LLM Wiki
lewislulu/llm-wiki-skill
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…
Applies Naval Ravikant's ideas on identity: dropping labels to see reality clearly, and using a publicly declared self-image in place of willpower.
SKILL.md written in Chinese; this summary is our English description.
Install Identity Work
$ npx skills add kangarooking/cangjie-skill --skill identity-work -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kangarooking/cangjie-skill identity-work --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/kangarooking/cangjie-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/books/naval-almanack-skill/identity-work .claude/skills/identity-work && 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 "identity-work" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-work into .claude/skills/identity-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "identity-work", 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/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-workType 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 kangarooking/cangjie-skill --skill identity-work -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kangarooking/cangjie-skill identity-work --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/books/naval-almanack-skill/identity-work .agents/skills/identity-work && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "identity-work" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-work into .agents/skills/identity-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "identity-work", 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 kangarooking/cangjie-skill --skill identity-work -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kangarooking/cangjie-skill identity-work --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/books/naval-almanack-skill/identity-work .cursor/skills/identity-work && 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 "identity-work" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-work into .cursor/skills/identity-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "identity-work", 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/kangarooking/cangjie-skill.git --path books/naval-almanack-skill/identity-work--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 kangarooking/cangjie-skill --skill identity-work -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kangarooking/cangjie-skill identity-work --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/books/naval-almanack-skill/identity-work .gemini/skills/identity-work && 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 "identity-work" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-work into .gemini/skills/identity-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "identity-work", 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 kangarooking/cangjie-skill identity-workInstalls 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 kangarooking/cangjie-skill --skill identity-work -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/books/naval-almanack-skill/identity-work .github/skills/identity-work && 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 "identity-work" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-work into .github/skills/identity-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "identity-work", 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 kangarooking/cangjie-skill --skill identity-work -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kangarooking/cangjie-skill identity-work --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/books/naval-almanack-skill/identity-work .opencode/skills/identity-work && 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 "identity-work" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/identity-work into .opencode/skills/identity-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "identity-work", 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
identity-work- GitHub stars
- 11k
- Token cost
- ~636 tokens
- SKILL.md length
- 146 words
- Files
- 3
- Skills in repo
- 22
- Repo updated
- First seen
- Licence
- MIT
At a glance
Applies Naval Ravikant's ideas on identity: dropping labels to see reality clearly, and using a publicly declared self-image in place of willpower.
- Works in 4 steps: 立场先行：「我发现我总在为某个标签辩护」 → 无法面对现实：「明明有问题却一直拖」 → 改变失败：「我下定决心了还是做不到」 → …
- Noticing you keep defending a stance or label instead of looking at the facts
- SKILL.md covers R — 原文 (Reading), I — 方法论骨架 (Interpretation), A1 — 书中的应用 (Past Application) and A2 — 触发场景 (Future Trigger) ★, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This Chinese-language skill is distilled from the Almanack of Naval Ravikant and applies when someone is defending a position, cannot see reality clearly, or keeps resolving to change without success. It treats identity as both a trap and a lever. Labels lock perception, so letting them go, and treating painful moments as moments of truth, helps you see clearly, while a new self-image can replace willpower when changing behavior.
It runs four steps: audit your beliefs by listing three that arrive as a bundle and marking which were never tested independently; find the way into the truth by asking what reality you are avoiding and admitting one item to a trusted person; declare the new identity and tell at least 3 people; then act in line with it every day for 30 days. It tells the agent to stop and suggest professional counseling for deep trauma and says to solve concrete outside problems first. Related skills named are acceptance, self-liberation and judgment-training.
When your agent uses it
- Noticing you keep defending a stance or label instead of looking at the facts
- Resolutions keep failing and willpower is not working
- Reflecting on self-deception or a reality you have been avoiding
Example prompts
- “I keep defending my startup's strategy even though the numbers say otherwise. Walk me through an identity audit.”
- “I decided to quit late-night snacking but fail every time. How can a new self-image help?”
- “Am I deceiving myself about this project? Help me find what I am avoiding.”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 立场先行：「我发现我总在为某个标签辩护」
- 无法面对现实：「明明有问题却一直拖」
- 改变失败：「我下定决心了还是做不到」
- 自我欺骗：「我总是给自己找借口」
What it can do on your machine
Read from SKILL.md and the folder at commit a28de55. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Identity Work loads about 636 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 146 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from kangarooking/cangjie-skill at commit a28de55, republished under its MIT licence (© kangarooking). 146 words, ~636 tokens.
Download SKILL.mdSave it as
.claude/skills/identity-work/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- identity-work
- description
- 当用户发现自己在为立场辩护、看不清现实、或反复立志却改变不了自己时调用。 核心理念: 身份是认知牢笼也是行为杠杆——放下身份才能看清真相(痛苦=真相时刻), 更新自我形象才能替代自律(对外承诺)。 不适用于: 需要专业心理咨询的深层创伤。 Triggers: 立场/身份/自我/看不清现实/改变不了自己/自律失败/identity/self-image
- source_book
- 《纳瓦尔宝典：财富与幸福指南》 纳瓦尔·拉维坎特
- source_chapter
- 第一章·财富 / 第二节 培养判断力 / 如何清晰地思考 + 第二章·幸福 / 选择去塑造你自己
- tags
- identity, self-awareness, change, reality
身份工作：看清现实与重塑自我
R — 原文 (Reading)
痛苦时刻的一个定义是“你看清事物本来面貌的时刻。”……好消息是痛苦时刻……是真相时刻。……我尽量不要有太多预先决定。我认为创造身份和标签会锁死你的认知，让你无法看清真相。……为了在没有自律的情况下自我提升，请更新你的自我形象。
— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》
I — 方法论骨架 (Interpretation)
「身份」是一把双刃剑，两个方向都要用： 认知侧——清空身份看清现实：身份和标签会锁死认知，让人为立场辩护而非看事实； 痛苦时刻是「愿望与现实冲突无法再回避」的真相时刻，是看清现实的最佳入口； 操作：公开认错（防自欺）、对成捆一致的信念高度怀疑、从基本原则重估一切。 行为侧——用自我形象替代自律：靠意志力对抗旧习惯不可持续，真正的杠杆是重塑「我是谁」—— 先对外宣布新身份（「我戒烟了」），利用承诺一致性让新自我形象约束行为； 「自律是通向新自我形象的桥梁」，最终「你就是它」。
A1 — 书中的应用 (Past Application)
案例 1: 公开承认失败
- 问题: 生意没做好时容易自欺
- 方法论的使用: 在联合创始人和同事面前公开承认
- 结论: 「如果我没有对别人隐瞒，我就不会欺骗自己」
- 结果: 用外部承诺锁死自欺通道
案例 2: 向所有人宣布戒烟
- 问题: 靠意志力戒烟失败
- 方法论的使用: 「对每一个你认识的人说：我戒烟了。我戒了。我向你保证。」
- 结论: 对外承诺=用身份约束行为
- 结果: 「那就是你需要去做的全部」
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 立场先行：「我发现我总在为某个标签辩护」
- 无法面对现实：「明明有问题却一直拖」
- 改变失败：「我下定决心了还是做不到」
- 自我欺骗：「我总是给自己找借口」
语言信号
- "我为我的立场辩护/看不清现实"
- "我改变不了自己/自律失败"
- "我是不是在自欺欺人"
- "identity / why can't I change / self-deception"
与相邻 skill 的区分
- 与
acceptance的区别: 身份工作拆掉「不肯面对现实的自我」；接受是拆掉之后的落地动作 - 与
self-liberation的区别: 本 skill 改身份；解放 skill 卸外部期望
E — 可执行步骤 (Execution)
做信念审计
- 完成标准: 列出 3 条「成捆一致」的信念，标注哪些未经独立检验、哪些是为标签辩护
找真相入口
- 完成标准: 问「我在回避什么现实？最痛苦的地方在提醒我什么？」，并把其中一条向可信的人公开承认
- 判停条件: 若涉及深层创伤，停止自助流程并建议专业咨询
声明新身份
- 完成标准: 把想改变的习惯写成身份宣言（「我是……的人」），向至少 3 人宣布
用行为回填身份
- 完成标准: 接下来 30 天每天做一个与新身份一致的小动作，把「我尝试」改成「我就是」
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 深层创伤/人格层面的问题（需专业咨询，不能靠身份宣言）
- 用户需要先解决外部实际问题时（先行动，再调身份）
作者在书中警告的失败模式
- 身份锁死认知: 「创造身份和标签会锁死你的认知，让你无法看清真相」
- 用「我要」拖延: 「当你说'我要做这个'和'我要做那个'的时候，你其实是在拖延」
作者的盲点 / 时代局限
- 「放下身份」对少数群体/弱势身份可能意味着放弃重要的群体支持
- 身份重塑并非对所有人都同样可行（社会结构约束）
容易混淆的邻近方法论
acceptance: 接受需要先放下自我，身份工作是那个「放下」的动作
相关 skills (阶段 3 定稿)
- composes-with:
acceptance、self-liberation、judgment-training
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v16)
- 测试通过率: 见 test-results.md
- 蒸馏时间: 2026-08-01
© kangarooking, 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 2 other files in books/naval-almanack-skill/identity-work of kangarooking/cangjie-skill.
- SKILL.md
- test-prompts.json
- test-results.md
Open the folder on GitHubat commit a28de55
Compare with similar skills
Identity Work 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 |
|---|---|---|---|---|---|---|
| Identity Work this skillkangarooking/cangjie-skill | 11k | — | ~636 | Automated safety check: Pass | MIT | |
| LLM Wikilewislulu/llm-wiki-skill | 655 | — | ~3.7k | Automated safety check: Pass | None | |
| Self Skill Creatornotdog1998/yourself-skill | 3.4k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Morning Journal and Planningdavidhariri/life-system | 845 | — | ~1.7k | Automated safety check: Notes | None | |
| Munger Perspectivealchaincyf/munger-skill | 378 | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Daily Notes Workflowballred/obsidian-claude-pkm | 1.9k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Self Skill Creator
notdog1998/yourself-skill
Builds a personal self skill from your chat logs, diaries and photos, then lets you extend or correct it, working in English or Chinese.
Morning Journal and Planning
davidhariri/life-system
Reviews yesterday's journal, checks today's to-dos against your inbox and active decisions, and asks pointed questions to keep daily actions aligned with your annual goals.
Munger Perspective
alchaincyf/munger-skill
查理·芒格的思维框架与表达方式。基于《穷查理宝典》、伯克希尔/Daily Journal股东会、 USC/哈佛演讲、访谈记录、外部批评等50+来源的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。
Daily Notes Workflow
ballred/obsidian-claude-pkm
Creates today's daily note in an Obsidian vault and guides morning, midday and evening routines for planning, task review and reflection.
Daily Journal
huytieu/COG-second-brain
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.
More from kangarooking/cangjie-skill
All 22 skills in this repoBook to Skills Distiller
kangarooking/cangjie-skill
Distills a book, video transcript, podcast, course or interview into a set of atomic, executable agent skills through a staged, verified pipeline.
Naval Almanack Source Router
kangarooking/cangjie-skill
Front door to a compact skill pack based on the Chinese edition of the Naval Almanack book, routing wealth, happiness and decision questions to the right reference card.
Almanack of Naval Ravikant Guide
kangarooking/cangjie-skill
Answers questions on wealth, decisions, happiness and life philosophy using capability notes distilled from The Almanack of Naval Ravikant, routed by intent.
Change, Accept or Leave Framework
kangarooking/cangjie-skill
Helps someone stuck ruminating over an unchangeable situation decide whether to change it, accept it, or leave it, drawn from a chapter of Navalism-style writing.
Major Decision Heuristics
kangarooking/cangjie-skill
Helps with big life and career choices you cannot settle, such as a new job, a move or a partnership, using three rules drawn from the Naval Almanack.
Status Games and Inner Scorecard
kangarooking/cangjie-skill
Helps you work out whether a situation is a zero-sum status game, a positive-sum wealth game or a single-player game, using an inner scorecard and an envy test drawn from Naval Ravikant's ideas.
Related
Categories
Questions about Identity Work
What does Identity Work do?
Applies Naval Ravikant's ideas on identity: dropping labels to see reality clearly, and using a publicly declared self-image in place of willpower. This Chinese-language skill is distilled from the Almanack of Naval Ravikant and applies when someone is defending a position, cannot see reality clearly, or keeps resolving to change without success. It treats identity as both a trap and a lever.
When should I use Identity Work?
Identity Work fits situations like: noticing you keep defending a stance or label instead of looking at the facts; resolutions keep failing and willpower is not working; reflecting on self-deception or a reality you have been avoiding.
How do I install Identity Work in Claude Code?
Run `npx skills add kangarooking/cangjie-skill --skill identity-work -a claude-code`. Or copy the skill folder (books/naval-almanack-skill/identity-work in kangarooking/cangjie-skill) into .claude/skills/identity-work in your project. Claude Code loads it when a task matches its description.
How do I install Identity Work in Codex?
Run `npx skills add kangarooking/cangjie-skill --skill identity-work -a codex`. Or copy the skill folder (books/naval-almanack-skill/identity-work in kangarooking/cangjie-skill) into .agents/skills/identity-work in your project. Codex loads it when a task matches its description.
Can I use Identity Work 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 kangarooking/cangjie-skill --skill identity-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/identity-work, .gemini/skills/identity-work, .github/skills/identity-work and .opencode/skills/identity-work in your project.
What does Identity Work need to run?
SKILL.md names no scripts, command-line tools or credentials: Identity Work is instructions for the agent only.
Does Identity Work 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 Identity Work 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. Review the folder before installing.
What licence does Identity Work use?
Identity Work is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Identity Work use?
About 636 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Identity Work?
Skills that share tags, products or a category with Identity Work: LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), Self Skill Creator (notdog1998/yourself-skill, 3.4k stars), Morning Journal and Planning (davidhariri/life-system, 845 stars) and Munger Perspective (alchaincyf/munger-skill, 378 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Identity Work?
kangarooking (a GitHub user) maintains it in kangarooking/cangjie-skill, which has 11,029 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 2, 2026.
Source: kangarooking/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.