Automate note collection and post publishing
An RPA flow gathers Xiaohongshu notes into Feishu, OpenClaw drafts posts from them, and xiaohongshu-mcp publishes the results.
- What they did
- The person set up a scheduled Yingdao RPA job to look up Xiaohongshu by keyword, ignore items already recorded, and save note and author data into a Feishu Bitable. OpenClaw then connected with the Feishu credentials, read the table, and used a custom Xiaohongshu copywriting skill to turn the collected items into draft notes. After that, xiaohongshu-mcp, installed through OpenClaw, handled publishing.
- How it went
- They got the full chain working from collection through a published note and say it cuts about 3 hours from their day. Some RPA fields returned blank, so they had to use workarounds.
- Tips
- Plan for around 2 hours of uninterrupted setup time. Let RPA handle scraping if you want to avoid spending agent tokens on data collection.
Try it yourself with OpenClaw
Build a content workflow for my [platform] account about [topic]. On a schedule, collect the most popular posts for [keywords] into my [Feishu table or other database], skip anything already saved, and extract the post and author fields. Then read that table, draft [number] new posts in my style based on the collected items, and pause to show me each draft for approval before any publishing step. Only after I confirm, publish the approved drafts through [publishing tool or connector]. If any fields are missing, tell me what you could not capture and suggest a workaround instead of guessing.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
1 more report of this
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Use an agent to draft and publish SEO blog posts
A writer set up OpenClaw to mimic their style, spot search opportunities, and prepare posts for manual approval before publishing.
Automate a weekly RSS newsletter draft
One person uses OpenClaw to gather feed items, rank them, draft intros, and wait for approval before sending the newsletter.
Use agents to draft and render short social videos
A creator used OpenClaw agents to plan, script, voice, and render WeChat videos, then approved each one in Telegram before publishing.
Edit a video in chat and export the finished file
A developer made an OpenClaw skill that turns chat requests into backend video edits and returns the rendered file.
Edit a keynote take into two finished video formats
Andreas Fuchs used Claude Code to convert one keynote recording into a polished edit with captions, graphics, branding, music, and both widescreen and vertical exports.
Turn one idea into a finished video
Grok’s Agent Mode took a concept from brainstorming through writing, images, edits, and final video in one canvas.