best-skills is a collection of reusable skills for coding agents, including tools for writing papers, creating diagrams and presentations, generating code documentation, and other tasks. Users install its skills into agents such as Cursor, Claude Code, Codex, or OpenClaw so those agents can recognize relevant requests and run the corresponding workflows. The catalogue entries are examples of the skills included in the collection.
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 xstongxue/best-skills --skill project-docsgit clone --depth 1 https://github.com/xstongxue/best-skillsWrote 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/xstongxue/best-skills/project-docs)<a href="https://agentmods.dev/skills/xstongxue/best-skills/project-docs"><img src="https://agentmods.dev/badge/skills/xstongxue/best-skills/project-docs/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/xstongxue/best-skills/project-docs"><img src="https://agentmods.dev/badge/skills/xstongxue/best-skills/project-docs.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 | $0.00177 | $0.01668 |
| Opus 5 | $0.00088 | $0.00834 |
| Sonnet 5 | $0.00035 | $0.00334 |
| Haiku 4.5 | $0.00018 | $0.00167 |
Grade A, and why
project-docs 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 12d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
project-docs：项目深度文档生成
输出到项目的 docs/ 目录。核心约束：文档里的代码、类名、路径都必须来自真实文件，见 Phase 3。
Step 0：判断要做哪种
| 用户表述 | 做什么 |
|---|---|
| 生成项目文档 / 新人文档 / 深入理解项目（没指定篇目） | 全部生成，Phase 1 → 2 → 3 → 4 |
| 帮我写架构文档 / 只要代码导读 / 写构建和调试 | 只写指定的几篇，读项目的范围可相应缩小 |
| 代码改了，更新文档 / 文档过期了 | 读 docs/.project-map.md，比对现在的代码，只重写受影响的篇目 |
docs/ 已经有内容时：先列出已有文件，问用户是覆盖、跳过已存在的、还是备份到 docs.bak/。不要直接盖掉。
不该用这个 skill 的情况：用户要的是论文章节、项目梳理、重点问题清单、简历项目描述——也就是给导师、评委、HR、领导看，且格式由对方指定的东西，用 codegen-doc。这个 skill 只管给新同事看、要能照着上手的文档。
Phase 1：先读项目，把结果记下来
记到 docs/.project-map.md。后面每一篇要用的路径、类名、代码，都从这个文件取。
分三步读，不要试图把所有源文件都读完：
- 看轮廓 —— 目录树、构建和依赖文件、README，判断用什么语言、属于哪类项目
- 看骨架 —— 入口文件读全文、接口和类型定义、列出每个模块干什么
- 跟一个完整例子走一遍 —— 挑一个有代表性的示例或功能，从入口追到结束
怎么读、记成什么格式、什么时候可以停，见 reference/explore.md。把那份模板填完再进 Phase 2，其中术语表至少 5 条。
Phase 2：按项目类型决定写哪几篇
01_architecture.md → 架构：项目长什么样
02_philosophy.md → 思想：为什么这样设计
03_lang_concepts.md → 语言特性：读代码前的准备
04_code_walkthrough.md → 代码导读：跟着真实流程走一遍
05_runtime_model.md → 运行时：并发和生命周期
06_build_guide.md → 构建：怎么编译运行
07_integration_guide.md → 对接：怎么写新功能
08_debug_guide.md → 调试：出问题怎么查
09_design_conventions.md → 规范：怎么设计得更好
默认模板偏向 C++ 那类"要编译、有多线程、有进程间通信"的项目。前端、数据脚本、库这类项目必须按对照表替换或跳过对应篇目，见 reference/project-types.md。
编号固定，跳过的留空号，不要往前挪。 跳过 05 就是 01,02,03,04,06,07,08,09，原因见 project-types.md。
Phase 3：写
贴代码前先读那个文件
.project-map.md 里只有路径，不是代码原文。要贴哪段代码，先 Read 那个文件确认现在的内容。引用统一带位置：src/core/channel.cpp:120-135。
不这样做，新人会照着一个不存在的类名去搜索——比没有文档更糟。
写给谁看
刚接触项目的新同学。不假设他们了解项目背景，但假设有基础编程能力。
每篇都要有的
- 开头一个
> 一句话说明这篇解决什么问题 - 先说"是什么" → 再说"为什么" → 最后说"怎么做"
- 有对比（❌ 不用框架怎么写 vs ✅ 用框架怎么写）
- 抽象的概念配一个生活里的例子
- 结尾一张速查表或检查清单
图怎么画
| 要表达什么 | 用什么 |
|---|---|
| 调用关系、时序、状态变化、类之间的继承 | Mermaid |
| 目录树、分层框图、内存布局 | ASCII |
ASCII 图宽度控制在 80 字符内，超了在 Typora 和网页里会折行错位。
多长
每篇 300–600 行。不到 300 说明挖得不够深；超过 600 该拆节。避免一篇两千行、另一篇三十行。
用词
What ships with it
5 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.
- 12d ago First seen · 114 lines · 177 tokens per session scan A e68efaf47fe4
project-docs is a skill published in the GitHub repository xstongxue/best-skills (2,814 stars, last pushed 17d ago), licensed Apache-2.0. It adds 177 tokens to every session and 1,668 once invoked, about $0.0009 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
math-olympiad
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any…
google-agents-cli-onboarding
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs…
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gh-pr-review
Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…