REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
微信读书(WeRead)增强工具包:集成 Agent、API、SDK、CLI 与插件,内置 40 项操作;支持阅读微信公众号、书架与笔记读写、书籍导入及 AI 权限。
作者提供的原文
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/teng-lin-weread-omni)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 weread-omni | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | teng-lin | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 715 | 470,165 | 234,528 | 150,695 | 144,727 |
| 最近代码更新 | 2026年11月16日 | 2026年11月20日 | 2026年4月20日 | 2026年11月20日 | 2026年11月19日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
teng-lin 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodex
依据开发者 README 和 repo 中的文件夹
GitHub 账号 teng-lin(个人),已创建 15 年
★ 715 星 · 代码最近更新 2026年11月16日
没有,都是纯文本文件,由 AI 阅读后照做
没有脚本,所以不会自己联网
没有发现 hook 或写入电脑设置的操作
根据仓库 commit fe86090 中的文件自动检查(只读取文件,没有运行任何内容)。这不是安全保证,请自己阅读后再决定
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
无法上传到 claude.ai,因为描述超过 200 个字符(475 个字符)。请改用"让 AI 帮你安装"
复制这句话,粘贴到 Claude Code 的对话中
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
重新打开 Claude Code,输入 /weread,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
正在检查命令 · 通过后才会显示复制按钮
摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
把 weread 文件夹放到 ~/.agents/skills/weread
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
在 Cursor 的 Agent 聊天中输入 / 并选择 weread
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · 复制这句话,粘贴到应用的对话中
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: weread
description: Search WeRead, inspect books and reading data, manage the bookshelf, public-account subscriptions and reviews, read, write, edit, and batch-sync highlights and notes, build private article feeds and archives, ask WeRead AI, or import a personal book through the installed `weread-omni` JSON CLI. Use for requests involving 微信读书, WeChat Reading, a user's WeRead shelf, public accounts, articles, highlights, notes, reviews, reading statistics, recommendations, or book lookup.
---
# WeRead
Use the installed CLI as the only interface. Always pass `--json`, parse
successful stdout as JSON, and summarize the result for the user. On a non-zero
exit, parse the JSON error from stderr. Never expose credentials or paste raw
tokens.
## Batch annotations and rate limits
For multiple annotations, an entire chapter, updates from a source document,
or a resumed run, read [the batch annotation workflow](references/batch-annotations.md)
before the first write. It defines source completeness, range selection,
deduplication, durable receipts, recovery, and exhaustive acceptance checks.
Serialize all remote CLI calls for the selected account, including searches,
reads, writes, and verification. Wait at least **2 seconds after each call
finishes** before starting the next; use one queue, without parallel workers.
This is a conservative operating interval validated in a 263-note run, not an
official server quota; one CLI command can make several HTTP requests.
On HTTP 429 or an explicit frequency-limit response, stop the write queue and
follow the batch workflow's recovery table. Never automatically retry a write
whose outcome is uncertain. Save its intent and response before continuing.
## Account selection
Choose exactly one account for the session and preserve it through every CLI
call. Use the alias supplied by the user or operator. If none was supplied,
`weread-omni accounts --json` must show exactly one configured account. In the
examples below, `$ACCOUNT` means that alias. Do not switch accounts after a
failure.
Writes are permitted unless the operator has set `WEREAD_READONLY`. A refused
write fails with `disabled by WEREAD_READONLY`; report that limit as policy, and
never unset it or retry against another account on the user's behalf.
## Session preflight
Before the first authenticated operation, run:
```bash
weread-omni --account "$ACCOUNT" doctor --json
```
Proceed only when the result has `ok: true`, `cli.package:
"weread-omni"`, and `auth.status: "authenticated"`. On an authentication
error, require the same `cli.package` in the JSON error before following its
`hint`. Do not start QR login without user confirmation. Follow the returned
account-specific hint; malformed or unreadable state must be corrected or
removed first. Retry `doctor` once with the same account. If it returns
non-JSON or names another
package, stop and report the path from `command -v weread-omni`; do not guess
another command.
## Read workflow
Start with the narrowest read that answers the request. Preserve `bookId`
values from search or shelf results for follow-up commands.
Book metadata, chapter listings, and downloaded public-account articles are
served from a local library after the first read, so a repeated read can return
a stored copy rather than a fresh one. If a result looks out of date, say so and
offer `--refresh` to refetch and replace it; `--no-library` skips the library
entirely for one command. Never present stored content as freshly fetched.
```bash
weread-omni --account "$ACCOUNT" public-accounts read-article 'https://mp.weixin.qq.com/s/ARTICLE' --json
weread-omni --account "$ACCOUNT" search books "三体" --json
weread-omni --account "$ACCOUNT" search books "刘慈欣" --scope 6 --json
weread-omni --account "$ACCOUNT" book info BOOK_ID --json
weread-omni --account "$ACCOUNT" book search BOOK_ID "exact original text" --chapter-uid CHAPTER_UID --json
weread-omni --account "$ACCOUNT" shelf sync --count 20 --json
weread-omni --account "$ACCOUNT" public-accounts subscriptions --count 20 --json
weread-omni --account "$ACCOUNT" public-accounts articles MP_WXS_123 --count 20 --json
weread-omni --account "$ACCOUNT" public-accounts resolve-article 'https://mp.weixin.qq.com/s/ARTICLE' --json
weread-omni --account "$ACCOUNT" notes notebooks --count 10 --json
weread-omni --account "$ACCOUNT" notes recent --count 10 --json
weread-omni --account "$ACCOUNT" notes mine BOOK_ID --count 10 --json
weread-omni --account "$ACCOUNT" notes underlines BOOK_ID CHAPTER_UID --json
weread-omni --account "$ACCOUNT" notes read-reviews BOOK_ID CHAPTER_UID --reviews '[{"range":"393-401","count":10}]' --json
weread-omni --account "$ACCOUNT" review single REVIEW_ID --json
weread-omni --account "$ACCOUNT" read-data detail --mode weekly --json
weread-omni --account "$ACCOUNT" discover recommend --count 10 --json
weread-omni --account "$ACCOUNT" ai ask-book BOOK_ID "Summarize the central argument" --json
```
`search books` defaults to `--scope 10` for ebooks. Choose the scope from the
request: `0` all, `10` ebooks, `16` web fiction, `14` audio, `6` authors, `12`
full text, `13` booklists, `2` public accounts, or `4` articles. Do not use
scope 10 for every intent. When `hasMore` is 1, pass the last result's
`searchIdx` as `--max-idx`; a page is not the complete result set.
Use only the cursor that belongs to the command:
- For `shelf sync`, pass `nextOffset` as `--offset`.
- For `public-accounts articles`, omit `--offset` on the first call, or pass a
previous `synckey` as `--synckey` for a delta refresh. Never combine the two.
If the response has `nextOffset`, pass it as `--offset`; stop when it is absent.
- For `notes notebooks`, pass the final book's `sort` as `--last-sort`.
- `notes recent` is a bounded account-wide snapshot; it has no page cursor.
- For `notes best` and `review list`, add the returned item count to the
previous `--max-idx`.
- Use `synckey` only to refresh previously fetched data. It is not a page
cursor.
Preserve every upstream `hasMore` and cursor exactly; do not infer completion
from a short result or from a missing `hasMore`.
`shelf sync` returns a compact page by default. Use `--full` only when the user
needs exact upstream sync fields; it cannot be combined with `--count` or
`--offset`.
Use `book detail` for product images and other books by the same author or
rightsholder. It returns six entries per related catalog by default; use
`--count` (1-12) when a smaller result is enough. Use `book chapters` or
`book progress` for those specific views.
`book chapters` returns the table of contents, where each
entry carries the `chapterUid` that the notes and review commands use to address
a position in a book. Use `notes bookmarks`, `notes best`, or `notes underlines`
for those note types. To read thoughts under a popular highlight, take its
`chapterUid` and `range` from `notes best`, call `notes read-reviews`, then use
`review single` when the user wants one thought in full. Use `review list`,
`discover similar`, and `ai suggest` for reviews, related books, and suggested
questions.
For a supplied article URL, use `public-accounts read-article URL --json` directly;
no public-account search or subscription is needed. `resolve-article` only returns
an ID and `review single` may only contain metadata or an abstract.
Use the returned `markdown` or `contentHtml`, and cite `sourceUrl`. A cache hit is
marked `fromCache: true`, with `cachedAt` and a null `fetchedAt`. `status: readable`
does not independently establish completeness (`completeness: unverified`);
inspect the article structure and ending when completeness matters. `partial`
means only a preview was obtained. An unavailable body exits nonzero with JSON
diagnostics on stderr; never summarize its metadata as though it were the body.
For public-account discovery and subscription, follow this sequence:
1. Search with `weread-omni --account "$ACCOUNT" search books KEYWORD --scope 2 --json`.
2提问、分享技巧或报告无法使用。按“有帮助”数量排序。