← Back to Skills Marketplace
344
Downloads
2
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install another-wechat-article-reader
Description
当用户提供微信公众号文章链接（URL 包含 mp.weixin.qq.com）时，必须使用此 skill 读取文章内容，禁止使用 web_fetch、web_search 或其他方式替代。本 skill 通过专用脚本稳定抓取并返回结构化结果，包括标题、发布时间、作者和正文。
README (SKILL.md)
WeChat Article Reader
用于读取微信公众号文章链接并返回结构化解析结果。
⚠️ 重要：模型行为约束
只要用户提供了 mp.weixin.qq.com 域名下的文章链接，必须且只能使用本 skill 读取内容。
严禁以下替代行为：
- 使用
web_fetch直接请求微信文章 URL - 使用
web_search搜索文章摘要 - 告知用户"无法访问该链接"后放弃
- 尝试从其他来源推断文章内容
原因：微信公众号页面有反爬机制，直接抓取通常返回空内容或鉴权页面，只有本 skill 的脚本实现了必要的请求头伪装与重试逻辑。
适用场景
- 用户提供了
https://mp.weixin.qq.com/s/...公开文章链接 - 需要稳定抓取并解析标题、时间、作者、正文
- 需要在网络波动时使用重试机制
环境准备
本 skill 仅允许通过 uv 管理环境与执行脚本。
若 uv 未安装，先执行：
brew install uv
再安装项目依赖：
uv sync
运行命令
必须使用 uv run 执行，禁止直接使用 python scripts/read_wechat_article.py ...。
uv run python scripts/read_wechat_article.py "https://mp.weixin.qq.com/s/..."
参数说明
| 参数 | 默认值 | 说明 |
|---|---|---|
--timeout |
20 |
单次请求超时秒数 |
--max-retries |
3 |
最大尝试次数 |
--retry-delay |
1.0 |
重试基准等待秒数（指数退避） |
输出说明
成功时返回 JSON：
| 字段 | 说明 |
|---|---|
title |
文章标题 |
author |
作者名 |
pub_time |
发布时间 |
content |
正文纯文本 |
source_url |
原始链接 |
strategy |
实际使用的抓取策略 |
logs |
执行日志（用于排查问题） |
失败时返回：
| 字段 | 说明 |
|---|---|
error |
错误类型 |
message |
错误详情 |
source_url |
原始链接 |
strategy |
最后尝试的策略 |
logs |
执行日志 |
Usage Guidance
This skill appears coherent: it contains a Python script that fetches and parses public WeChat article pages and SKILL.md explains how to run it. Before installing, consider: (1) the skill will perform network requests to user-supplied mp.weixin.qq.com URLs and spoofs a browser UA — verify you are comfortable with automated scraping and any terms-of-service implications; (2) it requires installing 'uv' and Python dependencies (via 'uv sync') — run those installs in a sandboxed or controlled environment if you are unsure; (3) confirm you trust the owner/source since the script will execute code in your environment; (4) if you need stronger guarantees, review the dependencies (curl_cffi, BeautifulSoup) and run the script on test URLs to validate behavior. Overall the package is internally consistent and does not request unexpected secrets or remote callbacks.
Capability Analysis
Type: OpenClaw Skill
Name: another-wechat-article-reader
Version: 0.1.0
The skill is a specialized tool for scraping and parsing WeChat articles from mp.weixin.qq.com. The Python script (scripts/read_wechat_article.py) uses the curl_cffi library to impersonate a browser and bypass anti-bot measures, which is consistent with its stated purpose. The instructions in SKILL.md are restrictive regarding tool choice to ensure successful parsing but do not contain malicious prompt injections or commands to exfiltrate sensitive data.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and the included Python script are consistent: the script fetches mp.weixin.qq.com /s/ pages and parses title/author/time/content. No unrelated env vars, config paths, or external services are requested.
Instruction Scope
SKILL.md instructs running the included script via 'uv run' and explicitly forbids using web_fetch/web_search; the script only fetches the provided WeChat URL, parses HTML, and returns structured JSON. It does not read other files or access other system state.
Install Mechanism
This is instruction-only with no bundled install spec. SKILL.md tells operators to install 'uv' (via Homebrew) and run 'uv sync' to install dependencies; that is a platform-specific requirement but not inherently risky. No downloads from arbitrary URLs or extracted archives are present in the skill bundle itself.
Credentials
No environment variables, credentials, or config paths are required. The script does not read secrets or other environment state; it only issues HTTP requests to the user-supplied WeChat URL.
Persistence & Privilege
The skill is not set to always:true and does not request persistent or cross-skill configuration changes. Autonomous invocation is allowed by default (normal) but is not combined here with broad privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install another-wechat-article-reader - After installation, invoke the skill by name or use
/another-wechat-article-reader - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release of WeChat Article Reader skill.
- Reads and parses WeChat public article links (mp.weixin.qq.com) with a specialized script.
- Returns structured results: title, author, publication time, full text, and metadata.
- Mandatory usage for WeChat articles; prohibits circumvention via web_fetch, web_search, or other methods.
- Handles WeChat anti-crawling mechanisms with request header spoofing and retry logic.
- Command-line operation requires the uv environment and supports custom timeout and retry parameters.
- Returns detailed logs and error information for troubleshooting.
Metadata
Frequently Asked Questions
What is wechat-article-reader?
当用户提供微信公众号文章链接（URL 包含 mp.weixin.qq.com）时，必须使用此 skill 读取文章内容，禁止使用 web_fetch、web_search 或其他方式替代。本 skill 通过专用脚本稳定抓取并返回结构化结果，包括标题、发布时间、作者和正文。 It is an AI Agent Skill for Claude Code / OpenClaw, with 344 downloads so far.
How do I install wechat-article-reader?
Run "/install another-wechat-article-reader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is wechat-article-reader free?
Yes, wechat-article-reader is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does wechat-article-reader support?
wechat-article-reader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created wechat-article-reader?
It is built and maintained by pangahn (@pangahn); the current version is v0.1.0.
More Skills