For AI

Agent skill · okdata-wechat-articles

WeChat article monitoring and export

What did these Official Accounts publish this week, and can I have it all as Markdown?

Lists the new articles of each WeChat Official Account you name over the past days, with reads and likes where WeChat gives them; exports the articles you pick as Markdown with their comments; then sums it up per account as a weekly report.

  • 1 platforms
  • 35 calls in the example
  • ≤ $0.70 for that run
  • 40 calls before it asks

Tell your AI

Install the okdata skill okdata-wechat-articles from https://okdata.online/.well-known/agent-skills/okdata-wechat-articles/SKILL.md into your skills folder.

The package is one folder with one SKILL.md; unzip it into your agent's skills folder. The skill is free; you pay only for the calls it makes.

Ask it like this

  • “Turn what these 5 Official Accounts published this week into a weekly report, and export the articles as Markdown.”
  • “Which article from these accounts got the most reads this week? Export it with its comments.”
  • “Every Monday, list last week's articles from our three competitors' Official Accounts with links.”

Example run

What it does

  1. Plans and states the cost before the first paid call, and asks before going past 40 calls.
  2. For an account given by name, call the account search once with the name as query and take the matching id. Skip this for accounts given by id or article link.
  3. For each account, call its article list once and keep the articles published in the last days days.
  4. (If the platform has it.) For each post kept, call the metrics endpoint with its link to add reads and likes.
  5. For each article to export, call the article endpoint with its link (url) and save the full text as one Markdown file: the title as the heading, then the account, publish time and link, then the body.
  6. (If the platform has it.) For each exported article, call the comments endpoint with its link, one page, and add the comments at the end under a Comments heading.
  7. Lays every result out as one table and answers from it, with the cost and where the data came from.

What you get back

AccountTitlePublishedReadsLikesCommentsMarkdown fileLink

One row per item fetched. A cell stays empty when the platform does not show that figure; nothing is guessed.

Inputs it needs

InputNeededMeaning
accountsyesOfficial Account names, ids or article links, comma-separated.
daysnoHow many days back to list, 1 to 30; 7 if not given.
exportnoWhich articles to export in full: all, or titles or links, comma-separated; all if not given.

Platforms and endpoints

PlatformEndpointPrice
WeChat Official AccountsOfficial Account article history wechat_mp.accounts.articles.list$0.02 per call · about 10 articles per page
WeChat Official AccountsOfficial Account article detail wechat_mp.articles.get$0.02 per call
WeChat Official AccountsOfficial Account search wechat_mp.accounts.search$0.058 per account · at most $0.58 per call
WeChat Official AccountsOfficial Account article stats wechat_mp.articles.metrics$0.02 per call
WeChat Official AccountsOfficial Account article comments wechat_mp.articles.comments.list$0.02 per call · about 20 comments per page

Connect once, then just ask.

Every new key comes with $0.10 to try it. One sentence connects your agent.

Start free
Connect your AI

Paste this into your agent

Read https://okdata.online/agents.md and set up okdata for me; my key is in the OKDATA_API_KEY environment variable.

Claude Code, Cursor, Codex and other agents that can open a link set themselves up from it.

MCP serverhttps://api.okdata.online/mcp