agentleFS
posteverywhereposteverywhere/cursor-plugin/skills/recycle-top-posts/SKILL.md

recycle-top-posts

Skill0 starsChanged 28 days agoMITView on GitHub

Find the user's best past social media posts in PostEverywhere and schedule fresh versions of them. Use when the user wants to reuse, recycle, reshare or "bring back" posts that did well, fill gaps in their schedule with proven content, or asks which old posts are worth posting again.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Pick the period: Default to the last 90 days.

    line 12
  2. Very specific:

    Find the posts: Call list_posts_advanced with status: "published", published_after and published_before, sort: "published_at", and limit: …

    line 13
  3. Very specific:

    Space them out: Leave at least a few weeks between a post and its new version on the same account.

    line 17

≈ “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

Recycle top posts

Find what worked before, write new versions of it, and space them out. A new version says the same idea in new words; it is never a copy.

Steps

  1. Pick the period. Default to the last 90 days. Call get_analytics_summary (period: "custom" with from and to) to see which platforms did best.
  2. Find the posts. Call list_posts_advanced with status: "published", published_after and published_before, sort: "published_at", and limit: 100. Page with offset if there are more. Each destination carries its own numbers (views, likes, comments, shares) where the platform reports them.
  3. Rank them. Rank by engagement on each platform, not across platforms: a good LinkedIn post and a good X post have different numbers. Use get_post_results for a closer look at the top few. Leave out posts that were about a date or offer that has passed.
  4. Show the shortlist. List the top five to ten posts: platform, date, first line, and the numbers. Say "not available" when a platform didn't report a number. Ask the user which to recycle.
  5. Write new versions. For each chosen post, write a fresh version: a new first line, a new angle or example, the same core idea and the same facts. Change the format when it helps (a tip list becomes a question, a quote becomes a short story). Follow the user's voice guide if there is one (see brand-voice).
  6. Space them out. Leave at least a few weeks between a post and its new version on the same account. Call list_posts_advanced with status: "scheduled" to avoid clashes, or offer to use the posting queue (get_queue, then use_queue: true).
  7. Show the plan. Present a table: date and time, accounts, the old first line and the new text. Ask the user to confirm.
  8. Create them. After the user confirms, create them as drafts with bulk_create_posts (draft: true on each), or schedule them with each post's scheduled_for if the user said to. To reuse the original media, get its ids with get_post, check each one is still in the library with get_media, and pass them in media_ids.
  9. Report back. List each new post id, its accounts and its time.

Be honest

  • A small number of posts can't show what works. Say so when the sample is small.
  • Some platforms don't report every number. Don't rank a post low because its numbers are missing.

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.