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
| Endpoint | Calls | At most |
|---|---|---|
wechat_mp.accounts.articles.list | 5 | $0.10 |
wechat_mp.articles.metrics | 10 | $0.20 |
wechat_mp.articles.get | 10 | $0.20 |
wechat_mp.articles.comments.list | 10 | $0.20 |
| Total | 35 | $0.70 |
What it does
- Plans and states the cost before the first paid call, and asks before going past 40 calls.
- For an account given by name, call the account search once with the name as
queryand take the matching id. Skip this for accounts given by id or article link. - For each account, call its article list once and keep the articles published in the last
daysdays. - (If the platform has it.) For each post kept, call the metrics endpoint with its link to add reads and likes.
- 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. - (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.
- Lays every result out as one table and answers from it, with the cost and where the data came from.
What you get back
| Account | Title | Published | Reads | Likes | Comments | Markdown file | Link |
|---|---|---|---|---|---|---|---|
One row per item fetched. A cell stays empty when the platform does not show that figure; nothing is guessed.
Inputs it needs
| Input | Needed | Meaning |
|---|---|---|
accounts | yes | Official Account names, ids or article links, comma-separated. |
days | no | How many days back to list, 1 to 30; 7 if not given. |
export | no | Which articles to export in full: all, or titles or links, comma-separated; all if not given. |
Platforms and endpoints
| Platform | Endpoint | Price |
|---|---|---|
| WeChat Official Accounts | Official Account article history wechat_mp.accounts.articles.list | $0.02 per call · about 10 articles per page |
| WeChat Official Accounts | Official Account article detail wechat_mp.articles.get | $0.02 per call |
| WeChat Official Accounts | Official Account search wechat_mp.accounts.search | $0.058 per account · at most $0.58 per call |
| WeChat Official Accounts | Official Account article stats wechat_mp.articles.metrics | $0.02 per call |
| WeChat Official Accounts | Official Account article comments wechat_mp.articles.comments.list | $0.02 per call · about 20 comments per page |