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 sanhuang520-ship-it/awesome-chinese-ai-tools --skill github-readme-cngit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote 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/sanhuang520-ship-it/awesome-chinese-ai-tools/github-readme-cn)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/github-readme-cn"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/github-readme-cn/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/sanhuang520-ship-it/awesome-chinese-ai-tools/github-readme-cn"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/github-readme-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 133 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00099 | $0.02119 |
| Opus 5 | $0.00049 | $0.01059 |
| Sonnet 5 | $0.00020 | $0.00424 |
| Haiku 4.5 | $0.00010 | $0.00212 |
Grade A, and why
github-readme-cn 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub 中文项目门面优化
先说清楚这个技能不做什么：它不能让你的项目火。
下面的建议来自对 15 个近期高增长仓库的结构实测。这些是相关性，不是因果—— 我能测到"12/15 首屏有图"，但测不到"因为有图所以火"。真正决定传播的是有没有人替你转发， 而那个变量不在 README 里。
把门面做好的意义是：当流量真的来的时候，不至于漏掉。 仅此而已。
什么时候用
写或重写开源项目的 README、仓库描述、topics；项目做完了没人看想找原因； 准备投稿到社区/周刊之前的自查。
第一步：先问清楚三件事
- 仓库地址（有的话直接看现状，没有就问定位）
- 目标读者是谁——中文开发者？特定行业？海外？决定语言和例子
- 这个项目和同类比，凭什么选它——答不上来的话，README 写得再漂亮也没用
⚠️ 用户说"帮我优化 README"时，不要直接开始写。 先看他现在的 README 和仓库，指出具体差在哪，再动手。凭空写出来的通常是套话。
首屏是唯一重要的位置
GitHub 上不滚动能看到的大约是 README 前 15 行。绝大多数人只看这一屏。
实测：15 个高增长仓库的首屏
| 特征 | 命中 | 说明 |
|---|---|---|
| 首屏有图 | 12/15 | 最普遍的一条 |
| 首屏有徽章 | 11/15 | shields.io |
| 首屏有安装命令 | 4/15 | 少见，但对工具类很有用 |
| 首屏能点到 demo | 3/15 | 少见，做了就是差异化 |
| 标题用中文 | 2/15 | 即便是中文项目也多用英文名 |
中位数参考：README 15 KB · 图片 10 张 · 仓库名 14 字符 · topics 9 个
首屏该有的东西，按顺序
<div align="center">
<img src="真实产品截图或效果图" width="100%">
# 项目名
**一句话说清楚它给你什么**（不是"这是一个基于 XX 的 YY 框架"）
[徽章] [徽章] [徽章]
[🌐 在线体验] · [📋 文档] · [📸 效果图]
</div>
> **和同类比有什么不一样**
> ① …… ② …… ③ ……
```bash
一行就能跑起来的命令
---
## 关于首屏那张图
**用真实产出，不要用设计稿或抽象插画。**
如果你的项目输出是可视的（网页、图表、CLI 界面、渲染结果），
直接 headless 截图，比任何设计稿都有说服力：
```bash
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
--headless --disable-gpu --hide-scrollbars \
--force-device-scale-factor=2 --window-size=1400,900 \
--screenshot=shot.png "https://你的页面"
多张拼成一条横幅比单张更能体现"有内容"。PNG 转 WebP 通常能省 80%+ 体积。
⚠️ 截图前务必确认它真的反映差异。常见翻车：用 ?theme=xxx 之类的 URL 参数截 8 张"不同主题"，
结果参数根本不生效，8 张图 md5 完全相同。截完对一下哈希。
⚠️ 样张里不要编数据。演示文案里写"测试 200 组样本，准确率 91%"这种， 读起来像真实结果——如果你没测过，这就是造假。
命名与描述
| 项 | 建议 |
|---|---|
| 仓库名 | 中位数 14 字符。awesome-chinese-ai-tools（24）就偏长，且带了已经不准的词 |
| 仓库描述 | GitHub 搜索结果里显示的就是这句。放数字和差异点，别放形容词 |
| topics | 上限 20 个。用目标用户真正会搜的词，不是你觉得贴切的词 |
topics 是最容易被忽略的一环。检查方法：去 GitHub 搜你希望被搜到的词， 看排前面的仓库都打了哪些 topic。如果你的词和他们完全不重合，就是搜不到的原因。
⚠️ 用英文词搜，也打英文 topic。 2026-08-28 实测：
元素周期表的前 5 名 没有一个是周期表项目，互动学习 物理 化学返回 0 结果；换成periodic table interactive则前 5 全部相关。中文项目可以有中文说明， 但别指望中文关键词把人带过来。（数据见references/measured-data.md第四节）
What ships with it
1 file 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.
- 11d ago First seen · 182 lines · 99 tokens per session scan A 5ace90a50ffb
github-readme-cn is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 99 tokens to every session and 2,119 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
update-dependencies
Upgrade project dependencies with breaking change research for major version updates. Use when the user asks to "update dependencies", "upgrade packages", "upgrade dependencies", "update deps", "upgrade deps", "update npm deps", "update Swift packages", "cargo update", "go get updates", "bundle update", or "pip…
review-plan
Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.