Agent skill

Weixin Access

by qufei1993 in qufei1993/cc-weixin

Manage WeChat access control (pairing codes and allowlist). An agent skill from qufei1993/cc-weixin.

MITAuto-check passedProductivity & Automation

Install Weixin Access

skills CLI
$ npx skills add qufei1993/cc-weixin --skill weixin-access -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qufei1993/cc-weixin weixin-access --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qufei1993/cc-weixin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/weixin/skills/access .claude/skills/weixin-access && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
weixin-access
GitHub stars
154
Token cost
~372 tokens
SKILL.md length
181 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Manage WeChat access control (pairing codes and allowlist). An agent skill from qufei1993/cc-weixin.

  • Works in 4 steps: Load access config with loadAccessConfig() → Add the userId to allowFrom if not… → Save with saveAccessConfig() → …
  • Tasks that involve Messaging and chat bots
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Authorization and RBAC

What it does

Weixin Access is an agent skill from qufei1993/cc-weixin. Manage WeChat access control (pairing codes and allowlist)

Its SKILL.md is about 370 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Messaging and chat bots and Authorization and RBAC. It works with WeChat. The repository describes itself as: Connect WeChat to Claude Code via official iLink Bot API. Send and receive text, images, voice, and files between WeChat and your AI coding session. The licence is MIT.

When your agent uses it

  • Tasks that involve Messaging and chat bots
  • Tasks that involve Authorization and RBAC

Example prompts

  • “/weixin-access”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Load access config with loadAccessConfig()
  2. Add the userId to allowFrom if not already present
  3. Save with saveAccessConfig()
  4. Confirm the user was added

What it can do on your machine

Read from SKILL.md and the folder at commit 908773c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Weixin Access loads about 372 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 181 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~372

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from qufei1993/cc-weixin at commit 908773c, republished under its MIT licence (© qufei1993). 181 words, ~372 tokens.

Download SKILL.mdSave it as .claude/skills/weixin-access/SKILL.md (or your agent's skills folder).
name
weixin-access
description
Manage WeChat access control (pairing codes and allowlist)
user-invocable
true
argument-hint
<pair CODE | allow USER | remove USER | policy MODE | status>

WeChat Access Control

Manage who can send messages to your AI coding assistant via WeChat.

Instructions

Parse the command argument and perform the appropriate action:

pair <code>

Confirm a 6-digit pairing code. Call confirmPairing(code) from ./src/pairing.js.

  • If valid: display the confirmed user ID and confirm they've been added to the allowlist.
  • If invalid/expired: display an error.
allow <userId>

Manually add a user ID to the allowlist:

  1. Load access config with loadAccessConfig()
  2. Add the userId to allowFrom if not already present
  3. Save with saveAccessConfig()
  4. Confirm the user was added
remove <userId>

Remove a user ID from the allowlist:

  1. Load access config
  2. Remove the userId from allowFrom
  3. Save the config
  4. Confirm removal
policy <mode>

Set the access policy. Mode must be one of: pairing, allowlist, disabled.

  • pairing: New users get a pairing code, must be confirmed (default)
  • allowlist: Only pre-approved users can message (no new pairing codes)
  • disabled: Anyone can message (not recommended)
status

Display current access configuration:

  • Current policy
  • Number of allowed users
  • List of allowed user IDs

Import functions from ./src/pairing.js and ./src/accounts.js.

© qufei1993, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/weixin/skills/access of qufei1993/cc-weixin.

Open the folder on GitHubat commit 908773c

Compare with similar skills

Weixin Access next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Weixin Access compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Weixin Access this skillqufei1993/cc-weixin154—~372Automated safety check: PassMIT
SetupRich627/whatsapp-claude-plugin103—~1.4kAutomated safety check: NotesApache-2.0
Add WeChat Channelnanocoai/nanoclaw31k—~1.9kAutomated safety check: NotesMIT
Cloudbase Wechat IntegrationTencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~1.9kAutomated safety check: PassMIT
Minimal Web Baas DemoTencentCloudBase/CloudBase-AI-Toolkit1.1k1 repos~2.3kAutomated safety check: PassMIT
Miniprogram DevelopmentLeoYeAI/openclaw-master-skills2.2k1 repos~2kAutomated safety check: PassMIT

Similar skills

  • Setup

    Rich627/whatsapp-claude-plugin

    Interactive WhatsApp channel onboarding — guides through device linking, phone number config, and access control setup

    103 GitHub stars~1.4k tokensUpdated today
    Productivity & AutomationAuto-check: notes
  • Add WeChat Channel

    nanocoai/nanoclaw

    Adds a personal WeChat channel to a NanoClaw install through Tencent's iLink Bot API, with QR-code login and long polling instead of a public webhook.

    31k GitHub stars~1.9k tokensUpdated yesterday
    Productivity & AutomationAuto-check: notes
  • Cloudbase Wechat Integration

    TencentCloudBase/CloudBase-AI-Toolkit

    CloudBase WeChat integration guide for Mini Program WeChat Pay, Mini Program virtual payment (虚拟支付, wx.requestVirtualPayment), Official Account JSAPI Pay, Native QR-code Pay, Official Account OAuth…

    1.1k GitHub starsUsed in 2 repos~1.9k tokens
    Productivity & AutomationAuto-check passed
  • Minimal Web Baas Demo

    TencentCloudBase/CloudBase-AI-Toolkit

    Fast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS).

    1.1k GitHub starsUsed in 1 repo~2.3k tokens
    Productivity & AutomationAuto-check passed
  • Miniprogram Development

    LeoYeAI/openclaw-master-skills

    WeChat Mini Program development rules. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub starsUsed in 1 repo~2k tokens
    Productivity & AutomationAuto-check passed
  • Wechat Channel

    aAAaqwq/AGI-Super-Team

    微信 (WeChat) 与 OpenClaw 的双向集成通道。基于 Wechaty + PadLocal 实现微信消息的接收和发送,支持私聊、群聊、@提及检测、图片/文件传输。当需要通过微信与 AI 助手交互、接收微信消息触发 AI 响应、或从 OpenClaw 发送消息到微信时使用此技能。

    105 GitHub starsUsed in 1 repo~1.3k tokens
    Productivity & AutomationAuto-check: notes

More from qufei1993/cc-weixin

  • Weixin Configure

    qufei1993/cc-weixin

    Connect or disconnect your WeChat account via QR code scan. An agent skill from qufei1993/cc-weixin.

    154 GitHub stars~585 tokensUpdated 5 mo ago
    Auto-check passed

Works with

Questions about Weixin Access

What does Weixin Access do?

Manage WeChat access control (pairing codes and allowlist). An agent skill from qufei1993/cc-weixin. Weixin Access is an agent skill from qufei1993/cc-weixin.

When should I use Weixin Access?

Weixin Access fits situations like: tasks that involve Messaging and chat bots; tasks that involve Authorization and RBAC.

How do I install Weixin Access in Claude Code?

Run `npx skills add qufei1993/cc-weixin --skill weixin-access -a claude-code`. Or copy the skill folder (plugins/weixin/skills/access in qufei1993/cc-weixin) into .claude/skills/weixin-access in your project. Claude Code loads it when a task matches its description.

How do I install Weixin Access in Codex?

Run `npx skills add qufei1993/cc-weixin --skill weixin-access -a codex`. Or copy the skill folder (plugins/weixin/skills/access in qufei1993/cc-weixin) into .agents/skills/weixin-access in your project. Codex loads it when a task matches its description.

Can I use Weixin Access in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qufei1993/cc-weixin --skill weixin-access -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/weixin-access, .gemini/skills/weixin-access, .github/skills/weixin-access and .opencode/skills/weixin-access in your project.

What does Weixin Access need to run?

SKILL.md names no scripts, command-line tools or credentials: Weixin Access is instructions for the agent only.

Does Weixin Access access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Weixin Access safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Weixin Access use?

Weixin Access is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Weixin Access use?

About 372 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Weixin Access?

Skills that share tags, products or a category with Weixin Access: Setup (Rich627/whatsapp-claude-plugin, 103 stars), Add WeChat Channel (nanocoai/nanoclaw, 31k stars), Cloudbase Wechat Integration (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars) and Minimal Web Baas Demo (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Weixin Access?

qufei1993 (a GitHub user) maintains it in qufei1993/cc-weixin, which has 154 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on April 16, 2026.

Source: qufei1993/cc-weixin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.