Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

weread-omni Skill

Repository ↗

by teng-lin★ 7151 skills

Install

What it does

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。

  • Connects Instruction files the AI reads, with steps that call an outside service
  • Account or key Some steps need a key for WEREAD_ACCESS_TOKEN, WEREAD_REFRESH_TOKEN (per the README)
  • Category Coding
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/teng-lin-weread-omni.svg)](https://mcp.popnx.com/en/skills/teng-lin-weread-omni)

Use together with

MCP servers that connect the AI to services for the same work

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

by morlutoWidely used↓ 388.7K/wk★ 470.2KUpdated 8 days ago

MCP · Connects a serviceRuns on your computer

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

by fallow-rsWidely used↓ 2.4M/wk★ 5.4KUpdated yesterday

MCP · Connects a serviceRuns on your computer

Desktop Commander

MCP server for terminal commands, file operations, and process management

by wonderwhy-erWidely used↓ 740.3K/wk★ 10.4KUpdated 2 days ago

MCP · Connects a serviceRuns on your computer

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
weread-omni
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
Makerteng-linmorlutomultica-aiGraphify-Labsharry0703
Skills11111
GitHub stars715470,165234,528150,695144,727
Last code changeNov 16, 2026Nov 20, 2026Apr 20, 2026Nov 20, 2026Nov 19, 2026
LicenseMITMIT–Apache-2.0MIT

1 skills (instruction sets) by teng-lin that an AI reads and follows · not an MCP server

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

Claude CodeCodex

From the maker’s README and the folders in the repo

Install

Is it safe?

  • Who made it

    GitHub account teng-lin (person), 15 years old

  • Use and upkeep

    ★ 715 stars · code last changed Nov 16, 2026

  • Any scripts?

    No, plain text files the AI reads and follows

  • Uses the internet?

    No scripts, so it does not go online by itself

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit fe86090 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

First: which AI do you use?

Pick your app and this page shows only how to install it there

Option 1Upload to claude.ai (web and app)

Uploading to claude.ai would fail: the description is over 200 characters (475). Use "Let the AI install it" instead

Option 1Let Claude Code install it

Copy this sentence and paste it into a Claude Code chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Restart Claude Code, then type /weread or ask for a matching task and Claude picks it up

Checked against official docs Nov 12, 2026 · Source: code.claude.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

The maker’s recommended way

Install Node.js (if you don’t have it)

Already installed? Check first · Open Terminal, type this command and press Enter

node -v
  • A version number such as v26.13.1 = installed, skip this step
  • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
How to open Terminal

Mac: press ⌘ + Space, type Terminal, press Enter

Windows: open Start, type Windows PowerShell, then Open

Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed

Open the Node.js download page ↗

When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v

Install once; it works for everything that needs Node.js

Checking the commands · copy buttons appear once they pass

Copied from the maker’s README; it downloads and runs the maker’s code

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.claude/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Claude Code, then type /weread or ask for a matching task and Claude picks it up

Skills you install yourself work in the ChatGPT desktop app, Codex CLI and the Codex IDE extension · ChatGPT on the web and mobile cannot use skills you install yourself, only skills that come with a plugin from the directory

ChatGPT desktop app

The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills

Option 1Let ChatGPT install it

Open Codex in the ChatGPT desktop app and paste this sentence into the chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2Put the folder there yourself

Put the weread folder at ~/.agents/skills/weread

~ is your home folder ($HOME)

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

After installing

  • ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
  • To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
  • Codex picks up newly installed skills by itself; if one does not show up, restart Codex

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

ChatGPT on the web and mobile

Skills you install yourself do not work here; only skills that come with a plugin from the directory

To use this skill with ChatGPT, use the ChatGPT desktop app as above

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

Option 1Let Codex install it

Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Codex, then ask for a matching task; Codex lists the skill

Option 1Let Cursor install it

Copy this sentence and paste it into a Cursor chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

In Cursor’s Agent chat, type / and pick weread

Checked against official docs Nov 12, 2026 · Source: cursor.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.cursor/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. In Cursor’s Agent chat, type / and pick weread

Option 1Let the AI install it

For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.

View on GitHub ↗

Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026

View the original SKILL.md

The text below comes from the maker’s repo, not from PopNx MCP

Showing the first 8,000 characters · Open the full file on GitHub

---
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

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
715
Maker
teng-lin
License
MIT
Last code change
Nov 16, 2026
SKILL.md files in the repo (including translated copies and templates)
1
Topics
agent, sdk, skills, typescript, weread