imjszhang/js-eyes/js-wechat-ops-skill

Claude Code and agent skill by imjszhang/js-eyes

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

微信公众号内容读取 skill，基于 JS-Eyes 浏览器自动化获取文章标题、作者、正文、封面和图片列表。

Install

npx vskill@latest install imjszhang/js-eyes/js-wechat-ops-skill

SKILL.md

js-wechat-ops-skill

面向微信公众号文章详情读取的 skill。首版聚焦单篇文章，不做搜索、历史文章列表和评论区。

前置条件

  1. Node.js 22+、JS Eyes 2.8.5+，且 JS-Eyes Server 已运行
  2. 浏览器已安装 JS-Eyes 扩展并连接到服务器
  3. 浏览器可正常访问微信公众号文章页面
  4. 宿主设置 security.allowRawEval: true；JS Eyes 2.5+ 会同步到扩展，扩展侧显式 false 仍可强制关闭
  5. Chrome 要求 135+；Chrome 138+ 还需开启浏览器控制的 Allow User Scripts

公开文章通常无需登录；受限或失效文章取决于浏览器已有会话，本 Skill 不执行登录自动化。

提供的 AI 工具

工具说明
wechat_get_article读取微信公众号文章详情，返回标题、作者、摘要、正文、封面图和图片列表

CLI

bash
node skills/js-wechat-ops-skill/index.js article "https://mp.weixin.qq.com/s/xxxx" --pretty

编程 API

javascript
const { BrowserAutomation } = require('./lib/js-eyes-client');
const { getArticle } = require('./lib/api');
const browser = new BrowserAutomation('ws://localhost:18080');
const result = await getArticle(browser, 'https://mp.weixin.qq.com/s/xxxx');

Recording

js-wechat-ops-skill 现已接入统一的 skill recording 底座，支持调用历史、结果缓存和调试记录。

  • 默认记录模式跟随 js-eyes 全局配置中的 recording.mode
  • CLI 可覆盖：
  • --recording-mode off|history|standard|debug
  • --debug-recording
  • --no-cache
  • --recording-base-dir /absolute/path
  • --run-id custom-id

默认按技能分目录落盘到 ~/.js-eyes/skill-records/js-wechat-ops-skill/，其中包含：

  • history/：按月滚动的调用历史 jsonl
  • cache/article：文章结构化缓存
  • debug/：调试模式下的页面步骤、DOM 统计和结果快照

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
43
Repository forks
7
7-day trend score
19

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 21 Sep 2026, a month ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/imjszhang/js-eyes/js-wechat-ops-skill/badge)](https://verified-skill.com/skills/imjszhang/js-eyes/js-wechat-ops-skill)

Something wrong with this skill or its page? Tell us.