Wechat Articles Skill
v1.0.0抓取微信公众号文章并转换为Markdown格式。当用户提供微信文章链接（mp.weixin.qq.com）或要求抓取/保存/下载公众号文章时触发。
⭐ 0· 131·0 current·0 all-time
by@hunkguo
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the code and instructions: the included Python script uses Playwright + BeautifulSoup to fetch mp.weixin.qq.com pages, extract selectors (#activity-name, #js_content, #js_name), convert HTML to Markdown and save to disk. Requiring a headless browser and HTML parsing libraries is proportionate to the stated purpose.
Instruction Scope
SKILL.md instructs the agent to open WeChat article URLs with Playwright and save Markdown to disk — the code follows that. The only notable mismatch: the documentation and README say images will be downloaded to an images/ folder, but the script creates an images/ directory and inserts image links/placeholders without actually performing HTTP downloads of image files. Aside from that implementation gap, the instructions do not ask the agent to read unrelated files, env vars, or send data to any external endpoints other than the target article URLs.
Install Mechanism
There is no automated install spec (instruction-only + included script). The README documents manual installation via pip and playwright install (official packages). Playwright/Chromium is a heavy dependency but expected for headless browser scraping. No downloads from unknown URLs or extract steps in the skill package itself.
Credentials
The skill requires no environment variables, credentials, or config paths. The script runs locally and only needs network access to the target WeChat pages. No unrelated credentials or secrets are requested.
Persistence & Privilege
Skill is not always-enabled and does not request elevated privileges or modify other skills. It writes output files to a user-specified output directory (expected behavior).
Assessment
This skill and its script appear coherent and focused on scraping WeChat articles, but check these before installing: 1) You must install Python dependencies (playwright and beautifulsoup4) and run `playwright install chromium` as documented; Playwright will download Chromium (large binary). 2) The script saves Markdown to disk and creates an images/ folder — it currently inserts image links/placeholders but does not actually download image files despite README/SKILL.md claiming image download; if you need images, inspect/modify the script to fetch and save them. 3) The SKILL.md example command uses a hard-coded OpenClaw path — ensure the script path matches your installation. 4) Scraping may violate content terms or copyright for some articles (including paywalled content); use in compliance with law and site terms. 5) Run the skill in a controlled environment (or sandbox) if you are concerned about giving it network access. Overall: functionality is proportionate to its description and no covert data exfiltration or unrelated credential requests were found.Like a lobster shell, security has layers — review code before you run it.
latestvk97fkv58qj4tqk21g5zfzztt9x8376xz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.