pm-claude-skills 80.2.0 → 81.1.0

package/README.md

@@ -1,16 +1,17 @@
-# 🧠 PM Skills — 1176 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 1235 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
 
 <p align="center">
   <a href="https://mohitagw15856.github.io/pm-claude-skills/">
     <picture>
       <source media="(prefers-color-scheme: dark)" srcset="web/docs-assets/hero.svg">
       <source media="(prefers-color-scheme: light)" srcset="web/docs-assets/hero-light.svg">
-      <img src="web/docs-assets/hero.svg" width="100%" alt="PM Skills — 1176 professional skills your AI assistant can read. Plain markdown, works with Claude, ChatGPT, Gemini, Cursor, and Codex. MIT licensed." />
+      <img src="web/docs-assets/hero.svg" width="100%" alt="PM Skills — 1235 professional skills your AI assistant can read. Plain markdown, works with Claude, ChatGPT, Gemini, Cursor, and Codex. MIT licensed." />
     </picture>
   </a>
 </p>
 
 <p align="center">
+  <a href="README.zh-CN.md"><strong>简体中文</strong></a> &middot;
   <a href="#-quick-start"><strong>Quick start</strong></a> &middot;
   <a href="https://mohitagw15856.github.io/pm-claude-skills/"><strong>Playground</strong></a> &middot;
   <a href="SKILLS.md"><strong>All skills</strong></a> &middot;
@@ -20,6 +21,10 @@
   <a href="ROADMAP.md"><strong>Roadmap</strong></a>
 </p>
 
+<p align="center">
+  🇨🇳 <strong>中文用户</strong>：<a href="README.zh-CN.md">中文说明</a> · <a href="#-中文支持--chinese-support">中文技能包</a> · 支持 Trae、Qoder、通义灵码、CodeBuddy · 支持 DeepSeek、通义千问、Kimi、智谱 GLM、豆包 · <a href="docs/CHINA.md">国内安装指南</a>
+</p>
+
 <p align="center">
   <a href="https://github.com/mohitagw15856/pm-claude-skills/stargazers"><img src="https://img.shields.io/github/stars/mohitagw15856/pm-claude-skills?style=social" alt="Stars"></a>
   <a href="SKILLS.md"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fmohitagw15856.github.io%2Fpm-claude-skills%2Fskills.json&query=%24.count&label=skills&color=blue" alt="Skills"></a>
@@ -33,15 +38,15 @@
 
 > **Your landlord kept your deposit. Your mom got a medical bill that makes no sense. You got laid off on a Tuesday. Someone you love died, and no one handed you the checklist.**
 >
-> Generic AI is a very confident intern. **PM Skills** is the senior colleague's notes — 1176 of them, one markdown file each, for the moments at work *and* in life where "it depends" is not an answer. *(PM stands for Professional, not just Product Management. Yes, we get asked.)*
+> Generic AI is a very confident intern. **PM Skills** is the senior colleague's notes — 1235 of them, one markdown file each, for the moments at work *and* in life where "it depends" is not an answer. *(PM stands for Professional, not just Product Management. Yes, we get asked.)*
 
 <!-- AEO Answer Capsule — 68 words -->
-PM Skills is an open-source library of 1176 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.
+PM Skills is an open-source library of 1235 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.
 <!-- End AEO Capsule -->
 
 <table align="center"><tr>
-<td align="center"><b>1176</b><br><sub>skills</sub></td>
-<td align="center"><b>134</b><br><sub>bundles</sub></td>
+<td align="center"><b>1235</b><br><sub>skills</sub></td>
+<td align="center"><b>142</b><br><sub>bundles</sub></td>
 <td align="center"><b>35</b><br><sub>professions</sub></td>
 <td align="center"><b>12</b><br><sub>platforms</sub></td>
 <td align="center"><b>4.8 / 5</b><br><sub><a href="https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html">eval-scored</a></sub></td>
@@ -57,6 +62,28 @@ PM Skills is an open-source library of 1176 Agent Skills — plain-markdown SKIL
 | **02** | Your assistant loads the one skill that matches | [`security-deposit-recovery`](skills/security-deposit-recovery/SKILL.md), a single markdown file, read only when it is relevant |
 | **03** | You get the finished document, not advice about it | The challenge to each deduction, the demand letter, and the point at which small claims is worth it |
 
+## 🇨🇳 中文支持 · Chinese support
+
+**用中文提问即可。** 六个面向中文用户的技能包，60 个技能有简体中文版、25 个有繁体中文版，技能路由能理解中文请求。
+*Ask in Chinese. Six packs built for Chinese users, 60 skills translated into Simplified Chinese and 25 into Traditional, and routing that understands Chinese requests.*
+
+| 技能包 Pack | 内容 What it covers | 试着说 Try saying |
+|---|---|---|
+| [**pm-china-work**](plugins/pm-china-work/) 职场 | 周报 / 月报、述职报告 / 年终总结、晋升答辩、复盘、需求评审、职级对标、飞书文档、钉钉日志、企业微信公告 | "帮我把这些笔记整理成周报。" |
+| [**pm-china-exams**](plugins/pm-china-exams/) 考试与求职 | 申论、结构化面试、考研规划、校招与三方协议、国企面试 | "下个月公务员面试，帮我模拟一轮。" |
+| [**pm-china-life**](plugins/pm-china-life/) 生活事务 | 劳动合同解读、经济补偿金 N / N+1 / 2N、个税年度汇算、五险一金、高考志愿 | "公司要裁我，能拿多少补偿？" |
+| [**pm-zh-content**](plugins/pm-zh-content/) 内容平台 | 小红书笔记、公众号文章、抖音脚本、直播带货脚本 | "帮我写一篇小红书笔记。" |
+| [**pm-chuhai**](plugins/pm-chuhai/) 出海 | 出海市场进入、跨境电商 listing、PIPL 与 GDPR 对照 | "我们想出海，东南亚还是中东？" |
+| [**pm-cv**](plugins/pm-cv/) 简历 | 按目标公司定制简历、中英文简历、导出 Word | "帮我做一份中英文简历，要投外企。" |
+
+**国内安装 Install from China** (npm mirror, plus the coding tools popular in China):
+
+```bash
+npx --registry=https://registry.npmmirror.com pm-claude-skills add --agent trae   # 或 qoder / lingma / codebuddy / claude
+```
+
+**在线试用 Playground**：用你自己的 DeepSeek、通义千问、Kimi、智谱 GLM（有免费模型）或豆包 API Key。**More:** [中文说明 README.zh-CN.md](README.zh-CN.md) · [国内安装指南 docs/CHINA.md](docs/CHINA.md) · [中文翻译 skills-i18n/zh](skills-i18n/zh/)
+
 ## 🚪 Pick a door — 30 seconds each
 
 | | You… | Do this |
@@ -64,6 +91,7 @@ PM Skills is an open-source library of 1176 Agent Skills — plain-markdown SKIL
 | ▶ | **just want to see it** | open the **[Playground](https://mohitagw15856.github.io/pm-claude-skills/)** and run a skill in your browser. No install, no signup, no "enter your email to continue" |
 | 🧠 | **use Claude Code** | `/plugin` → search **pm-skills** → install. Ask *"decode this lease"* and watch |
 | 🛠 | **use anything else** | `npx pm-claude-skills add` and pick your tool (Cursor, Codex, Windsurf, ChatGPT, Gemini…) |
+| 🇨🇳 | **read Chinese** | **[中文说明](README.zh-CN.md)**：用中文提问，六个中文技能包，支持 Trae、Qoder、通义灵码和国内模型 |
 | 🔎 | **don't know what to ask for** | type it at **[find](https://mohitagw15856.github.io/pm-claude-skills/find.html)** — *"my landlord kept my deposit"* — and it names the skill |
 | 🎒 | **are in the middle of something** | start from your moment, not the catalogue → **[Skill Packs](PACKS.md)** · 🍼 new parent · 💼 laid off · 🌍 new country · 👵 caring for a parent · 🕊️ losing someone · 💸 money in crisis |
 
@@ -74,6 +102,7 @@ PM Skills is an open-source library of 1176 Agent Skills — plain-markdown SKIL
 | Works with | |
 |---|---|
 | **Assistants** | [Claude Code](docs/installation.md) · [ChatGPT](exports/chatgpt/) · [Gemini](exports/gemini/) · [Cursor, Codex, Windsurf](docs/installation.md) · [any MCP client](mcp-remote/) |
+| **Popular in China** | [Trae, Qoder, Lingma 通义灵码, CodeBuddy](docs/CHINA.md) · [DeepSeek, Qwen, Kimi, GLM, Doubao in the playground](docs/CHINA.md) |
 | **Where you already work** | [Telegram](integrations/telegram/) · [Slack](integrations/slack-app/) · [Raycast](integrations/raycast/) · [Obsidian](integrations/obsidian-plugin/) · [n8n](connectors/) |
 | **For builders** | [Python](https://pypi.org/project/pm-skills/) · [Hugging Face dataset](dataset/) · [Docker](Dockerfile) · [GitHub Actions](action/) · [decision layer](integrations/jev/) |
 
@@ -109,8 +138,8 @@ PM Skills is an open-source library of 1176 Agent Skills — plain-markdown SKIL
 <table>
 <tr>
 <td width="50%" align="center">
-<a href="https://mohitagw15856.github.io/pm-claude-skills/galaxy3d.html"><img src="web/docs-assets/demo-galaxy.webp" width="100%" alt="Galaxy 3D — fly through all 1176 skills as a glowing constellation you orbit and click into" /></a>
-<br /><sub><b>🌌 <a href="https://mohitagw15856.github.io/pm-claude-skills/galaxy3d.html">Galaxy 3D</a></b> — all 1176 skills as a constellation. The ones you've run burn brighter. Zero productivity value, 100% recommended.</sub>
+<a href="https://mohitagw15856.github.io/pm-claude-skills/galaxy3d.html"><img src="web/docs-assets/demo-galaxy.webp" width="100%" alt="Galaxy 3D — fly through all 1235 skills as a glowing constellation you orbit and click into" /></a>
+<br /><sub><b>🌌 <a href="https://mohitagw15856.github.io/pm-claude-skills/galaxy3d.html">Galaxy 3D</a></b> — all 1235 skills as a constellation. The ones you've run burn brighter. Zero productivity value, 100% recommended.</sub>
 </td>
 <td width="50%" align="center">
 <a href="https://mohitagw15856.github.io/pm-claude-skills/wrapped.html"><img src="web/docs-assets/demo-holo.webp" width="100%" alt="PM Skills Wrapped — your practice turned into a shareable, Spotify-Wrapped-style story" /></a>
@@ -123,7 +152,9 @@ PM Skills is an open-source library of 1176 Agent Skills — plain-markdown SKIL
 
 | Release | What it adds | Try saying | Read more |
 |---|---|---|---|
-| **[v80.2.0](https://github.com/mohitagw15856/pm-claude-skills/releases/latest)** trust in a release | The MCP install command fixed, a check that every release installs and runs, announcements in `doctor` and the playground, and frozen versions of the flagship skills that a team can pin | *"Run the doctor."* | [CHANGELOG.md](CHANGELOG.md) · [skill releases](docs/SKILL-RELEASES.md) |
+| **[v81.1.0](https://github.com/mohitagw15856/pm-claude-skills/releases/latest)** launch kit and 3D explorer | Nine skills to ship a side project strangers trust, a topic-to-3D-explorer pipeline, the library as a [tech tree](https://mohitagw15856.github.io/pm-claude-skills/tech-tree/), and Chinese exam and office-tool skills | *"Make my app self-hostable."* · *"Build a 3D explorer of the heart."* | [pm-oss-launch](plugins/pm-oss-launch/) · [pm-3d-explorer](plugins/pm-3d-explorer/) |
+| **[v81.0.0](https://github.com/mohitagw15856/pm-claude-skills/releases/tag/v81.0.0)** Chinese support and the CV studio | Five packs for Chinese users, Chinese models and coding tools, 75 translations, and a CV shaped for one company from its tracking system, country, sector, values and job ad | *"帮我写周报"* · *"Write my CV for this Monzo job."* | [中文支持](#-中文支持--chinese-support) · [pm-cv](plugins/pm-cv/) |
+| **[v80.2.0](https://github.com/mohitagw15856/pm-claude-skills/releases/tag/v80.2.0)** trust in a release | The MCP install command fixed, a check that every release installs and runs, announcements in `doctor` and the playground, and frozen versions of the flagship skills that a team can pin | *"Run the doctor."* | [CHANGELOG.md](CHANGELOG.md) · [skill releases](docs/SKILL-RELEASES.md) |
 | **[v80.1.0](https://github.com/mohitagw15856/pm-claude-skills/releases/tag/v80.1.0)** design taste | A five-stage UI pipeline (direction, system, motion, critique, verification) that stops generic AI-looking interfaces, with pointers to five specialist design skills | *"Run the design pipeline on this landing page."* | [pm-design-taste](plugins/pm-design-taste/) · [credits](plugins/pm-design-taste/THIRD_PARTY.md) |
 | **v80.0.0** the promote loop | Scans your own transcripts for what you keep asking, drafts it as a skill, tests the triggers, publishes it | *"What do I keep asking you for?"* | [PROMOTE-LOOP.md](docs/PROMOTE-LOOP.md) |
 | **v79.0.0** the decision layer | Typed questions with a probability per option: which skill, is this input safe, ship or slip | *"Should we ship Friday?"* | [JEV-DECISION-LAYER.md](docs/JEV-DECISION-LAYER.md) |
@@ -141,7 +172,7 @@ Say it in your own words. The description does the routing:
 | 🛂 *"prep me for the visa interview"* → [the-visa-interview](skills/the-visa-interview/SKILL.md) | 🔨 *"is this contractor quote fair?"* → [home-contractor-quote-decoder](skills/home-contractor-quote-decoder/SKILL.md) | 🏡 *"should we rent or buy?"* → [rent-vs-buy](skills/rent-vs-buy/SKILL.md) |
 | 📝 *"draft my self-review honestly"* → [performance-review](skills/performance-review/SKILL.md) | 🚢 *"ship Friday or slip a week?"* → [ship-or-slip](skills/ship-or-slip/SKILL.md) | ♻️ *"what do I keep asking you for?"* → [promoter-scan](skills/promoter-scan/SKILL.md) |
 
-…all 1176 live in **[the catalog](SKILLS.md)**.
+…all 1235 live in **[the catalog](SKILLS.md)**.
 
 ## ⚡ Quick start
 
@@ -158,7 +189,7 @@ No `npm install` needed — `npx pm-claude-skills …` always runs the latest. P
 
 ## 📚 The skills
 
-Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules, not vibes), a concrete output template, quality checks, and anti-patterns. All 1176 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
+Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules, not vibes), a concrete output template, quality checks, and anti-patterns. All 1235 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
 
 <table align="center">
   <tr align="center">
@@ -184,9 +215,9 @@ Every skill follows the same discipline: what it produces, the inputs it needs,
 </table>
 
 <p align="center">
-  <b><a href="SKILLS.md">Browse all 1176 →</a></b> ·
+  <b><a href="SKILLS.md">Browse all 1235 →</a></b> ·
   <b><a href="https://mohitagw15856.github.io/pm-claude-skills/">try one in your browser →</a></b> ·
-  <b><a href="plugins/">134 bundles →</a></b>
+  <b><a href="plugins/">142 bundles →</a></b>
 </p>
 
 <details>
@@ -235,7 +266,7 @@ Every skill follows the same discipline: what it produces, the inputs it needs,
 | <img src="web/docs-assets/logos/pm-design.svg" width="20" alt=""/> [Design & UX](plugins/pm-design/) | <img src="web/docs-assets/logos/pm-legal.svg" width="20" alt=""/> [Legal](plugins/pm-legal/) | <img src="web/docs-assets/logos/pm-finance.svg" width="20" alt=""/> [Finance](plugins/pm-finance/) |
 | <img src="web/docs-assets/logos/pm-founders.svg" width="20" alt=""/> [Founders](plugins/pm-founders/) | <img src="web/docs-assets/logos/pm-security.svg" width="20" alt=""/> [Security](plugins/pm-security/) | <img src="web/docs-assets/logos/pm-gov.svg" width="20" alt=""/> [Government](plugins/pm-gov/) |
 
-…plus HR, sales, operations, research, healthcare, educators, writers, social media, and more — **[the full profession index](SKILLS.md)**, or by bundle in [`plugins/`](plugins/) (134 bundles). Install any bundle: `/plugin install pm-decoders@pm-skills`.
+…plus HR, sales, operations, research, healthcare, educators, writers, social media, and more — **[the full profession index](SKILLS.md)**, or by bundle in [`plugins/`](plugins/) (142 bundles). Install any bundle: `/plugin install pm-decoders@pm-claude-skills`.
 
 ### Meta
 
@@ -268,6 +299,35 @@ ADHD-friendly executive function, useful for every brain:
 </tr>
 </table>
 
+<table>
+<tr>
+<td width="50%" valign="top">
+
+### 🚀 [pm-oss-launch](plugins/pm-oss-launch/): ship your side project
+From "works on my machine" to a repo strangers install, trust and contribute to:
+- [readme-benefit-writer](skills/readme-benefit-writer/SKILL.md): every feature as a benefit, plus a Your data section
+- [demo-data-generator](skills/demo-data-generator/SKILL.md): a seeded, no-signup demo with no real personal data
+- [self-host-packager](skills/self-host-packager/SKILL.md): one-command Docker self-hosting with backups and upgrades
+- [readonly-mcp-wrapper](skills/readonly-mcp-wrapper/SKILL.md): a read-only MCP server over your docs folder
+
+Plus importers, good first issues, a licence audit, fortnightly releases and the 20-second demo clip. Install: `/plugin install pm-oss-launch@pm-claude-skills`
+
+</td>
+<td width="50%" valign="top">
+
+### 🧊 [pm-3d-explorer](plugins/pm-3d-explorer/): topic in, 3D explorer out
+Turn any topic into an interactive 3D page learners can take apart:
+- [explorer-interface-brief](skills/explorer-interface-brief/SKILL.md): the UI brief and an image prompt for the mock
+- [model-prompt-pack](skills/model-prompt-pack/SKILL.md): image-to-3D prompts and a parts list where every label has a source
+- [explorer-viewer-builder](skills/explorer-viewer-builder/SKILL.md): a single-file Three.js viewer with exploded view and quiz mode
+- [explorer-pipeline](skills/explorer-pipeline/SKILL.md): runs all three in order with a build checklist
+
+Install: `/plugin install pm-3d-explorer@pm-claude-skills`
+
+</td>
+</tr>
+</table>
+
 ## 🔍 What does a skill look like?
 
 <!-- AEO Answer Capsule — 62 words -->
@@ -334,13 +394,13 @@ Checks frontmatter, the `Use when …` trigger clause a model actually matches o
 ## ❓ Straight answers
 
 <details><summary><b>Is it actually free?</b></summary>
-Yes — MIT, all 1176 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access.
+Yes — MIT, all 1235 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access.
 </details>
 <details><summary><b>Do I need an API key?</b></summary>
 Not to browse, read, install, or use skills inside a tool you already have. The playground serves a few sponsor-funded free runs a day. A key only matters for optional extras: running skills from CI, or the typed decision layer (which falls back to keyword routing without one).
 </details>
-<details><summary><b>The catalog says 1176 but the folder has more. Which is it?</b></summary>
-Both. There are <b>1188</b> directories under <code>skills/</code>; <b>12</b> of them are <a href="docs/DEPRECATION.md">deprecated</a> (marked in their frontmatter, each pointing at the skill that replaced it). They stay on disk so an old install command or a bookmarked name never breaks, and they are hidden from the catalog, the playground and the headline count. 1176 is what a person can browse; 1178 is what an installer can resolve.
+<details><summary><b>The catalog says 1235 but the folder has more. Which is it?</b></summary>
+Both. There are <b>1188</b> directories under <code>skills/</code>; <b>12</b> of them are <a href="docs/DEPRECATION.md">deprecated</a> (marked in their frontmatter, each pointing at the skill that replaced it). They stay on disk so an old install command or a bookmarked name never breaks, and they are hidden from the catalog, the playground and the headline count. 1235 is what a person can browse; 1178 is what an installer can resolve.
 </details>
 <details><summary><b>I'm not a product manager. Is this for me?</b></summary>
 PM stands for <i>Professional</i> here. Most of the library is decoders for leases and medical bills, salary-negotiation practice, career-moment kits, life admin, and 35 professions from teaching to veterinary. The product-management corner is just where it started.
@@ -352,6 +412,15 @@ No. Skills are inert text files in a folder; your assistant reads them when rele
 Every skill passes a structural gate (SkillSpec L3) and a security scan in CI; 208 outputs are <a href="https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html">eval-scored in the open</a> (avg 4.8/5), and the <a href="skillbench/REPORT.md">benchmark report</a> publishes the negative findings too. When something is machine-translated or unscored, it's labelled.
 </details>
 
+## 🌳 The tech tree
+
+**[Open the tech tree →](https://mohitagw15856.github.io/pm-claude-skills/tech-tree/)** The whole library drawn as a strategy-game research tree: every bundle is a branch, every skill a node. Shipped skills are *researched*, the three most-voted requests are *in research*, and the rest are *proposed*. Search any skill, click it for its description, and copy its install command.
+
+- **Rebuild the data:** `node scripts/build-tech-tree.mjs` reads `.claude-plugin/marketplace.json` and `plugins/`, and writes `site/tech-tree/data.json`.
+- **Refresh the votes:** `node scripts/build-tech-tree.mjs --refresh-votes` counts 👍 reactions on open [`skill-request`](https://github.com/mohitagw15856/pm-claude-skills/issues?q=is%3Aissue+is%3Aopen+label%3Askill-request) issues and updates `site/tech-tree/votes.json`. To vote, react to a request or [open one](https://github.com/mohitagw15856/pm-claude-skills/issues/new?labels=skill-request&title=Skill:%20).
+- **Preview locally:** `npx serve site/tech-tree` (or `python3 -m http.server -d site/tech-tree`), then open the address it prints. Opening the file directly will not load `data.json`.
+- **GitHub Pages:** the *Deploy Skill Playground* workflow rebuilds the tree and publishes it at `/tech-tree/` on every push to `main`. In a fork, turn on Pages under **Settings → Pages → Source: GitHub Actions**, and the same workflow publishes it. The page is a single HTML file plus `data.json`, so any static host works too.
+
 ## 🗺️ Roadmap
 
 - ✅ Exports to 12 platforms and one install command
@@ -398,4 +467,4 @@ MIT — use them, fork them, ship them at work. Skills are judgment, and judgmen
 
 ---
 
-*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 1176 skills · 134 bundles · 35 professions · every commit gated. The long version — every feature, wave, and frontier bet — lives in the **[Showcase](docs/SHOWCASE.md)**.*
+*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 1235 skills · 142 bundles · 35 professions · every commit gated. The long version — every feature, wave, and frontier bet — lives in the **[Showcase](docs/SHOWCASE.md)**.*

package/README.zh-CN.md

@@ -0,0 +1,88 @@
+# PM Skills：一千多个专业 Agent Skills
+
+[English](README.md) · **简体中文** · [在中国使用](docs/CHINA.md) · [全部技能](SKILLS.md) · [更新日志](CHANGELOG.md)
+
+> 在国内？不需要访问 GitHub：通过 npmmirror、清华 PyPI 镜像、[Gitee 镜像](https://gitee.com/mohitagw/pm-claude-skills)和[魔搭数据集](https://www.modelscope.ai/datasets/mohitagw15856/pm-skills-instruct)安装，详见[在中国使用](docs/CHINA.md)。
+
+> 想系统地学怎么用和写 Agent Skills？见六课的开源小课：[用 Agent Skills 做职场工作](docs/learn-zh/README.md)。
+
+PM Skills 是一个开源的 Agent Skills 库。每个技能是一份 Markdown 文件（`SKILL.md`），教 AI 助手把一件专业工作做到资深水平：从写 PRD、周报，到解读劳动合同、准备晋升答辩。
+
+这里的 PM 指 Professional（专业人士），不只是产品经理。
+
+MIT 开源协议，永久免费。没有运行时、没有遥测、不需要账号。
+
+## 它是怎么工作的
+
+| | 步骤 | 例子 |
+|---|---|---|
+| **01** | 用你自己的话说出需要什么 | "公司要裁我，能拿多少补偿？" |
+| **02** | AI 助手加载与之匹配的那一个技能 | [`cn-severance-calculator`](skills/cn-severance-calculator/SKILL.md)，一份 Markdown 文件，只在相关时读取 |
+| **03** | 你得到的是完成的成果，而不是关于怎么做的建议 | 适用的情形（N、N+1 或 2N）、逐步计算、签字前要核对的事项 |
+
+## 安装
+
+**Claude Code：**
+
+```bash
+npx --registry=https://registry.npmmirror.com pm-claude-skills add --agent claude
+```
+
+**国内常用的 AI 编程工具：**
+
+```bash
+npx pm-claude-skills add --agent trae        # Trae
+npx pm-claude-skills add --agent qoder       # Qoder
+npx pm-claude-skills add --agent lingma      # 通义灵码
+npx pm-claude-skills add --agent codebuddy   # CodeBuddy
+```
+
+只装部分技能包：
+
+```bash
+npx pm-claude-skills add --agent trae --bundle pm-china-work,pm-cv
+```
+
+还支持 Cursor、Windsurf、Codex、Cline 等，详见 [docs/CHINA.md](docs/CHINA.md)。
+
+## 适合中国用户的技能包
+
+| 技能包 | 内容 | 试着说 |
+|---|---|---|
+| [**pm-china-work**](plugins/pm-china-work/) 职场 | 周报 / 月报、述职报告 / 年终总结、晋升答辩、复盘、需求评审、职级对标、飞书文档、钉钉日志、企业微信公告 | "帮我把这些笔记整理成周报。" |
+| [**pm-china-exams**](plugins/pm-china-exams/) 考试与求职 | 申论、结构化面试、考研规划、校招与三方协议、国企面试 | "下个月公务员面试，帮我模拟一轮。" |
+| [**pm-china-life**](plugins/pm-china-life/) 生活事务 | 劳动合同解读、经济补偿金估算、个税年度汇算、五险一金、高考志愿 | "三年合同试用期六个月，合法吗？" |
+| [**pm-zh-content**](plugins/pm-zh-content/) 内容平台 | 小红书笔记、公众号文章、抖音脚本、直播带货脚本 | "帮我写一篇小红书笔记。" |
+| [**pm-chuhai**](plugins/pm-chuhai/) 出海 | 出海市场进入计划、跨境电商 listing、PIPL 与 GDPR 对照 | "我们想出海，东南亚还是中东？" |
+| [**pm-cv**](plugins/pm-cv/) 简历 | 按目标公司定制简历、中英文简历、ATS 检查、导出 Word | "帮我做一份中英文简历，要投外企。" |
+
+此外还有一千多个通用技能，覆盖产品、工程、数据、设计、市场、销售、人力、法律、财务等 35 个职业。完整列表见 [SKILLS.md](SKILLS.md)。
+
+## 中文翻译
+
+[`skills-i18n/zh/`](skills-i18n/zh/) 中有 60 个技能的简体中文翻译，[`skills-i18n/zh-TW/`](skills-i18n/zh-TW/) 中有 25 个技能的繁体中文翻译。英文版本为规范版本；翻译由 CI 检查结构是否一致。
+
+用中文提问时，技能路由也能理解：例如"我的房东扣了我的押金"会匹配到押金追回技能。
+
+## 在线试用
+
+[Playground](https://mohitagw15856.github.io/pm-claude-skills/) 支持用你自己的 API Key 调用 DeepSeek、通义千问、Kimi、智谱 GLM（有免费模型）和豆包。Key 只保存在你的浏览器里。
+
+Playground 托管在 GitHub Pages，在国内可能访问较慢；技能安装到本地后不依赖任何在线服务。
+
+## 质量
+
+每个技能都经过结构检查（SkillSpec L3）、安全扫描和重复检测，并在 CI 中强制执行。涉及法律、税务、劳动的技能会给出明确的免责声明，并指向应当咨询的机构。
+
+## 参与贡献
+
+欢迎用中文提 Issue 和 PR：
+- 如果某个技能在中国的场景下不准确，请告诉我们
+- 希望增加哪些技能
+- 帮助翻译或审校翻译
+
+参见 [CONTRIBUTING.md](CONTRIBUTING.md)。项目地址：https://github.com/mohitagw15856/pm-claude-skills
+
+## 协议
+
+MIT。

package/bin/cli.mjs

@@ -8,11 +8,12 @@
 //   npx pm-claude-skills list
 //
 // Flags for `add`:
-//   --agent <name>   claude | hermes | codex | openclaw | cursor   (required)
+//   --agent <name>   see `list` (required)
+//   --bundle <a,b>   only the skills in these bundles (e.g. pm-china-work,pm-cv)
 //   --target <path>  override the default install directory
 //   --link           symlink instead of copy (native agents; falls back to copy)
 //   --dry-run        print what would happen without writing
-import { readdirSync, existsSync, mkdirSync, rmSync, cpSync, symlinkSync, copyFileSync, statSync, readFileSync } from 'node:fs';
+import { readdirSync, existsSync, mkdirSync, rmSync, cpSync, symlinkSync, copyFileSync, statSync, readFileSync, writeFileSync } from 'node:fs';
 import { join, dirname, basename, resolve } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { execFileSync } from 'node:child_process';
@@ -28,6 +29,34 @@ const VERSION = (() => {
 const NATIVE = new Set(['claude', 'hermes', 'codex', 'openclaw']);
 // Rule-file agents install generated files from exports/<agent> (ext per agent).
 const RULEFILE = { cursor: '.mdc', windsurf: '.md', aider: '.md', kilocode: '.md' };
+// Generated rule-file agents: rule files are written at install time from skills/,
+// so the package does not carry thousands of near-identical files per tool.
+// Formats follow each tool's documented rule frontmatter (checked 2026-10-04).
+const yamlString = (s) => JSON.stringify(String(s));
+const GENERATED = {
+  trae: {
+    dir: ['.trae', 'rules'],
+    note: 'Trae applies each rule when its description matches the task (apply intelligently).',
+    render: (d, body) => `---\ndescription: ${yamlString(d)}\nalwaysApply: false\n---\n\n${body}\n`,
+  },
+  qoder: {
+    dir: ['.qoder', 'rules'],
+    note: 'Qoder applies each rule by model decision, from its description.',
+    render: (d, body) => `---\ntrigger: model_decision\ndescription: ${yamlString(d)}\n---\n\n${body}\n`,
+  },
+  lingma: {
+    dir: ['.lingma', 'rules'],
+    maxChars: 10000,
+    note: 'Lingma applies each rule by model decision. It truncates any rule file over 10,000 characters.',
+    render: (d, body) => `---\ntrigger: model_decision\ndescription: ${yamlString(d)}\n---\n\n${body}\n`,
+  },
+  codebuddy: {
+    dir: ['.codebuddy', 'rules'],
+    note: 'CodeBuddy loads each rule on demand when its description is relevant.',
+    render: (d, body) => `---\ndescription: ${yamlString(d)}\nalwaysApply: false\nenabled: true\n---\n\n${body}\n`,
+  },
+};
+const AGENTS = [...NATIVE, ...Object.keys(RULEFILE), ...Object.keys(GENERATED)];
 const defaultTarget = (agent) => ({
   claude: join(homedir(), '.claude', 'skills'),
   hermes: join(homedir(), '.hermes', 'skills'),
@@ -37,8 +66,33 @@ const defaultTarget = (agent) => ({
   windsurf: join(process.cwd(), '.windsurf', 'rules'),
   aider: join(process.cwd(), '.aider', 'skills'),
   kilocode: join(process.cwd(), '.kilocode', 'rules'),
+  ...Object.fromEntries(Object.entries(GENERATED).map(([k, g]) => [k, join(process.cwd(), ...g.dir)])),
 }[agent]);
 
+// Split a SKILL.md into its description and body (CRLF-safe).
+function splitSkill(text) {
+  const m = text.match(/^---\r?\n([\s\S]*?)\r?\n---\r?\n?/);
+  if (!m) return { description: '', body: text.trim() };
+  const d = m[1].split(/\r?\n/).map((l) => l.match(/^description:\s*(.*)$/)).find(Boolean);
+  const description = d ? d[1].trim().replace(/^"([\s\S]*)"$/, '$1').replace(/^'([\s\S]*)'$/, '$1') : '';
+  return { description, body: text.slice(m[0].length).trim() };
+}
+
+// --bundle a,b → the set of skill names in those bundles, or null for no filter.
+function bundleFilter(value) {
+  if (value === undefined || value === null) return null;
+  const names = String(value).split(',').map((s) => s.trim()).filter(Boolean);
+  if (!names.length) { console.error('Error: --bundle needs at least one bundle name, e.g. --bundle pm-china-work'); process.exit(2); }
+  const allowed = new Set();
+  for (const b of names) {
+    if (!/^[a-z0-9]+(-[a-z0-9]+)*$/.test(b)) { console.error(`Error: "${b}" is not a bundle name.`); process.exit(2); }
+    const dir = join(PKG_ROOT, 'plugins', b, 'skills');
+    if (!existsSync(dir)) { console.error(`Error: no bundle called "${b}". See the bundles in plugins/.`); process.exit(2); }
+    for (const s of readdirSync(dir)) if (existsSync(join(dir, s, 'SKILL.md'))) allowed.add(s);
+  }
+  return allowed;
+}
+
 function parse(argv) {
   const out = { _: [] };
   for (let i = 0; i < argv.length; i++) {
@@ -166,10 +220,11 @@ function placeDir(src, dest, { link, dryRun }) {
 
 function add(opts) {
   const agent = opts.agent;
-  if (!agent || !(NATIVE.has(agent) || agent in RULEFILE)) {
-    console.error(`Error: --agent must be one of: claude, hermes, codex, openclaw, cursor, windsurf, aider, kilocode.`);
+  if (!agent || !AGENTS.includes(agent)) {
+    console.error(`Error: --agent must be one of: ${AGENTS.join(', ')}.`);
     process.exit(2);
   }
+  const only = bundleFilter(opts.bundle);
   const skillsDir = join(PKG_ROOT, 'skills');
   if (!existsSync(skillsDir)) { console.error(`Error: bundled skills/ not found at ${skillsDir}.`); process.exit(1); }
   const target = resolve(opts.target || defaultTarget(agent));
@@ -186,12 +241,31 @@ function add(opts) {
   console.log(`${opts.dryRun ? '[dry-run] ' : ''}Installing for '${agent}' into ${target}`);
   if (!opts.dryRun) mkdirSync(target, { recursive: true });
 
-  if (agent in RULEFILE) {
+  if (agent in GENERATED) {
+    const gen = GENERATED[agent];
+    const tooLong = [];
+    for (const name of readdirSync(skillsDir).sort()) {
+      const src = join(skillsDir, name, 'SKILL.md');
+      if (!existsSync(src)) continue;
+      if (only && !only.has(name)) continue;
+      const raw = readFileSync(src, 'utf8');
+      if (/^deprecated:/m.test((raw.match(/^---\r?\n([\s\S]*?)\r?\n---/) || [, ''])[1])) continue;
+      const { description, body } = splitSkill(raw);
+      const out = gen.render(description, body);
+      if (gen.maxChars && out.length > gen.maxChars) tooLong.push(name);
+      const dest = join(target, `${name}.md`);
+      if (opts.dryRun) console.log(`  would write ${name}.md -> ${dest}`);
+      else writeFileSync(dest, out);
+      count++;
+    }
+    if (tooLong.length) console.log(`  note: ${tooLong.length} rule file(s) exceed ${gen.maxChars.toLocaleString('en')} characters and will be truncated by ${agent}: ${tooLong.slice(0, 5).join(', ')}${tooLong.length > 5 ? ', …' : ''}`);
+  } else if (agent in RULEFILE) {
     const ext = RULEFILE[agent];
     const exportDir = join(PKG_ROOT, 'exports', agent);
     if (!existsSync(exportDir)) { console.error(`Error: ${exportDir} missing.`); process.exit(1); }
     for (const f of listFiles(exportDir, ext).sort()) {
       if (basename(f) === 'README.md') continue;   // skip the generated index
+      if (only && !only.has(basename(f, ext))) continue;
       const dest = join(target, basename(f));
       if (opts.dryRun) console.log(`  would install ${basename(f)} -> ${dest}`);
       else copyFileSync(f, dest);
@@ -202,6 +276,7 @@ function add(opts) {
     for (const name of readdirSync(skillsDir)) {
       const src = join(skillsDir, name);
       if (!existsSync(join(src, 'SKILL.md'))) continue;
+      if (only && !only.has(name)) continue;
       placeDir(src, join(target, name), opts);
       count++;
     }
@@ -251,6 +326,7 @@ function add(opts) {
       windsurf: `Windsurf will pick up the rules in ${target} on its next session.`,
       aider: `Load any of them with:  aider --read ${join(target, '<skill>.md')}`,
       kilocode: `Kilo Code will pick up the rules in ${target} on its next session.`,
+      ...Object.fromEntries(Object.entries(GENERATED).map(([k, g]) => [k, `${g.note} Rules written to ${target}.`])),
     }[agent] || `Restart ${agent} — it auto-discovers SKILL.md skills in ${target} by their description.`;
     console.log(note);
     console.log(`\n${STAR}`);
@@ -260,12 +336,14 @@ function add(opts) {
 function list() {
   console.log('Supported agents and default targets:\n');
   // Derive from the registries above so this can't drift from what `add` accepts.
-  for (const a of [...NATIVE, ...Object.keys(RULEFILE)]) {
+  for (const a of AGENTS) {
     console.log(`  ${a.padEnd(9)} ${defaultTarget(a)}`);
   }
   console.log('\nNative SKILL.md agents: claude, hermes, codex, openclaw (install skill folders).');
   console.log('Claude also gets subagents + slash commands. Cursor / Windsurf / Kilo Code install');
   console.log('rule files; Aider installs conventions you load with "aider --read".');
+  console.log('Trae, Qoder, Lingma (通义灵码) and CodeBuddy get rule files generated at install time.');
+  console.log('Add --bundle pm-china-work,pm-cv to install only some bundles.');
   console.log(`\n${STAR}`);
 }
 
@@ -274,7 +352,14 @@ function list() {
 // `find` tokenizes a task, drops stopwords, and RANKS every skill by term overlap
 // against title+description, nudged by tier and (existing) eval score. No API/network.
 const FIND_STOP = new Set(('a an the of to in on or and for with your you i we my our need want help me please how do can could make write create build draft produce prepare prep get set run use using when asked into that this from each will able about more also not no is are be as at any one it its their them they then over same first start new mine give me').split(/\s+/));
-const findTokens = (s) => (String(s).toLowerCase().match(/[a-z0-9]+/g) || []).filter((w) => w.length > 2 && !FIND_STOP.has(w));
+const FIND_ZH_STOP = new Set(['帮我', '我写', '写一', '一份', '一个', '一下', '我的', '怎么', '什么', '可以', '需要', '如何', '请帮', '给我', '这个', '我们']);
+const findTokens = (s) => {
+  const latin = (String(s).toLowerCase().match(/[a-z0-9]+/g) || []).filter((w) => w.length > 2 && !FIND_STOP.has(w));
+  // Chinese has no spaces: match it as two-character pieces.
+  const zh = [];
+  for (const run of String(s).match(/[\u4e00-\u9fff]{2,}/g) || []) for (let i = 0; i < run.length - 1; i++) { const bi = run.slice(i, i + 2); if (!FIND_ZH_STOP.has(bi)) zh.push(bi); }
+  return [...latin, ...zh];
+};
 // Present the eval field honestly — a real measured score or an explicit "no claim",
 // never an invented number. Mirrors the badge shown on the web catalog.
 function evalBadge(ev) {
@@ -302,7 +387,7 @@ function find(opts) {
   const ql = query.toLowerCase();
   const scored = catalogForFind().map((s) => {
     const titleSet = new Set(findTokens(`${s.title || s.name} ${s.name}`));
-    const hset = new Set([...titleSet, ...findTokens(s.description || '')]);
+    const hset = new Set([...titleSet, ...findTokens(`${s.description || ''} ${s.descriptionZh || ''}`)]);
     let overlap = 0, titleHits = 0;
     for (const t of qset) { if (hset.has(t)) overlap++; if (titleSet.has(t)) titleHits++; }
     const phrase = (s.description || '').toLowerCase().includes(ql) ? 2 : 0;
@@ -371,7 +456,7 @@ const HELP = `pm-claude-skills — install professional Agent Skills into any AI
 (This is a CLI, not a library — you don't need \`npm install\`; \`npx …\` always runs the latest.)
 
 Usage:
-  npx pm-claude-skills add --agent <claude|hermes|codex|openclaw|cursor|windsurf|aider> [--target <path>] [--link] [--dry-run]
+  npx pm-claude-skills add --agent <${AGENTS.join('|')}> [--bundle <a,b>] [--target <path>] [--link] [--dry-run]
   npx pm-claude-skills run <skill> [--text "…" | --input <file>] [--model <m>] [--out <file>]
   npx pm-claude-skills find "<describe your task>" [--json] [--limit <n>]   # ranked task→skill router (start here)
   npx pm-claude-skills search [query…] [--json] [--limit <n>]
@@ -397,6 +482,8 @@ Examples:
   npx pm-claude-skills add --agent cursor     # .mdc rules into ./.cursor/rules
   npx pm-claude-skills add --agent windsurf   # .md rules into ./.windsurf/rules
   npx pm-claude-skills add --agent codex --link
+  npx pm-claude-skills add --agent trae --bundle pm-china-work,pm-cv   # Trae rules for two bundles
+  npx pm-claude-skills add --agent qoder      # Qoder / Lingma: --agent lingma
 
   npx pm-claude-skills find "prep a QBR for an at-risk account"   # describe the task, get ranked skills + a measured/unmeasured badge
   npx pm-claude-skills search board            # exact keyword filter by name/description

package/exports/README.md

@@ -8,7 +8,7 @@ by hand; edit the source skill and run:
 node scripts/build-exports.mjs
 ```
 
-Currently exporting **1176 skills** to:
+Currently exporting **1235 skills** to:
 
 - **ChatGPT — Custom GPT instructions** → `exports/chatgpt/`
 - **Google Gemini — Gem instructions** → `exports/gemini/`