agentleFS
sergebulaevsergebulaev/facebook-skills/skills/fb-repurposer/SKILL.md

fb-repurposer

Skill75 starsChanged 5 months agoMITView on GitHub

Repurpose existing content into a native Facebook Page post. Take a LinkedIn post, X thread, blog, or newsletter and rewrite it for a Page: warm the tone, lead with a standalone claim before the \"See more\" fold, move links to the first comment, strip off-platform artifacts (hashtag walls, \"link in bio\", @-handles), then humanize and publish via Publora on approval. Not for writing from scratch (use fb-post-writer), auditing a draft (use fb-humanizer), or comment replies (use fb-engagement-drafter).

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Not for a blank-page draft (use fb-post-writer), not for reviewing an already-Facebook draft (use fb-humanizer --mode audit), and not for …

    line 24
  2. Distinctive:

    If the source's whole point is a link, put the link in the first comment and let the post stand on its own claim.

    line 52
  3. Distinctive:

    Strip off-platform artifacts: Remove "link in bio", "smash subscribe", "read more below", hashtag walls, X @-handles that only exist …

    line 54
  4. Very specific:

    Humanizer pass: Run fb-humanizer V3 on the draft: 2026 AI vocab by paragraph density, em dashes above the cap (about one per 100 words, …

    line 58
  5. Distinctive:

    Keep the source's claim and facts intact.

    line 95
  6. Distinctive:

    Never paste the source verbatim and trim.

    line 98
  7. Distinctive:

    No tag-bait ("tag 3 friends").

    line 102

≈ “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

Facebook Repurposer

Turn something you already made into a Page post that reads like it was born on Facebook. Repurposing is not copy-paste. A post that killed on LinkedIn will die on a Facebook Page if you paste it: wrong tone (corporate press release vs warm Page voice), wrong length, links that suppress reach, and artifacts (hashtag walls, "link in bio", X @-handles) that scream off-platform.

This skill transforms, it does not generate. It reads your source, keeps the idea, and rebuilds the delivery for a Facebook Page.

When to use

  • "Turn this LinkedIn post into a Facebook Page post"
  • "Repurpose my blog post / newsletter / X thread for our Page"
  • "This worked on Threads, adapt it for Facebook"
  • "I have a rough idea in another format, make it native here"

Not for a blank-page draft (use fb-post-writer), not for reviewing an already-Facebook draft (use fb-humanizer --mode audit), and not for replying to comments on your Page (use fb-engagement-drafter).

How it works

Voice profile first (all drafts). If ../../references/voice-profile.md has filled: yes, load it and match the user's voice fingerprint, hard rules, and CTA/link style throughout. If it is not filled, mention once that fb-humanizer --mode profile can learn their voice from a few posts, then proceed with the generic voice rules.

Story bank next. If ../../references/story-bank.md has filled: yes, load it and take every concrete detail (numbers, dates, named projects, positions) from there instead of asking mid-draft. Never invent a figure, a date or a client name that is not in the bank or supplied by the user in this conversation. If the bank has nothing that fits, ask the user, or say once that fb-humanizer --mode interview fills it in 20 to 40 minutes. A draft with a plausible invented number is worse than a draft with none: one is vague, the other is a retraction.

  1. Take the source. Any format: a post, a paragraph, a script, a caption, a transcript, a bullet list, a link to read. Ask for the source and the goal (shares / comments / reactions) if not given.
  2. Extract the spine. Strip the source platform's shell and pull out the one claim, the one story, or the one number worth keeping. Most repurposing fails because it keeps the words instead of the point.
  3. Choose the container. One claim, number, or moment -> a short Page post (aim under 80 chars). A true narrative or a build -> a story post (FB8-FB10 shapes). Match the source to a 2026 Facebook shape in ../../references/hook-formulas.md, picked by the goal.
  4. Warm the tone for a Page. A Page voice is warm and human, not a press release and not clickbait. Rewrite the source's hook: lead with a standalone claim that lands the whole point above the "See more" fold. Facebook folds longer posts, so line one must carry it alone.
  5. Refit the format. Lead short. One idea per post, line breaks as beats. Cut the source's connective tissue and corporate throat-clearing. 0-2 hashtags, 0-2 emoji, none on a serious take.
  6. Move links off the body. External links suppress organic reach on a Page. If the source's whole point is a link, put the link in the first comment and let the post stand on its own claim.
  7. Strip off-platform artifacts. Remove "link in bio", "smash subscribe", "read more below", hashtag walls, X @-handles that only exist elsewhere, and any "as I posted on LinkedIn" throat-clearing. A repurposed post should not admit it was repurposed.
  8. Humanizer pass. Run fb-humanizer V3 on the draft: 2026 AI vocab by paragraph density, em dashes above the cap (about one per 100 words, never swapped for a period), stacked rule-of-three triads, "We are thrilled to announce", generic openers and reveal bridges. Fix only a story paragraph that reads machine-flat; never manufacture variance. Keep the user's real numbers and named entities from the source.
  9. Approval card. Show: source -> Facebook mapping (what became what), the container (short post or story post), shape used, char count (flag if it crosses the 80-char sweet spot), whether a link moved to the first comment, primary goal.
  10. On approval. Publish via lib.publish(kind="post", draft_text=<approved>, target_url="https://www.facebook.com/YourPage", platforms=[<FACEBOOK_PLATFORM_ID>], scheduled_time=<iso_or_None>). For a deliberate long story post, pass kind="story". The wrapper handles Publora / manual / diy routing.

Native-fit rules (source -> Facebook)

  • LinkedIn post -> Facebook: warm the corporate tone. LinkedIn tolerates a thought-leadership register; a Page wants a human talking to people. Drop the buzzwords, keep the insight.
  • X thread -> Facebook: unroll into one short story post. A Page reads a numbered thread as noise, so stitch the beats into a single readable arc and cut the "1/", "2/" scaffolding and @-handles.
  • Blog / newsletter -> Facebook: pick the one relatable angle, not a summary. Lead with the human moment or the single most useful line; let the link (if any) live in the first comment.
  • YouTube script -> Facebook: lead with the payoff, not the intro. "Here is what we found" beats "In this video".
  • Instagram / TikTok caption -> Facebook: strip emoji density and hashtag blocks; a Page reads them as clutter. Keep the one line that carries.

Hard rules

Global voice rules: see root SKILL.md Voice rules. Additional skill-specific rules:

  • Keep the source's claim and facts intact. Repurposing changes the delivery, never the meaning or the numbers.
  • The first line must land the whole point above the fold, on its own.
  • Never paste the source verbatim and trim. Rebuild the hook and tone from the spine.
  • One specific number where the source offers one. Keep it.
  • Warm and human, never a press release and never "You won't BELIEVE" clickbait.
  • No tag-bait ("tag 3 friends"). Earn the share with the post.
  • Links move to the first comment. The body carries the claim.

Anti-patterns (skill will refuse)

  • Copy-pasting the source with light edits (that is not repurposing).
  • Keeping the source platform's artifacts ("link in bio", "smash subscribe", hashtag walls, X @-handles, "1/ 2/" thread numbering).
  • "You won't BELIEVE" clickbait or ALL CAPS for intensity.
  • Engagement bait ("LIKE and SHARE if you agree", "tag 3 friends").
  • Em dashes above the cap (more than about one per 100 words), or an em dash swapped for a period.
  • "The result?" / "Here's what" reveal bridges and staccato stacks added during the rewrite.
  • Rule-of-three lists without specifics.
  • "leverage", "fundamentally", "game-changer", "deep dive".
  • A bare external link in the post body (move it to the first comment).
  • Meta throat-clearing ("I originally posted this on...").

Resources

  • ../../references/hook-formulas.md - the 10 Facebook shapes to re-hook with (FB1-FB7 short, FB8-FB10 story)
  • ../../references/algorithm-heuristics.md - 2026 Facebook Page ranking rules (the under-80 boost, link reach suppression, timing, limits)

Related skills

  • fb-post-writer - write a fresh Page post from scratch
  • fb-humanizer - scrub AI tells, plus --mode audit to review the result
  • fb-hook-extractor - reverse-engineer a hook from a Page post you admire
  • fb-engagement-drafter - reply to the comments your post earns

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.