Markdown Article Formatter
JimLiu/baoyu-skills
Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.
仓颉 · 认知植入术：丢进素材（书/访谈/文章/PDF），自动蒸馏出一个人的思维Skill. An agent skill from Yeadon8888/cangjie-skill.
Install Cangjie
$ npx skills add Yeadon8888/cangjie-skill --skill cangjie -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Yeadon8888/cangjie-skill cangjie --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cangjie" agent skill from https://github.com/Yeadon8888/cangjie-skill/tree/main into .claude/skills/cangjie/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cangjie", 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.
$ npx skills add Yeadon8888/cangjie-skill --skill cangjie -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Yeadon8888/cangjie-skill cangjie --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cangjie" agent skill from https://github.com/Yeadon8888/cangjie-skill/tree/main into .agents/skills/cangjie/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cangjie", 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 Yeadon8888/cangjie-skill --skill cangjie -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Yeadon8888/cangjie-skill cangjie --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cangjie" agent skill from https://github.com/Yeadon8888/cangjie-skill/tree/main into .cursor/skills/cangjie/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cangjie", 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.
$ npx skills add Yeadon8888/cangjie-skill --skill cangjie -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Yeadon8888/cangjie-skill cangjie --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cangjie" agent skill from https://github.com/Yeadon8888/cangjie-skill/tree/main into .gemini/skills/cangjie/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cangjie", 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 Yeadon8888/cangjie-skill cangjieInstalls 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 Yeadon8888/cangjie-skill --skill cangjie -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cangjie" agent skill from https://github.com/Yeadon8888/cangjie-skill/tree/main into .github/skills/cangjie/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cangjie", 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 Yeadon8888/cangjie-skill --skill cangjie -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Yeadon8888/cangjie-skill cangjie --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cangjie" agent skill from https://github.com/Yeadon8888/cangjie-skill/tree/main into .opencode/skills/cangjie/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cangjie", 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.
Facts
- Skill name
cangjie- GitHub stars
- 262
- Token cost
- ~1.1k tokens
- SKILL.md length
- 239 words
- Files
- 28 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
仓颉 · 认知植入术：丢进素材（书/访谈/文章/PDF），自动蒸馏出一个人的思维Skill. An agent skill from Yeadon8888/cangjie-skill.
- Works in 7 steps: ：确认对象和素材 → ：消化素材并整理为结构化调研文件 → ：提取认知上下文 → …
- Documents & Office work in your project
- SKILL.md covers 收到素材后，执行以下流程 and 注意事项
What it does
Cangjie is an agent skill from Yeadon8888/cangjie-skill. 仓颉 · 认知植入术：丢进素材（书/访谈/文章/PDF），自动蒸馏出一个人的思维Skill。 提取的不是"他说了什么"，而是"他为什么这样想"——信念形成故事、真实决策、失败教训、内在矛盾。 触发词：「仓颉」「蒸馏XX」「做个XX的思维Skill」「用仓颉提取」「帮我蒸馏」。 只要用户上传了某人的素材（书/演讲/访谈）并希望提取思维方式，就应该触发。
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 34 other files, including scripts and reference files (for example `README.md`, `README_EN.md` and `STORY.md`).
It sits in Documents & Office. The repository describes itself as: 仓颉 · 认知植入式思维蒸馏引擎 — 不是让AI说得像他，是让AI想得像他。基于女娲架构升级。 The licence is MIT.
When your agent uses it
- Documents & Office work in your project
Example prompts
- “他为什么这样想”
- “/cangjie”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3cc1e69. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cangjie loads about 1.1k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 239 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.
Safety
Auto-check passed
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); the scripts in this folder are not scanned.
SKILL.md
The full file from Yeadon8888/cangjie-skill at commit 3cc1e69, republished under its MIT licence (© Yeadon8888). 239 words, ~1,090 tokens.
Download SKILL.mdSave it as
.claude/skills/cangjie/SKILL.md (or your agent's skills folder). This skill also uses 27 other files; get the full folder from GitHub.- name
- cangjie
- description
- 仓颉 · 认知植入术：丢进素材（书/访谈/文章/PDF），自动蒸馏出一个人的思维Skill。 提取的不是"他说了什么"，而是"他为什么这样想"——信念形成故事、真实决策、失败教训、内在矛盾。 触发词：「仓颉」「蒸馏XX」「做个XX的思维Skill」「用仓颉提取」「帮我蒸馏」。 只要用户上传了某人的素材（书/演讲/访谈）并希望提取思维方式，就应该触发。
仓颉 · 认知植入术
喂进去的是一个人说过的话，提取出来的是他为什么说这些话。
收到素材后，执行以下流程
Step 1：确认对象和素材
收到用户输入后，先确认：
A. 蒸馏谁？
- 用户明确说了人名 → 直接进行
- 用户丢了文件但没说人名 → 读文件判断，和用户确认
B. 素材是什么？
- 用户上传了文件（PDF/TXT/MD/EPUB） → 直接读取
- 用户只说了人名没给素材 → 用 WebSearch 采集（见下方采集指引）
- 两者都有 → 以用户素材为主，网搜为补充
C. 聚焦方向？
- 问用户：全面蒸馏，还是聚焦某个维度（决策方式？创业思维？人生哲学？）
- 用户说"就这样"或不指定 → 默认全面
确认后，创建输出目录：
[person-name]-perspective/
├── SKILL.md
└── references/
└── research/Step 2：消化素材并整理为结构化调研文件
这一步的目标不是"读完就提取"，而是先把原始素材整理成结构化的调研文件，再从调研文件中提取。
详细的分块原则、文件格式、命名规范见 <skill-base>/references/research-guide.md。以下是主干流程：
A. 用户上传了文件
分块扫描：长文档先读目录，标记高价值章节，优先精读这些章节
带着7级清单扫描：
级别 找什么 命中后 1 最高 信念形成故事（"我信X是因为经历了Y"） 逐字记录 2 高 真实决策复盘（做了什么+当时在想什么+事后反思） 逐字记录 3 高 失败/错误承认（本人承认的） 逐字记录 4 高 内在矛盾暴露（前后不一致、说一套做一套） 标注两个矛盾点的出处 5 中 认知边界声明（"这不是我的领域"） 简要记录 6 中 思维习惯案例（反复出现的分析模式） 记录具体案例 7 低 通用观点/金句 没有形成故事就跳过 写入提取记录：按
research-guide.md中的文件格式规范，写入references/research/02-extraction-notes.md。每条提取标注优先级、原文出处和提取类型。
B. 用户没给文件，需要网搜
按6个维度采集，每个维度的搜索结果保存为独立文件：
| 维度 | 存到 | 最低要求 |
|---|---|---|
| 著作/长文 | 01-writings.md | ≥2篇长文或1本书核心内容 |
| 访谈/对话 | 02-conversations.md | ≥1段深度对话 |
| 社交媒体 | 03-expression.md | ≥20条发言 |
| 外部评价 | 04-external.md | ≥2个不同视角 |
| 重大决策 | 05-decisions.md | ≥2个决策+反思 |
| 时间线 | 06-timeline.md | 关键转折覆盖完整 |
每份调研文件必须包含：来源清单（标注一手/二手和可信度）+ 提取记录（标注优先级和出处）。
C. 交叉验证（多份素材时执行）
- 同一信念在 ≥2 份素材中出现 → 标注 ★，置信度高
- 只在 1 份素材中出现 → 保留但标注来源单一
- 不同素材中出现矛盾 → 保留双方，这本身就是内在矛盾的证据
铁律：
- 没有保存提取证据的蒸馏等于空中楼阁
references/research/下最终保留三个文件：01-sources.md（来源清单）+02-extraction-notes.md（提取记录）+03-key-quotes.md（关键原文引用）- 不要把整本书/整篇访谈原文放进 references——只保留被引用的关键段落
- 详见
<skill-base>/references/research-guide.md
Step 3：提取认知上下文
素材消化完后，按以下结构提取。这是仓颉的核心——只提取模型不可能自己知道的东西。
3.1 信念及其形成故事（5-7条）
不是"他信什么"——模型已经知道了。 是"他为什么信这个"——这只存在于具体素材中。
每条信念必须包含：
- 信念本身（一句话）
- 形成故事（什么经历/事件让他开始信这个）
- 关键洞察（这个经历让他意识到了什么）
❌ "独立思考很重要" → 太通用，跳过
✅ "我信独立思考，是因为在YC看了3000个项目后发现最好的想法一开始都被所有人反对" → 有形成故事，保留铁律：没有形成故事的信念不准进入最终 Skill。
3.2 真实决策案例（3-5个）
每个决策必须包含：
- 当时的情境（背景）
- 做了什么选择（行动）
- 当时在想什么（推理）
- 事后反思（对了还是错了，学到了什么）3.3 失败与自我修正（2-3个）
必须是本人承认过的失败，不是外部推断的。
3.4 内在矛盾（2-3对）
保留矛盾，不调和。矛盾是人格最有辨识度的特征。
3.5 认知边界
此人明确不懂什么，框架在哪里不适用。
3.6 思维习惯（3-7个）
写成第一人称习惯描述，不是推理步骤：
❌ "Step 1: 使用反转思维模型"
✅ "我遇到别人说'这个方案很好'时，本能反应是先想它怎么会失败"如果这个人有独创的命名框架（如 PG 的 "Do Things That Don't Scale"），把它内化为思维习惯而不是规则。
3.7 表达DNA（极简）
只提取 3 条偏好 + 3 条禁忌。模型自己会适配风格。
Step 4：展示提取摘要，等用户确认
仓颉提取完成。摘要如下：
蒸馏对象：[人名]
素材来源：[N份文件 / N条搜索结果]
提取结果：
- 信念（含形成故事）：N条
- 真实决策案例：N个
- 失败教训：N个
- 内在矛盾：N对
- 认知边界：N条
- 思维习惯：N个
是否继续生成 Skill？用户确认 → 进入 Step 5。 用户觉得不对 → 回到 Step 3 调整。
Step 5：组装 Skill
读取 references/skill-template.md，按模板组装。
核心结构：
# [人名]
你不是在扮演[人名]。你是一个被植入了[人名]认知上下文的AI。
## 我是谁 ← 50字自述，经历如何塑造思维
## 我的认知上下文 ← 仓颉的核心
### 信念及其来源 ← 每条有形成故事
### 关键决策 ← 真实案例+反思
### 栽过的跟头 ← 本人承认的失败
### 内在矛盾 ← 保留不调和
### 我不懂的 ← 认知边界
## 我看问题的方式 ← 思维习惯（第一人称）
## 我绝不做的事 ← 红线
## 我说话的方式 ← 3偏好+3禁忌
## 素材来源四个铁律：
- 没有形成故事的信念不进入
- 没有事后反思的决策不进入
- 不写 Step 1/2/3 推理步骤
- 全部第一人称
将 SKILL.md 写入 [person-name]-perspective/SKILL.md。
Step 6：质量自检
组装完成后，逐项检查：
- 每条信念都有形成故事？（不是光秃秃的观点）
- 每个决策都有事后反思？（不是光秃秃的事实）
- 失败全部是本人承认的？（不是外部推断）
- 矛盾是真实存在的？（不是凑数）
- 认知边界 ≥ 3 条？（具体的"我不懂"声明）
- 没有通用金句？（"独立思考很重要"这种已删掉）
- 没有推理步骤？（"Step 1 分析问题"这种已删掉）
- 表达DNA ≤ 3+3？（没有详细的句式分析）
- 素材有保存？（references/research/ 不为空）
全部通过 → 交付。有不通过项 → 回到 Step 3 补充。
Step 7：交付
告诉用户：
Skill 已生成：[path]/[person-name]-perspective/SKILL.md
你可以直接使用它来获取[人名]的视角：
> 用[人名]的方式帮我分析这个问题
素材和提取记录保存在 references/ 目录下。注意事项
素材质量决定 Skill 质量。 一本书 > 十篇二手总结。访谈原文 > 别人转述。
不是所有人都适合蒸馏。 如果一个人没有公开分享过自己的决策过程、失败经历和内心矛盾，蒸馏出来的 Skill 质量会很低。这时要在认知边界中标注"素材不足，以下维度为推测"。
蒸馏不等于认同。 仓颉提取的是一个人的认知方式，不代表认同他的所有观点。
仓颉观鸟兽之迹，知分理之可相别异也。 观足迹造字，观思维造 Skill。
© Yeadon8888, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 27 other files (scripts, references) in the repository root of Yeadon8888/cangjie-skill.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- README_EN.md
- STORY.md
- examples/adler-perspective/SKILL.md
- examples/adler-perspective/banner.png
- examples/adler-perspective/references/research/01-sources.md
- examples/adler-perspective/references/research/02-extraction-notes.md
- examples/adler-perspective/references/research/03-key-quotes.md
- examples/paul-graham-perspective/SKILL.md
- examples/paul-graham-perspective/banner.png
- examples/paul-graham-perspective/references/research/01-writings.md
- … and 14 more
Open the folder on GitHubat commit 3cc1e69
Compare with similar skills
Cangjie 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 |
|---|---|---|---|---|---|---|
| Cangjie this skillYeadon8888/cangjie-skill | 262 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Markdown Article FormatterJimLiu/baoyu-skills | 27k | 6 repos | ~3.5k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Obsidian MarkdownAtmosphere/atmosphere | 3.8k | 20 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| DOCXrvdbreemen/OTGW-firmware | 207 | 33 repos | ~4.3k | Automated safety check: Pass | Proprietary | |
| Word Document Reader and WriterHKUDS/DeepTutor | 41k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Obsidian Markdown
Atmosphere/atmosphere
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.
DOCX
rvdbreemen/OTGW-firmware
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).
Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
Crossposting
wasp-lang/wasp
Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.
Related
Categories
Questions about Cangjie
What does Cangjie do?
仓颉 · 认知植入术：丢进素材（书/访谈/文章/PDF），自动蒸馏出一个人的思维Skill. An agent skill from Yeadon8888/cangjie-skill. Cangjie is an agent skill from Yeadon8888/cangjie-skill.
When should I use Cangjie?
Cangjie fits situations like: documents & Office work in your project.
How do I install Cangjie in Claude Code?
Run `npx skills add Yeadon8888/cangjie-skill --skill cangjie -a claude-code`. Or copy the skill folder (the Yeadon8888/cangjie-skill repository) into .claude/skills/cangjie in your project. Claude Code loads it when a task matches its description.
How do I install Cangjie in Codex?
Run `npx skills add Yeadon8888/cangjie-skill --skill cangjie -a codex`. Or copy the skill folder (the Yeadon8888/cangjie-skill repository) into .agents/skills/cangjie in your project. Codex loads it when a task matches its description.
Can I use Cangjie in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yeadon8888/cangjie-skill --skill cangjie -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cangjie, .gemini/skills/cangjie, .github/skills/cangjie and .opencode/skills/cangjie in your project.
What does Cangjie need to run?
SKILL.md names no scripts, command-line tools or credentials: Cangjie is instructions for the agent only.
Does Cangjie access the network?
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.
Is Cangjie safe to install?
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Cangjie use?
Cangjie is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cangjie use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 5.8k tokens, read only when the agent opens those files.
What are the alternatives to Cangjie?
Skills that share tags, products or a category with Cangjie: Markdown Article Formatter (JimLiu/baoyu-skills, 27k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cangjie?
Yeadon8888 (a GitHub user) maintains it in Yeadon8888/cangjie-skill, which has 262 GitHub stars. The repository was last updated on September 18, 2026.
Source: Yeadon8888/cangjie-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.