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 honesty-communicationgit 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/honesty-communication)<a href="https://agentmods.dev/skills/kangarooking/cangjie-skill/honesty-communication"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/honesty-communication/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/honesty-communication"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/honesty-communication.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 | $0.00151 | $0.01575 |
| Opus 5 | $0.00076 | $0.00788 |
| Sonnet 5 | $0.00030 | $0.00315 |
| Haiku 4.5 | $0.00015 | $0.00158 |
Grade A, and why
honesty-communication 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 10d 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.
What it actually says
诚实与沟通
R — 原文 (Reading)
彻底的诚实仅是意味着我想自由。……在你向别人撒谎之前，你必须先对自己撒谎。……我会把彻底的诚实和沃伦·巴菲特的一条老的行事规则结合起来，那是具体地表扬、一般地批判。
— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》
I — 方法论骨架 (Interpretation)
诚实不是道德表演，而是认知安全与心理自由： ① 撒谎先骗自己——费曼「你从不应该在任何时候愚弄任何人，你是最容易愚弄的人」；对别人撒谎会让你相信自己的谎话，扭曲对事实的判断； ② 诚实=自由——所想与所说高度一致时，内心没有需要维护的多重线程；不与需要你注意言辞的人相处； ③ 具体表扬、一般批评——批评指向做法/类别而非个人，表扬要具体到这个人最值得称赞的点，这样对方的自我不会与你对抗； ④ 秘密越少，快乐越多——需要隐藏的东西会变成内心负担； ⑤ 诚实的边界感——「我不会主动说一些消极或令人讨厌的事」，诚实不等于口无遮拦。
A1 — 书中的应用 (Past Application)
案例 1: 不用「我喜欢/不喜欢」
- 问题: 判断被喜好污染
- 方法论的使用: 费曼规则——「我从不询问我喜欢或我不喜欢。我会认为这是什么或这不是什么。」
- 结论: 描述事实优先于表达喜好
- 结果: 判断保持对现实的锚定
案例 2: 剔除不诚实者
- 问题: 如何识别不可信的人
- 方法论的使用: 「如果有人总说他们自己是多么的诚实，他们很有可能是不诚实的」
- 结论: 过度自我标榜=掩盖信号
- 结果: 作者据此保持距离
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 给反馈：「怎么批评同事/孩子而不伤人」
- 拒绝别人：「怎么说'不'又不撒谎」
- 自我检查：「我是不是在自欺」
- 关系沟通：「这段关系里我总是言不由衷」
语言信号
- "怎么诚实又不伤人地沟通"
- "怎么拒绝/批评/表扬"
- "我不想说场面话"
- "how to be honest / give feedback / say no"
与相邻 skill 的区分
- 与
self-liberation的区别: 解放 skill 给「说不」的边界，本 skill 给「怎么说」 - 与
peer-selection的区别: 诚实是内部一致性标准；同伴选择是外部筛选标准
E — 可执行步骤 (Execution)
-
检查自欺点
- 完成标准: 找出本周 1 个「对别人没说真话/对自己隐瞒」的场景，确认它影响什么判断
-
用事实句式重述
- 完成标准: 把「我喜欢/我不喜欢」改成「这是什么/这不是什么」的陈述，检验是否更接近事实
-
执行具体表扬、一般批评
- 完成标准: 下次给反馈时：批评对事不对人（「这个做法」而非「你这个人」），表扬具体到细节
-
清理一个秘密
- 完成标准: 挑一个可以安全说出的秘密，对可信的人讲出来，感受「秘密减少=负担减少」
- 判停条件: 涉及他人隐私/安全时保留秘密——诚实不等于泄露
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 谈判/保密场景（诚实≠和盘托出，作者强调「不会主动说消极或令人讨厌的事」）
- 涉及他人隐私（别人的秘密不是你的诚实素材）
作者在书中警告的失败模式
- 自欺: 「当你对别人撒谎的时候，你也是在骗自己」
- 用诚实当伤害工具: 诚实要配积极——「诚实和积极几乎总是可能的」
作者的盲点 / 时代局限
- 「彻底诚实」在威权/职场政治环境中可能有现实代价，作者有足够的地位承受它
- 「秘密越少快乐越多」未区分健康隐私
容易混淆的邻近方法论
self-liberation: 期望边界给出拒绝的合法性，诚实给出拒绝的句式
相关 skills (阶段 3 定稿)
- composes-with:
identity-work（无所隐藏）、self-liberation、peer-selection
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v17)
- 测试通过率: 见 test-results.md
- 蒸馏时间: 2026-08-01
What ships with it
2 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.
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.
- 10d ago First seen · 121 lines · 151 tokens per session scan A 38eb679a1b11
honesty-communication is a skill published in the GitHub repository kangarooking/cangjie-skill (9,743 stars, last pushed 4d ago), licensed MIT. It adds 151 tokens to every session and 1,575 once invoked, about $0.0008 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
apply-solicited-advice-discipline
Use when someone asks you a specific question, or when you're tempted to offer advice, opinion, or evaluation nobody asked for — answer exactly the scope of what was asked and no more, and don't volunteer advice or judgment unprompted, because unsolicited or over-scoped advice is systematically discounted and can…
run-difficult-conversation
Use when preparing for or facilitating a high-stakes conversation involving conflict, feedback, performance issues, or sensitive interpersonal topics.
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.
dcf-valuation
An investing method for estimating whether a company's share price is cheap by thinking about its future cash earnings. DCF means discounted cash flow, a way to value future money in today's terms.
equanimity-mindset
An investing skill for regaining calm and making decisions based on a company’s long-term cash flows when price changes trigger fear, greed, or comparison with others.