Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added Tavily Search API as a secondary search option, expanding from a two-layer to a three-layer search strategy. - Updated documentation to reflect the new search order: primary (Brave Search), secondary (Tavily), fallback (direct web fetch). - Improved fallback logic and error handling, ensuring graceful degradation across all three strategies. - Added example for forcing a specific search strategy in the command-line usage. - Enhanced compliance documentation to clarify API key usage and strategy details.
What This Skill Does
Searches WeChat Official Account articles using a three-layer fallback strategy: Brave Search API, Tavily API, and direct scraping of Sogou WeChat search. Returns recent articles with configurable result count, date filtering, and multiple output formats.
The layered fallback between Brave, Tavily, and direct fetch means searches succeed even when individual APIs are unavailable or unconfigured.
When to use it
- Finding recent Chinese tech articles on a specific topic
- Monitoring WeChat Official Accounts for industry news
- Exporting article metadata as JSON for downstream processing
- Filtering WeChat content by date range for research
- Searching Chinese AI coverage not indexed by Western search engines
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: search for recent WeChat articles about large language models, return 10 results in JSON
- 1Invokes wechat-search with query '大模型', --max-results 10, --output json
- 2Attempts Layer 1: queries Brave Search API with site:mp.weixin.qq.com filter
- 3Brave returns results; skips Layer 2 and Layer 3 fallbacks
- 4Parses article metadata and sorts by recency
JSON array of 10 recent WeChat Official Account articles with titles, URLs, and publication dates
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.