agentleFS
tang-vutang-vu/social-posting-skills/skills/post-facebook/SKILL.md

post-facebook

Skill9 starsChanged 2 months agoMITView on GitHub

Adapt and publish campaign items on Facebook — profile/page and Group posts with group-rule discipline

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never post the same thing to a dozen groups — that's the spam pattern admins ban for.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Facebook Adapter

Facts live in platforms/facebook.json (63k char ceiling — effective length is far shorter, media bounds). Meta requires AI-content labels for synthetic media — mark generated images honestly.

What Facebook rewards (culture)

  • Groups over Pages for organic reach — but Groups are admin-ruled communities: the group's rules decide what flies, always.
  • Friendly, plain-spoken, community-minded posts. Questions to the community outperform announcements.
  • Native media over outbound links.

Drafting from the content graph

  • core-claim → friendly opener (a question or a "made this thing" line).
  • context + proof → short body; Facebook is not the place for the full technical dump.
  • cta → invite conversation.
  • Link → first comment (heuristic label in the data).
  • Target a Group? The preview must name the group and the user must confirm its rules allow this content type.

Publishing

  • manual → draft package (default — Group contexts vary too much to assume automation is welcome).
  • agent-browser → playbook exists, but many Groups queue posts for admin approval — "Pending" is normal, not a failure.
  • api → Pages API posts to Pages you manage (Meta app review); not implemented.

Genuine engagement

  • Be a group member: answer questions, help people, then occasionally share what you built where it's relevant.
  • Never post the same thing to a dozen groups — that's the spam pattern admins ban for.
  • Meta's AI rules: label AI-generated media; undisclosed synthetic content risks the account.

Pitfalls

  • Group posts may sit in admin-approval queues — record patiently.
  • Engagement bait ("like if you agree") is penalized and prohibited here.

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.