agentleFS
Sign inStart free
posteverywhereposteverywhere/claude-plugin/skills/fix-failed-posts/SKILL.md

fix-failed-posts

Skill1 starsChanged 33 days agoMITView on GitHub

Find and fix social media posts that failed to publish in PostEverywhere. Use when the user says a post didn't go out, a platform failed, an account stopped working, or asks what went wrong with a post.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Find the failures: Call list_posts_advanced with status: "failed" (and "partially_failed"), newest first.

    line 12
  2. Very specific:

    Confirm: Call get_post_results again after a short wait and tell the user what published.

    line 19
  3. Distinctive:

    Never retry the same post in a loop.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Fix failed posts

Find what failed, explain why in plain words, fix the cause, and retry only when a retry can work.

Steps

  1. Find the failures. Call list_posts_advanced with status: "failed" (and "partially_failed"), newest first. For one post the user named, call get_post_results with its id.
  2. Read the reason. Each failed destination carries an error. Sort it into one of these:
    • The account needs reconnecting (expired or revoked login, missing permission). Call get_account_health for that account to confirm, then create_reconnect_link and give the user the link. They open it and sign in again.
    • The post broke a platform rule (too long, wrong media, missing media). Fix it with update_post, then retry.
    • A temporary problem at the platform (rate limit, timeout, the platform was down). Retry.
    • Something the user must change on the platform itself (for example, an Instagram account that isn't a Business or Creator account). Tell them exactly what to change.
  3. Retry. For one post, call retry_failed_post. For many, call retry_failed_posts with the post ids, or filter by account_id or platform. Don't retry a failure that needs the user to act first; it will fail the same way.
  4. Confirm. Call get_post_results again after a short wait and tell the user what published.

Be careful

  • Never retry the same post in a loop. One retry after a fix is enough.
  • Retrying a post that already published on some platforms only retries the failed ones.

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.

Reviews can't be read right now.

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