ClawHub

Weixin Article Reader

v0.1.1

Extract the title, author, publish date, and full body text from Weixin official account article links on mp.weixin.qq.com. Use this skill when a user wants...

⭐ 0· 146·0 current·0 all-time
by@ricknote

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ricknote/weixin-article-reader.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Weixin Article Reader" (ricknote/weixin-article-reader) from ClawHub.
Skill page: https://clawhub.ai/ricknote/weixin-article-reader
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install weixin-article-reader

ClawHub CLI

Package manager switcher

npx clawhub@latest install weixin-article-reader
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description ask for extracting Weixin article fields and the bundle includes a small Python extractor that fetches mp.weixin.qq.com pages and parses title, author, publish date, and body — this matches expected capabilities.
✓
Instruction Scope
SKILL.md instructs running the bundled script against mp.weixin.qq.com URLs. The script only performs an HTTP GET to the provided URL and HTML parsing; it does not read unrelated files, environment variables, or send data to other endpoints.
✓
Install Mechanism
No install spec is present and the README/SKILL.md state the script uses only the standard library. Nothing is downloaded or written by an installer.
✓
Credentials
The skill requires no environment variables, no credentials, and does not access config paths. The script uses only the provided URL and makes an outbound request to that URL (proportionate to the task).
✓
Persistence & Privilege
always:false (default) and no system-wide modifications. agents/openai.yaml allows implicit invocation (normal platform behavior) but the skill does not request elevated or persistent privileges.
Assessment
This skill appears internally consistent and uses only standard Python to fetch and parse mp.weixin.qq.com article pages. Before installing, consider: (1) the script issues an outbound HTTP(S) request to the exact URL you provide — ensure you trust the URL and are comfortable with network access; (2) some Weixin pages may require cookies, JS, or be blocked, so extraction can fail or return empty content; (3) the agent is allowed to invoke the skill implicitly by default (platform normal), so if you want to avoid automatic retrievals, restrict invocation in your agent settings. If you need higher assurance, review the included script (scripts/extract_wechat_article.py) yourself; it contains no calls to external endpoints other than the target page and no credential handling.

Like a lobster shell, security has layers — review code before you run it.

contentvk97bmp684dvx2epva7ve0f99v183ydp5latestvk97bmp684dvx2epva7ve0f99v183ydp5wechatvk97bmp684dvx2epva7ve0f99v183ydp5
146downloads
0stars
2versions
Updated 3w ago
v0.1.1
MIT-0
@ricknote
contentlatestwechat
Download

Weixin Article Reader

Use this skill when the user provides a mp.weixin.qq.com article URL and wants the raw article text, or when article content must be extracted before summarization.

Usage

Prefer the bundled script:

python3 scripts/extract_wechat_article.py "https://mp.weixin.qq.com/s/xxxx"

If the current working directory is not the skill root, first locate the installed weixin-article-reader skill directory and run scripts/extract_wechat_article.py from there.

The script returns JSON with:

  • title
  • author
  • publish_date
  • content
  • source_url

Workflow

  1. Detect a mp.weixin.qq.com article URL.
  2. Run the bundled extraction script.
  3. If the user wants the full article, return title, author, publish date, and body text.
  4. If the user wants a summary, first confirm the extracted content is non-empty, then summarize it.

Response Guidance

  • For full-text requests, return the title, author, publish date, and then the article body.
  • For summaries, summarize the extracted content and include the title plus source URL.
  • If publish_date is empty, do not invent a date. State that the page did not expose a publish date in a reliably parsed form.

Notes

  • Do not use pip install.
  • Do not require beautifulsoup4 or requests.
  • Prefer the bundled script instead of relying on unavailable generic web-extraction helpers.
  • If the script returns empty content, explain that the article may use a special page structure or access restriction.
  • This skill only applies to mp.weixin.qq.com article pages. If the URL is from another domain, say the skill does not apply.

Comments

Loading comments...