Startup Pressure Test
Kappaemme-git/codex-startup-pressure-test-skill
Pressure-tests a startup idea with blunt, compact analysis of problem reality, competition, first customers and MVP, ending in a strong, weak or pivot verdict.
Helps you judge whether to commit long-term to a partner, project or relationship by testing for compounding value, trust and reputation.
SKILL.md written in Chinese; this summary is our English description.
Install Long-Term Compounding Decisions
$ npx skills add kangarooking/cangjie-skill --skill long-term-compounding -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kangarooking/cangjie-skill long-term-compounding --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/long-term-compounding .claude/skills/long-term-compounding && 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 "long-term-compounding" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/long-term-compounding into .claude/skills/long-term-compounding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-term-compounding", 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/long-term-compoundingType 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 long-term-compounding -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kangarooking/cangjie-skill long-term-compounding --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/long-term-compounding .agents/skills/long-term-compounding && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "long-term-compounding" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/long-term-compounding into .agents/skills/long-term-compounding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-term-compounding", 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 long-term-compounding -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kangarooking/cangjie-skill long-term-compounding --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/long-term-compounding .cursor/skills/long-term-compounding && 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 "long-term-compounding" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/long-term-compounding into .cursor/skills/long-term-compounding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-term-compounding", 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/long-term-compounding--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 long-term-compounding -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kangarooking/cangjie-skill long-term-compounding --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/long-term-compounding .gemini/skills/long-term-compounding && 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 "long-term-compounding" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/long-term-compounding into .gemini/skills/long-term-compounding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-term-compounding", 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 long-term-compoundingInstalls 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 long-term-compounding -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/long-term-compounding .github/skills/long-term-compounding && 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 "long-term-compounding" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/long-term-compounding into .github/skills/long-term-compounding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-term-compounding", 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 long-term-compounding -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 long-term-compounding --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/long-term-compounding .opencode/skills/long-term-compounding && 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 "long-term-compounding" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/long-term-compounding into .opencode/skills/long-term-compounding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "long-term-compounding", 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
long-term-compounding- GitHub stars
- 11k
- Token cost
- ~681 tokens
- SKILL.md length
- 157 words
- Files
- 3
- Skills in repo
- 22
- Repo updated
- First seen
- Licence
- MIT
At a glance
Helps you judge whether to commit long-term to a partner, project or relationship by testing for compounding value, trust and reputation.
- Works in 4 steps: 评估合作/合伙/签约对象：「这个人能合作五年十年吗」 → 犹豫是否接受短期高回报交易：「这单来钱快但伤口碑」 → 想积累声誉/复利资产：「怎么让机会主动来找我」 → …
- Deciding whether a business partner is worth a long-term commitment
- 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 skill applies the idea that wealth, knowledge, reputation and relationships all compound, so a choice should be judged by whether it pays off over a ten-year horizon rather than by what it yields today. It is drawn from a chapter of The Almanack of Naval Ravikant, with quoted passages and two worked cases from the book. The skill text is written in Chinese.
The agent runs four steps: test an opportunity for compounding, ask whether you could imagine working with a person for a lifetime, check for negative signals such as cynical, pessimistic or short-term thinkers, and make a reputation deposit by doing one good thing without keeping score. It states its limits: skip it when a counterpart is near fraud or illegality, or when urgent cash flow comes first, and the author's assumption of a stable environment is flagged as a weakness. A test prompts file and a test results file ship with it.
When your agent uses it
- Deciding whether a business partner is worth a long-term commitment
- Weighing a quick-money deal against damage to your reputation
- Choosing a project or relationship by its payoff over ten years
- Looking for ways to build a reputation so opportunities come to you
Example prompts
- “A client offers fast money but has a poor reputation. Is it worth taking them on?”
- “Should I commit to this cofounder for the long term? Run the lifetime test.”
- “How do I build a reputation in my field so people bring opportunities to me?”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 评估合作/合伙/签约对象：「这个人能合作五年十年吗」
- 犹豫是否接受短期高回报交易：「这单来钱快但伤口碑」
- 想积累声誉/复利资产：「怎么让机会主动来找我」
- 关系决策：「这段关系值得长期投入吗」
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
Long-Term Compounding Decisions loads about 681 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 157 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). 157 words, ~681 tokens.
Download SKILL.mdSave it as
.claude/skills/long-term-compounding/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- long-term-compounding
- description
- 当用户在选择合作者/生意模式/人生策略、问「要不要长期投入这段关系/这个项目」「如何积累声誉」时调用。 核心理念: 财富、知识、声誉、关系都遵循复利; 只玩长期正和游戏, 与能想象共事一辈子的人合作, 拒绝短期思维交易。 不适用于: 紧急止损、短期现金周转等必须立即决策的场景。 Triggers: 长期/复利/声誉/合作/信任/compounding/long-term/trust
- 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 / 第一节 创造财富 / 认识如何创造财富
- tags
- long-term, compounding, relationship, trust, reputation
长期复利游戏
R — 原文 (Reading)
玩复利游戏。无论是财富，人际关系或是知识，所有你人生里获得的回报，都来自于复利。……我的联合创始人Nivi说，“在一个长期游戏里，好像每个人都在让彼此发财，而在一个短期游戏里，好像每个人都在让自己发财。”
— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》 第一章·财富
I — 方法论骨架 (Interpretation)
把复利从金融概念升级为通用人生规律：财富、知识、声誉、关系都以指数方式积累， 所以选择的判据不是「现在能拿多少」，而是「这件事在十年尺度上是否复利」。 两个推论：① 只与「能想象共事一辈子」的长期伙伴合作——信任让谈判成本趋近于零； ② 只玩长期正和游戏——长期游戏里人人把饼做大，短期游戏里人人抢饼。 声誉是最典型的复利资产：持续几十年维护诚信，最终价值远超有才华但无声誉积累的人。 反面筛选信号：愤世嫉俗者、悲观主义者、短期思维者——他们会破坏复利结构。
A1 — 书中的应用 (Past Application)
案例 1: 与 Elad Gil 的交易
- 问题: 商业谈判成本高、信任难建立
- 方法论的使用: 与 Elad Gil 长期交易，对方主动多给好处、差额自掏腰包
- 结论: 信任让常规谈判极简，彼此愿意让利
- 结果: 作者几乎每笔交易都优先拉对方入局，关系进入复利循环
案例 2: 声誉换来别人做不了的交易
- 问题: 为什么巴菲特能买到别人买不到的公司
- 方法论的使用: 长期诚信+可靠+长期思维建立的声誉品牌
- 结论: 「你的性格和你的声誉是可以建立的……你知道这不是运气」
- 结果: 别人把「运气」当机会时，声誉者把机会变成确定收益
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 评估合作/合伙/签约对象：「这个人能合作五年十年吗」
- 犹豫是否接受短期高回报交易：「这单来钱快但伤口碑」
- 想积累声誉/复利资产：「怎么让机会主动来找我」
- 关系决策：「这段关系值得长期投入吗」
语言信号
- "长期 vs 短期怎么选"
- "这个人靠谱吗/值得长期合作吗"
- "怎么建立信任/声誉"
- "compounding / long-term game / is this person trustworthy"
与相邻 skill 的区分
- 与
game-selection的区别: 本 skill 关注时间尺度（长期/短期）；game-selection 关注博弈结构（零和/正和/单人） - 与
peer-selection的区别: 本 skill 的伙伴筛选服务于复利收益；peer-selection 服务于幸福与行为塑造
E — 可执行步骤 (Execution)
对候选机会跑复利测试
- 完成标准: 回答「十年后它还值多少？现在投入的信任/时间/钱会不会指数增长？」
- 判停条件: 若答案是「不可复利且只是快钱」，标记为短期游戏，慎重
对合作者跑『一辈子』测试
- 完成标准: 问「我能想象和这个人共事/生活一辈子吗？」；不能，则一天也别开始
检查负向信号
- 完成标准: 确认对方不是愤世嫉俗者/悲观主义者/短期思维者（他们要证明自己负面看法正确）
为声誉做一笔复利存款
- 完成标准: 本周期内做一件「对方会记得的好事」，不记账、不估量
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 对方已在诈骗/违法边缘（先止损，不要用长期主义自我麻痹）
- 用户急需短期现金流救急（先解决生存，再谈复利）
作者在书中警告的失败模式
- 与愤世嫉俗者合作: 「他们会任由坏事发生，以证明他们负面看法是正确的」
- 估量付出: 「不要去估量——一旦开始计较，你的耐性就会耗尽」
作者的盲点 / 时代局限
- 长期游戏假设环境稳定可预期；在剧变行业/强监管环境，长期承诺也有风险
- 「所有好处都来自复利」是强断言，未考虑不可复利的必要止损
容易混淆的邻近方法论
game-selection: 先识别博弈结构，再决定玩长期还是短期
相关 skills (阶段 3 定稿)
- composes-with:
wealth-structure（复利结构）、peer-selection（长期伙伴） - contrasts-with:
game-selection（时间尺度 vs 博弈结构）
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v03)
- 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/long-term-compounding of kangarooking/cangjie-skill.
- SKILL.md
- test-prompts.json
- test-results.md
Open the folder on GitHubat commit a28de55
Compare with similar skills
Long-Term Compounding Decisions 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 |
|---|---|---|---|---|---|---|
| Long-Term Compounding Decisions this skillkangarooking/cangjie-skill | 11k | — | ~681 | Automated safety check: Pass | MIT | |
| Startup Pressure TestKappaemme-git/codex-startup-pressure-test-skill | 991 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Zhang Yiming Perspectivealchaincyf/zhang-yiming-skill | 173 | 2 repos | ~3.2k | Automated safety check: Pass | MIT | |
| PESTEL Macro Analysisdeanpeters/Product-Manager-Skills | 7.2k | 2 repos | ~3.6k | Automated safety check: Pass | Custom licence | |
| Korean Government Grant Searchdjfksjd/ir-search | 392 | — | ~3.5k | Automated safety check: Notes | MIT | |
| Mao Zedong Thinking Partnerzhangtianruiwork-droid/Maoxuan-Changzheng | 437 | — | ~2.9k | Automated safety check: Pass | None |
Similar skills
Zhang Yiming Perspective
alchaincyf/zhang-yiming-skill
Answers product, organization, globalization, talent and growth questions in the voice of ByteDance founder Zhang Yiming, using a framework built from public material.
PESTEL Macro Analysis
deanpeters/Product-Manager-Skills
Scans political, economic, social, technological, environmental, and legal forces that could threaten or favor a product strategy.
Korean Government Grant Search
djfksjd/ir-search
Surveys open Korean government startup and R&D support programs and sorts them by fit with your project, checking eligibility against the original notices.
Mao Zedong Thinking Partner
zhangtianruiwork-droid/Maoxuan-Changzheng
Chinese-language persona skill that analyzes your problem with a Mao Zedong-style method: investigate first, locate the main contradiction, then probe with questions.
Constraint Engine
lijigang/ljg-skills
Finds the handful of constraints that truly define a domain, role, product or debate, grades each by hardness, and explains the behavior those constraints produce.
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 Long-Term Compounding Decisions
What does Long-Term Compounding Decisions do?
Helps you judge whether to commit long-term to a partner, project or relationship by testing for compounding value, trust and reputation. This skill applies the idea that wealth, knowledge, reputation and relationships all compound, so a choice should be judged by whether it pays off over a ten-year horizon rather than by what it yields today. It is drawn from a chapter of The Almanack of Naval Ravikant, with quoted passages and two worked cases from the book.
When should I use Long-Term Compounding Decisions?
Long-Term Compounding Decisions fits situations like: deciding whether a business partner is worth a long-term commitment; weighing a quick-money deal against damage to your reputation; choosing a project or relationship by its payoff over ten years; looking for ways to build a reputation so opportunities come to you.
How do I install Long-Term Compounding Decisions in Claude Code?
Run `npx skills add kangarooking/cangjie-skill --skill long-term-compounding -a claude-code`. Or copy the skill folder (books/naval-almanack-skill/long-term-compounding in kangarooking/cangjie-skill) into .claude/skills/long-term-compounding in your project. Claude Code loads it when a task matches its description.
How do I install Long-Term Compounding Decisions in Codex?
Run `npx skills add kangarooking/cangjie-skill --skill long-term-compounding -a codex`. Or copy the skill folder (books/naval-almanack-skill/long-term-compounding in kangarooking/cangjie-skill) into .agents/skills/long-term-compounding in your project. Codex loads it when a task matches its description.
Can I use Long-Term Compounding Decisions 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 long-term-compounding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/long-term-compounding, .gemini/skills/long-term-compounding, .github/skills/long-term-compounding and .opencode/skills/long-term-compounding in your project.
What does Long-Term Compounding Decisions need to run?
SKILL.md names no scripts, command-line tools or credentials: Long-Term Compounding Decisions is instructions for the agent only.
Does Long-Term Compounding Decisions 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 Long-Term Compounding Decisions 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 Long-Term Compounding Decisions use?
Long-Term Compounding Decisions 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 Long-Term Compounding Decisions use?
About 681 tokens (SKILL.md is roughly 2.7k 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 Long-Term Compounding Decisions?
Skills that share tags, products or a category with Long-Term Compounding Decisions: Startup Pressure Test (Kappaemme-git/codex-startup-pressure-test-skill, 991 stars), Zhang Yiming Perspective (alchaincyf/zhang-yiming-skill, 173 stars), PESTEL Macro Analysis (deanpeters/Product-Manager-Skills, 7.2k stars) and Korean Government Grant Search (djfksjd/ir-search, 392 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Long-Term Compounding Decisions?
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.