agentsclimarketplace

Content repurposer

Skill megandmartin/agent-skills-repo/skills/content-marketing/content-repurposer

75 production-grade agent skills for Hermes Agent + Paperclip — research, write, organize, earn, and run an AI workforce. Every skill passes a QA gate with hard safety rails. Built by Gen AI Hub.

Install
npx -y skills add megandmartin/agent-skills-repo --skill content-repurposer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 14 days oldThe repository was created 14 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Takes one long-form piece (article, video transcript, talk, research brief) and produces a repurposing matrix — LinkedIn post, X thread outline, newsletter blurb, and 3 short-video hooks — each adapted to platform norms, never copy-pasted. Use when the user asks to "repurpose this", "turn this into social content", "spread this across platforms", "atomize this post", or "get more out of this piece". Don't use for producing the final polished posts — this skill outlines; hand cells to linkedin-content-pack or x-thread-builder.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.1 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

Content Repurposer

Extracts the reusable core of one long-form piece and re-expresses it natively for four destinations: a LinkedIn post, an X thread outline, a newsletter blurb, and 3 short-video hooks. The test for every cell of the matrix: it must read like it was born on that platform, not exported to it. Everything ships as drafts.

When to Use

  • A finished long-form piece exists and the user wants multi-platform mileage from it.
  • A deep-research-brief deserves distribution beyond one channel.
  • Not for: producing the final polished LinkedIn pack or full X thread (this skill outlines; hand cells to linkedin-content-pack or x-thread-builder for full builds), or drafting the source piece itself.

Quick Reference

ActionCommand / Call
Word-count sourcepython3 -c "print(len(open('/tmp/source.txt').read().split()))"
Extract idea inventory5–8 atomic ideas, each quotable alone (step 2)
Platform fit rulesLinkedIn = professional lesson; X = punchy sequence; newsletter = editorial take; video = spoken hook
Char-check any cellpython3 -c "print(len('''TEXT'''))"
Full buildsRoute to linkedin-content-pack / x-thread-builder / newsletter-assembler

Procedure

  1. Precheck — confirm you have the full source text (save to /tmp/source.txt; run the word count — under ~400 words means it's not long-form, so tell the user a single-platform skill fits better). Confirm audience and which platforms matter; default to all four.
  2. Build the idea inventory — read the whole piece, then list 5–8 atomic ideas: each a standalone claim, stat, story, or framework with a line reference to where it lives in the source. This inventory — not the source's structure — feeds every platform. No idea in the inventory, no idea in the matrix.
  3. LinkedIn post — pick the idea with the strongest professional "lesson learned" or contrarian-but-defensible angle. Draft hook-first (line 1 ≤200 chars, python3-checked), short paragraphs, substance in-post, no engagement bait, link reserved for a first comment. This is a different idea-framing than the X thread uses — if two cells lead with the same sentence, one is wrong.
  4. X thread outline — pick the idea that decomposes into a sequence (steps, escalating list, before/after). Write the opener tweet in full (≤280 chars, python3-checked) plus one-line summaries for 5–9 body tweets and the CTA close. Punchier and more concrete than the LinkedIn framing.
  5. Newsletter blurb — 60–120 words of editorial take for an existing newsletter section: why the piece matters to that reader, one specific takeaway, then the link. Written as the curator's voice about the piece, not a summary of it.
  6. 3 short-video hooks — three distinct spoken opening lines (≤2 sentences each) for Reels/Shorts/TikTok, each from a DIFFERENT inventory idea. Written for the ear: present tense, direct address, concrete stakes in the first sentence. Banned: "Wait for it", "You won't believe", "Stop scrolling".
  7. Assemble & deliver — fill the matrix template, noting which inventory idea each cell used (prove no copy-paste: no sentence appears verbatim in two cells). Recommend brand-voice-guardian for a voice pass and the sibling skills for full builds of any cell.

Output Template

# Repurposing Matrix: [source title]
**Source:** [link/file] | **Audience:** [who]

## Idea inventory
1. [atomic idea] (source ref)
... (5–8 total)

## LinkedIn post (idea #x) — full draft
[hook / body / close]

## X thread outline (idea #y)
1/ [full opener, char-checked]
2/–n/ [one-line per tweet]
n+1/ [CTA close]

## Newsletter blurb (idea #z) — 60–120 words
[take + link]

## Short-video hooks
A. (idea #_) "[spoken line]"
B. (idea #_) "[spoken line]"
C. (idea #_) "[spoken line]"

## Next steps
- Full builds: linkedin-content-pack / x-thread-builder / newsletter-assembler

Pitfalls

  • Copy-paste with line breaks — the "X thread" is just the article's paragraphs chopped at 280 chars. Recovery: return to the idea inventory and re-express the idea in platform-native rhythm; if a cell shares a verbatim sentence with the source or another cell, rewrite it from the idea, not the text.
  • Same angle everywhere — all four cells lead with the same framing, so cross-platform followers see reruns. Recovery: step 2's inventory exists precisely for this — assign different lead ideas per cell and record the assignment in the output.
  • Video hooks written for the eye — subordinate clauses and semicolons nobody can speak. Recovery: read each hook aloud; if it takes a breath mid-sentence or sounds like prose, shorten to how a person actually talks.
  • Inventory drift — a matrix cell contains a claim that isn't in the source. Recovery: every cell cites its inventory idea number; audit each cell against its cited idea and cut anything the source doesn't support.

Verification

  • Idea inventory has 5–8 entries, each with a source reference
  • Every matrix cell cites which inventory idea it used; no two cells share a lead idea
  • No sentence appears verbatim in more than one cell or copied from the source
  • LinkedIn hook and X opener char-checked via python3 (counts reported)
  • All cells delivered as drafts; full-build handoffs to sibling skills noted

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most video audio skills give in ~1.3k tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

  • Read individual rule files for detailed explanationsin 21 of 622, across 10 files
  • Render final videoin 13 of 622, across 6 files
  • Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
  • Use this skill when dealing with Remotion codein 11 of 622, across 4 files
  • Save generated audio to a WAV filein 11 of 622, across 4 files
  • Handle conversion errors gracefullyin 10 of 622, across 6 files
  • Add captions to videos alwaysin 10 of 622, across 4 files
  • Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
  • Do not skip pipeline layersin 9 of 622, across 3 files
  • Do not make one tool do everythingin 9 of 622, across 3 files
  • Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
  • Never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

  • save full source text to a file
  • build a list of five to eight atomic ideas
  • base every matrix cell on the idea inventory
  • draft each cell in platform-native rhythm
  • assign a different lead idea to each cell
  • keep the LinkedIn hook under two hundred characters

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.