agentleFS
posteverywhereposteverywhere/copilot-plugin/skills/repurpose-content/SKILL.md

repurpose-content

Skill0 starsChanged 28 days agoMITView on GitHub

Turn one long piece of content into a set of social media posts with PostEverywhere. Use when the user shares a blog post, article link, video transcript, podcast notes, newsletter or other long text and wants posts made from it, or says "repurpose this" or "turn this into posts".

6 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. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Pick the accounts: Call list_accounts. Use the accounts the user named, or ask.

    line 14
  2. Very specific:

    Create them: After the user confirms, create them as drafts with create_post and draft: true, or several at once with bulk_create_posts …

    line 19
  3. Distinctive:

    Don't copy long passages word for word from someone else's article.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Repurpose content

Turn one source into several posts, each written for its platform. Everything is a draft until the user says go.

Steps

  1. Get the source. Use the text the user gave. If they gave a link, read it with your own web access if you have it. If you can't open it, ask the user to paste the text. Never write posts from a title or a guess.
  2. Pull out the ideas. List the main points, useful facts, quotes and examples in the source. Each one can become a post. Keep the source's facts exactly; don't add numbers, claims or links it doesn't contain.
  3. Pick the accounts. Call list_accounts. Use the accounts the user named, or ask. Skip any account that can't post and tell the user why.
  4. Plan the set. Suggest how many posts and where, for example one LinkedIn post, three X posts and one Threads post, each from a different idea. Ask if they want them spread over several days.
  5. Write the posts. Write each post for its platform (see the schedule-social-posts skill for the rules, and call get_platform_rules for any platform you are unsure about). Use a different angle per post: a key point, a quote, a how-to, a question. Add a link to the source when the user has one and the platform allows links. If the user has a voice guide (see brand-voice), follow it.
  6. Media. Instagram, TikTok, Pinterest and YouTube need an image or video. Use media the user gives you: upload_media_from_url for a public link, or list_media for files already in their library. If there is no media, leave those platforms out and say so.
  7. Show the drafts. Present them as a table: platform, date and time (if any), and the full text. Ask the user to confirm or change them.
  8. Create them. After the user confirms, create them as drafts with create_post and draft: true, or several at once with bulk_create_posts (each with draft: true). Only schedule or publish when the user asks, with schedule_post on each draft.
  9. Report back. List each post id, its accounts and its time.

Be careful

  • Credit the source when it isn't the user's own work.
  • Don't copy long passages word for word from someone else's article.

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.