← Back to Skills Marketplace
Wechat Report
by
Abigale-cyber
· GitHub ↗
· v1.0.0
· MIT-0
91
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install wechat-report
Description
Generate a structured comparison report for multiple WeChat Official Account articles under one topic. Use this when the user wants several公众号文章 collected in...
Usage Guidance
Before installing/running this skill: 1) Expect to install Python deps (requirements.txt), Node packages, and Playwright (npm + npx playwright install). The registry metadata omitted these runtime requirements — confirm you want to run those installers. 2) The skill fetches arbitrary web pages and launches a headless browser that executes page JS; run it in an isolated workspace or VM if you are cautious. 3) Do not point the skill at a profileDir containing sensitive cookies or other accounts unless you understand the privacy implications — the browser session can expose logged-in state to pages. 4) Review requirements.txt and any npm packages before installing. 5) The skill will only write local report and JSON files and will not automatically post to Feishu; it may require manual confirmation to sync downstream. If you are uncomfortable with running a headless browser that visits external pages or with the metadata omissions, do not install or run it until those are addressed.
Capability Analysis
Type: OpenClaw Skill
Name: wechat-report
Version: 1.0.0
The wechat-report skill is a legitimate tool designed to aggregate and analyze WeChat Official Account articles. It uses Python's subprocess module to execute local Node.js scripts (collect_engagement.js, fetch_article_html.js) that utilize Playwright for web scraping and metric extraction. The code follows safe practices, such as using yaml.safe_load for frontmatter parsing and list-based subprocess calls to prevent shell injection. All network activity (Bing RSS and WeChat URLs) and file operations are strictly aligned with the stated purpose of generating comparison reports and raw JSON data in the content-production/inbox directory.
Capability Assessment
Purpose & Capability
The skill's stated purpose (collect WeChat articles, extract content and engagement, produce a local report) matches what the code does. However the registry metadata lists no required binaries or environment variables while the runtime and README require Node, npm, Playwright, and Python dependencies — an omission that can mislead users about what will be installed/run.
Instruction Scope
SKILL.md and README describe running the skill on a frontmatter Markdown request file and producing local report files. The implementation performs network queries (Bing RSS and arbitrary web pages) and runs a headless browser (Playwright) which executes page JavaScript. This is expected for extraction, but means fetched pages can run arbitrary JS and trigger network activity from your machine; the skill writes output HTML/JSON under content-production/inbox/ and uses a persistent browser profile directory you supply.
Install Mechanism
There is no automated install spec in the registry. The README instructs manual pip and npm installs and Playwright browser installation (npx playwright install). The code does not download arbitrary binaries from suspicious hosts — it relies on standard package tooling — but the lack of an explicit install spec in the metadata is an incoherence to be aware of.
Credentials
The skill declares no environment variables or credentials (and does not require them explicitly). To surface engagement metrics it relies on a browser profile (Playwright persistent context) which could contain login cookies if you provide one; the skill itself does not request secrets. This is proportionate, but you should not pass profile directories containing unrelated sensitive sessions.
Persistence & Privilege
always is false and the skill does not request persistent inclusion or attempt to modify other skills. It does create/use profile directories and write report files under content-production/inbox/, which is expected and scoped to its purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wechat-report - After installation, invoke the skill by name or use
/wechat-report - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
wechat-report 1.0.0
- Initial release providing structured comparison reports for multiple WeChat Official Account articles under one topic.
- Generates a Markdown report including article metadata, engagement comparison, content structure tables, “爆款写法” tags, title/opening/ending analysis, and writing patterns summary.
- Supports collection of articles via topic or seed URLs, with optional engagement data.
- Output includes both human-readable and raw JSON formats.
- Does not automatically sync to Feishu; sync must be triggered separately by the user.
Metadata
Frequently Asked Questions
What is Wechat Report?
Generate a structured comparison report for multiple WeChat Official Account articles under one topic. Use this when the user wants several公众号文章 collected in... It is an AI Agent Skill for Claude Code / OpenClaw, with 91 downloads so far.
How do I install Wechat Report?
Run "/install wechat-report" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Wechat Report free?
Yes, Wechat Report is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Wechat Report support?
Wechat Report is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Wechat Report?
It is built and maintained by Abigale-cyber (@abigale-cyber); the current version is v1.0.0.
More Skills