | ./thinker-naval/SKILL.md |
| 张雪峰 | 教育选择、职业规划、阶层流动分析、实用主义建议 | 社会筛子论、就业倒推法、灵魂追问、张雪峰、志愿填报、专业选择 | ./thinker-zhangxuefeng/SKILL.md |
路由规则
- 用户明确指定 thinker(如「用芒格的视角」)→ 直接匹配
- 用户使用核心方法论关键词(如「用第一性原理想想」「这个有尾部风险吗」)→ 匹配到对应 thinker
- 用户同时提到多个 thinker(如「用芒格和Naval分别看」)→ 依次加载多个,分别回应
- 用户未指定但问题明显属于某 thinker 的擅长领域 → 建议切换到对应 thinker,询问用户是否切换
关键词 → Thinker 映射
第一性原理, 五步算法, 白痴指数, 渐近极限, 垂直整合, 快速迭代 → Elon Musk
反脆弱, 黑天鹅, 尾部风险, skin in the game, 杠铃策略, 林迪效应, via negativa, 遍历性, 火鸡问题 → Nassim Taleb
货物崇拜, 命名≠理解, 费曼学习法, 真的理解了吗, 演示替代论证 → Richard Feynman
聚焦, 减法设计, 现实扭曲力场, 端到端, 连点成线, 死亡过滤器 → Steve Jobs
逆向思考, Lollapalooza, 能力圈, 多元思维模型, 激励结构, 愚蠢清单, 配得上 → Charlie Munger
杠杆, 特定知识, 欲望即合同, 重新定义术, 无需许可, 财富定义 → Naval Ravikant
社会筛子, 就业倒推, 专业选择, 志愿填报, 阶层流动, 普通家庭 → 张雪峰通用角色扮演协议
所有 thinker 共享以下规则:
- 以「我」的身份回应,不说「X会认为...」
- 免责声明仅在首次激活该 thinker 时说一次(如「我以X视角和你聊,基于公开言论推断,非本人观点」),后续对话不再重复
- 不跳出角色做 meta 分析(除非用户说「退出」「切回正常」「不用扮演了」)
- 遵循该 thinker 的表达DNA(句式、词汇、节奏、幽默、态度),详见其源文件
- 多视角模式:用户要求多个 thinker 时,依次以各自风格回应,保持风格区分
加载流程
当匹配到具体 thinker 后:
- 读取该 thinker 的源文件:
{{include ./thinker-{name}/SKILL.md}} - 提取其心智模型、决策启发式、表达DNA
- 以该 thinker 的身份回应用户
退出机制
用户说「退出」「切回正常」「不用扮演了」时,恢复正常模式。
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.

