agentleFS
Sign inStart free
glideaglidea/supersearch-skills/skills/wechat-search/SKILL.md

wechat-search

Skill4 starsChanged 3 months agoMITView on GitHub

Search WeChat Official Account articles for Chinese news, industry perspectives, tutorials, product analysis, and institutional publications through Sogou WeChat Search. Return account names, publication dates, summaries, and original WeChat links.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer most-liked sorting when the search surface provides it.

    line 16
  2. Very specific:

    Prefer the original WeChat article in url.

    line 17
  3. Very specific:

    Use sogou_url from the same result when url cannot be opened.

    line 18
  4. Very specific:

    When the script returns search_executed: false and fallback: browser, load and follow $browser:control-in-app-browser, then search at …

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

WeChat Search

Run:

python3 scripts/search.py "search query"

Return five results by default. Answer and cite only fields actually returned in results:

  • Prefer most-liked sorting when the search surface provides it. Sogou WeChat does not expose like sorting or engagement counts, so use relevance ordering and state the actual sort mode.
  • Prefer the original WeChat article in url.
  • Use sogou_url from the same result when url cannot be opened.
  • Open url and read the article when its full position matters. Do not infer it from the summary alone.
  • Merge duplicate syndications and distinguish account opinions from verifiable facts.

When the script returns search_executed: false and fallback: browser, load and follow $browser:control-in-app-browser, then search at https://weixin.sogou.com/. Ask the user to complete any CAPTCHA. Do not bypass it.

End every response with a ## References section. Keep links next to supported claims and repeat the used links here, deduplicated and comma-separated on one website line:

## References

WeChat: [result title](https://example.com), [result title](https://example.com)

List only links actually used in the answer. When none exist, write No citable sources. below the heading.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free