Cangjie Skill is a system that turns methods from books, long videos, podcasts, and other source material into executable skills for AI agents. It helps users package knowledge into callable workflows, using the repository's code, methods, and templates; catalogue add-ons relate to these agent skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kangarooking/cangjie-skill --skill naval-almanackgit clone --depth 1 https://github.com/kangarooking/cangjie-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kangarooking/cangjie-skill/naval-almanack)<a href="https://agentmods.dev/skills/kangarooking/cangjie-skill/naval-almanack"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/naval-almanack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kangarooking/cangjie-skill/naval-almanack"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/naval-almanack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00255 | $0.02129 |
| Opus 5 | $0.00128 | $0.01064 |
| Sonnet 5 | $0.00051 | $0.00426 |
| Haiku 4.5 | $0.00026 | $0.00213 |
Grade A, and why
naval-almanack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
《纳瓦尔宝典：财富与幸福指南》 — 来源路由入口（compact pack）
触发与不触发
适用：与本书能力域相关的咨询与任务（见下方路由表的意图列）。 不适用：
- 具体投资标的分析、选股与理财产品建议
- 临床抑郁、精神疾病急性发作等需要专业治疗的场景（先就医）
- 急性自杀风险（先紧急求助）
- 需要外交辞令的谈判策略与具体薪酬数字
核心原则（常驻速览，概览类问题读到这里即可回答）
- 财富=睡觉时仍在赚钱的资产；靠「责任→产权→杠杆」构建，无法靠出租时间致富。
- 用特殊知识（对你像玩、对别人像工作）产品化自己，成为不可替代。
- 判断力比努力重要；无法决定就答否；两条均等的路选短期更痛苦的那条。
- 财富、知识、声誉、关系都遵循复利；只玩长期正和游戏，与能共事一辈子的人同行。
- 幸福是可训练的技能：减少欲望、活在当下；任何处境只有三选项——改变/接受/离开。
- 阅读是终极元技能：读你所爱、原著优先，每天 1-2 小时即进入极少数人行列。
能力路由（先读本表，按意图加载 1 张能力卡）
| 用户意图 | 先读 | 补读/备注 |
|---|---|---|
| 怎么赚钱/如何致富；该不该要期权/股权；评估一个生意或副业的结构 | references/capabilities/wealth-structure.md | 已晋级为独立 Skill wealth-structure（已安装时优先直接使用；本卡仅作原文与背景补充） |
| 职业/副业/自由职业方向纠结；我该做什么才能赚钱且不被替代；寻找独特优势 | references/capabilities/productize-yourself.md | 已晋级为独立 Skill productize-yourself（已安装时优先直接使用；本卡仅作原文与背景补充） |
| 换工作/买房/搬城/合伙/结婚等重大选择纠结；列了利弊表还是拿不定主意 | references/capabilities/decision-heuristics.md | 已晋级为独立 Skill decision-heuristics（已安装时优先直接使用；本卡仅作原文与背景补充） |
| 琐事/外包值不值得；时间分配与安排；离财务自由还差什么 | references/capabilities/hourly-rate-time.md | 已晋级为独立 Skill hourly-rate-time（已安装时优先直接使用；本卡仅作原文与背景补充） |
| 想养成阅读习惯；读什么书/怎么读；如何学习新领域/入门某学科 | references/capabilities/reading-metaskill.md | 已晋级为独立 Skill reading-metaskill（已安装时优先直接使用；本卡仅作原文与背景补充） |
| 刷手机/短视频/社交媒体上瘾；想戒断多巴胺零食 | references/capabilities/screen-detox.md | 已晋级为独立 Skill screen-detox（已安装时优先直接使用；本卡仅作原文与背景补充） |
| 需要方向性判断/这事靠谱吗；想提升决策能力/学心智模型 | references/capabilities/judgment-training.md | references/capabilities/reading-metaskill.md、references/capabilities/decision-heuristics.md |
| 要不要长期投入某段关系/某个项目；如何积累声誉与信任 | references/capabilities/long-term-compounding.md | references/capabilities/peer-selection.md、references/capabilities/wealth-structure.md |
| 为什么大公司磨洋工/小公司拼命；打工还是创业/该不该自己干 | references/capabilities/principal-agent.md | references/capabilities/judgment-training.md |
| 怎么才能更幸福；为什么得到了还不满足；怎么减少焦虑 | references/capabilities/happiness-skill.md | references/capabilities/acceptance.md、references/capabilities/monkey-mind-meditation.md |
| 为什么有人攻击我/大家卷来卷去；怎么不在乎别人眼光；为什么妒忌 | references/capabilities/game-selection.md | references/capabilities/happiness-skill.md、references/capabilities/long-term-compounding.md |
| 困在无法改变的处境里反复内耗；该忍还是该走 | references/capabilities/acceptance.md | references/capabilities/life-meaning.md、references/capabilities/happiness-skill.md |
| 被别人的期望压垮；容易愤怒/怎么不生气；感觉被工作困住/怎么说不 | references/capabilities/self-liberation.md | references/capabilities/happiness-skill.md、references/capabilities/honesty-communication.md |
| 脑子停不下来/焦虑反刍；想学冥想/提升专注力 | references/capabilities/monkey-mind-meditation.md | references/capabilities/happiness-skill.md、references/capabilities/rational-buddhism.md |
| 交朋友/选伴侣/换圈子纠结；感觉被周围人拖累/该不该疏远某人 | references/capabilities/peer-selection.md | references/capabilities/long-term-compounding.md、references/capabilities/honesty-communication.md |
| 发现自己在为立场辩护/看不清现实；反复立志却改变不了自己 | references/capabilities/identity-work.md | references/capabilities/acceptance.md、references/capabilities/honesty-communication.md |
| 怎么真诚沟通/拒绝别人/给反馈；不想说场面话/发现自己在隐瞒 | references/capabilities/honesty-communication.md | references/capabilities/identity-work.md |
| 某主张/玄学/灵修该不该信；想建立自己的验证标准 | references/capabilities/rational-buddhism.md | references/capabilities/life-meaning.md、references/capabilities/monkey-mind-meditation.md |
| 活着的意义是什么/虚无感；找不到方向/该为什么努力 | references/capabilities/life-meaning.md | references/capabilities/rational-buddhism.md、references/capabilities/acceptance.md |
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- BUILD_MANIFEST.json 3.0 KB
- references/capabilities/acceptance.md 5.4 KB
- references/capabilities/decision-heuristics.md 5.2 KB
- references/capabilities/game-selection.md 5.1 KB
- references/capabilities/happiness-skill.md 4.9 KB
- references/capabilities/honesty-communication.md 4.9 KB
- references/capabilities/hourly-rate-time.md 5.2 KB
- references/capabilities/identity-work.md 4.9 KB
- references/capabilities/judgment-training.md 5.1 KB
- references/capabilities/life-meaning.md 5.2 KB
- references/capabilities/long-term-compounding.md 5.2 KB
- references/capabilities/monkey-mind-meditation.md 5.2 KB
- references/capabilities/peer-selection.md 5.1 KB
- references/capabilities/principal-agent.md 5.1 KB
- references/capabilities/productize-yourself.md 5.5 KB
- references/capabilities/rational-buddhism.md 5.3 KB
- references/capabilities/reading-metaskill.md 5.0 KB
- references/capabilities/screen-detox.md 5.2 KB
- references/capabilities/self-liberation.md 5.1 KB
- references/capabilities/wealth-structure.md 5.4 KB
- references/capability-index.md 4.8 KB
- references/cheatsheet.md 2.7 KB
- references/glossary.md 2.8 KB
- references/overview.md 12 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 78 lines · 255 tokens per session scan A 3d5793b8f412
naval-almanack is a skill published in the GitHub repository kangarooking/cangjie-skill (9,795 stars, last pushed 4d ago), licensed MIT. It adds 255 tokens to every session and 2,129 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-builder
Use when automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
us-program-research
This skill should be used when the user needs structured research and ranking of US academic programs (PhD, Master.
legend-lore
Use this spell when you need everything knowable about a person, company, library, framework, concept, or system — not a quick answer, but a deep dossier.
comprehend-languages
Use this skill when the words are legible but the meaning is trapped inside an unfamiliar dialect, format, or community.
capability-circle
A framework for deciding which companies and industries an investor understands well enough to judge their future cash flow.
concentrated-investing
An investing framework about putting a larger share of money into a small number of companies you understand well. It distinguishes concentrated investing from broad diversification used for general wealth management.