agentleFS
ramkesh430ramkesh430/facebook-agent-skill/skills/fb-page/SKILL.md

fb-page

Skill1 starsChanged 16 days agoMITView on GitHub

Score a Facebook Page or professional-mode profile out of 100 on a 14-part rubric, then rewrite what lost points in fix-first order - name, intro, about, cover, action button, pinned post, contact details. Use when the user says "audit my Facebook page", "fix my page", "write my page bio", "why isn't my page getting messages", or shares a Page link or screenshots.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Ask for the Page link and screenshots of: the top of the Page on mobile, the intro/about, the pinned post, and (if they'll share) the inbox …

    line 18
  2. Distinctive:

    If the browser is available and the Page is public, read it, but never log in as the user.

    line 20
  3. Very specific:

    Pinned post: write it with /fb-post - what you do, proof, how to start.

    line 46
  4. Very specific:

    Run every piece of copy through /fb-human.

    line 50
  5. Very specific:

    Never invent reviews, numbers, awards or customers.

    line 54
  6. Distinctive:

    Don't recommend buying followers, likes or reviews, or review-for-discount swaps.

    line 55

≈ “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

fb-page

Scores the Page against rubric.json (14 parts, 100 points), then rewrites the parts that lost the most points first.

Collect

Ask for the Page link and screenshots of: the top of the Page on mobile, the intro/about, the pinned post, and (if they'll share) the inbox response stats. If the browser is available and the Page is public, read it, but never log in as the user. Also ask: who is the Page for, and what's the one action a visitor should take?

Score

For each part in rubric.json: full points, half, or zero, with one line of evidence. Total it and band it (STRONG 85+, OK 65+, WEAK).

PAGE SCORE  61 / 100  WEAK
  intro           0/12  "Welcome to our official page!" - no audience, no promise
  action button   4/8   "Learn more" -> homepage; visitors want to message
  recent          5/10  last post 19 days ago; 6 of last 10 are shares from other Pages
  ...

Fix, in order of points lost

For each fix, give the copy-ready replacement:

  • Name: what people would search. Brand + what/where if the brand says nothing.
  • Intro (101 chars): for whom + what they get + one proof. Three options.
  • About / description (155-255 chars): the search words, in sentences.
  • Cover: a brief for the image and its one line of text; mobile-safe.
  • Action button: one, matched to the one action.
  • Pinned post: write it with /fb-post - what you do, proof, how to start.
  • Contact: list exactly what's missing or out of date.
  • Messages: instant reply and 3-5 FAQ answers in the user's voice.

Run every piece of copy through /fb-human.

Rules

  • Never invent reviews, numbers, awards or customers. Use {{your number}}.
  • Don't recommend buying followers, likes or reviews, or review-for-discount swaps; they break Meta's rules and erode trust.
  • The user makes the changes. This skill writes them.

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.