content-repurposer
Skill1 starsChanged 3 months agoMITView on GitHub
Turn one piece of existing content into multiple platform-specific outputs. Use when the operator says 'repurpose this', 'turn this into posts', 'tweet thread from this', 'atomize', 'content from this transcript', or provides any long-form content to distribute across channels. REQUIRES source content as input — for a new post from scratch use social-media-manager. Outputs are copy-paste ready per platform.
29 other projects use a version of this.
Adopted by
Most recently taken up by
- imtiazrayhan/agentscamp-librarytheir own version, first seen Nov 16, 2026
- milad-ahmd/content-repurposertheir own version, first seen Nov 1, 2026
- Insightful-Pipe/social-media-skillstheir own version, first seen Nov 1, 2026
- milad-ahmd/agent-skillstheir own version, first seen Nov 1, 2026
- irinabuht12-oss/marketing-skillstheir own version, first seen Oct 27, 2026
- ARCASSystems/FounderOStheir own version, first seen Oct 24, 2026
Used with
Projects with it also use landing-page-copywriter, research-synthesizer and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
julianromliSkilllanding-page-copywriter
Write high-converting landing page copy using proven frameworks like PAS (Problem-Agitate-Solution), AIDA, and StoryBrand. Creates headlines, value propositions, CTAs, and full page sections optimized for conversion. Use when users need landing page copy, sales page content, or marketing website text.
Also in 4 projects that use this
o2alexanderfedinSkillresearch-synthesizer
Creates comprehensive synthesis documents distilling research findings into actionable insights. Activates when: creating synthesis.md files, aggregating research findings, integrating multi-source data, extracting strategic insights, or resolving conflicting information. Operates across technical, market, architecture, certification, and roadmap domains. Ensures evidence-based synthesis with full traceability to source research files.
Also in 3 projects that use this
raroqueSkillyoutube-script-writer
Write a tight, retention-focused YouTube script from a topic, outline, or research brief. Use when the user asks for a video script, wants to turn notes or research into a YouTube video, needs a hook/intro rewritten, or wants to plan a video end-to-end with pacing, visual beats, and CTAs.
Also in 3 projects that use this
Marine-softdrink524Skillseo-blog-writer
SEO-optimized blog post writer with expertise in keyword research, content structure, meta tags, and search engine ranking strategies. Use when creating blog posts, articles, or any content that needs to rank well on Google.
Also in 3 projects that use this
ncklrsSkillproposal-writer
Expert sales proposal and pricing presentation strategist. Use when writing proposals, executive summaries, ROI business cases, pricing presentations, SOWs (Statement of Work), RFP responses, or competitive positioning documents. Covers proposal structure, terms positioning, design formatting, follow-up strategy, and win-rate optimization.
Also in 4 projects that use this
Other versions29 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 29
- irinabuht12-oss/marketing-skills★ 6.5ksame name
- Affitor/affiliate-skills★ 757same name
- Ootto-AI/claude-content-skills★ 417same name
- OneWave-AI/claude-skills★ 378same name
- hamzafarooq/claude-code-starter★ 145same name
- marcosmodly/marketing-skill★ 141same name
- aircrushin/promptMinder★ 117same name
- travisjneuman/.claude★ 106same name
- OpenAnalystInc/10x-Content-Expert★ 15same name
- legioncodeinc/littlebird-skills★ 8same name
19 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- access-transfer-trackerSkill
- ai-3d-generatorSkill
- ai-asset-generatorSkill
- ai-demo-builderSkill
- apple-grade-designSkill
- brand-guide-builderSkill
- client-onboardingSkill
- cold-email-campaignSkill
- cold-emailSkill
- company-teardownSkill
- competitive-ads-extractorSkill
- content-calendarSkill
- content-research-writerSkill
- content-strategySkill
- daily-briefSkill
- discovery-call-prepSkill
- email-composerSkill
- follow-up-nurtureSkill
- gbp-local-seoSkill
- hormozi-100m-leadsSkill
- interactive-website-builderSkill
- invoice-trackerSkill
- lead-flow-verifierSkill
- lead-scraperSkill
- mcp-integrationSkill
- meeting-listenerSkill
- post-purchase-email-seriesSkill
- productization-journalSkill
- proposal-generatorSkill
- prospect-workupSkill
- regulated-copy-complianceSkill
- retainer-reportingSkill
- review-managerSkill
- scroll-demo-builderSkill
- seo-auditSkill
- site-launch-cutoverSkill
- site-qa-checklistSkill
- social-media-auditorSkill
- social-media-managerSkill
- social-video-producerSkill
- stylized-3d-worldbuildingSkill
- video-analyzerSkill
- web-researchSkill
- website-builderSkill
- weekly-client-checkinSkill
- welcome-email-seriesSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
No source content exists (post from scratch) → social-media-manager
- Distinctive: line 29
If the client operates in a regulated space (financing offers, health claims, legal services), run their compliance checklist over every …
- Distinctive: line 43
Read the voice source for the chosen mode.
- Distinctive: line 61
Rules: never open with "I'm excited to share..." or "In today's fast-paced world...".
- Distinctive: line 62
Write like a person, not a brand account.
- Distinctive: line 70
No tweet may depend on the previous one to make sense.
- Distinctive: line 109
If <TASK SYSTEM> tasks exist for these calendar slots, attach the draft location and move status to Review.
- Distinctive: line 111
If not, create one task per output batch, due on the intended post date, notes pointing at the saved file.
- Distinctive: line 122
When repurposing, create the long-form version first, then extract shorts from it.
“Common” is measured: kept by at least 6 in 10 of the 26 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.
Files
Content Repurposer
One input → multiple platform-ready outputs. No extra writing sessions needed.
Routing
- No source content exists (post from scratch) →
social-media-manager - Long-form written from scratch with research →
content-research-writer - Deciding WHAT to post and when →
content-calendar - This skill = the operator provides a transcript, blog post, case study, call summary, or raw idea and wants platform outputs from it.
Step 0 — Who is this for?
Confirm the mode before writing anything:
- Own-business mode — your content, your voice. Save under
ventures/<venture-slug>/deliverables/content/. - Client mode — voice source is
clients/<client-slug>/brand/brand.md(always check the client's brand folder before building anything). Save underclients/<client-slug>/deliverables/content/.
If the client operates in a regulated space (financing offers, health claims, legal services), run their compliance checklist over every output before delivery.
Step 1 — Analyze the input
Extract from the source:
- Core insight — the one big idea every output orbits
- Key quotes/phrases — anything punchy enough to stand alone
- Data points — numbers, results, names, places (real ones only — never invent)
- Story elements — before/after, lesson learned, unexpected outcome
- Audience relevance — why does the target reader care?
Step 2 — Load the voice
Read the voice source for the chosen mode. Defaults if none exists (ask before assuming):
- Straightforward, no corporate-speak; gets to the point
- Real examples over abstract concepts; speaks from experience
- Confident without arrogance; no emojis unless the brand uses them
- Education-first — teach something useful in every output
- Narrow beats wide — each output speaks to one specific reader
- Assume nothing — every output works standalone for a first-time reader
Step 3 — Generate outputs
LinkedIn post
Length: 150-300 words. Structure: Line 1 = scroll-stopping hook (bold claim, specific number, counterintuitive insight) — it must work alone, it's all people see before "...see more". Empty line 2. Then story/context, one idea per line, short paragraphs. End with takeaway + CTA (question, follow, comment prompt). Last line: 3-5 hashtags. Rules: never open with "I'm excited to share..." or "In today's fast-paced world...". Write like a person, not a brand account. Specific beats clever — "we signed a client from one cold email" beats "cold email works if you do it right".
X/Twitter thread (3-7 tweets)
Tweet 1: the hook — must deliver standalone value. Tweets 2-6: one idea each, under 280 characters, specifics (names, numbers, tools), "→" or numbered lists for structure. Final tweet: restate the core idea + CTA ("Follow for more [topic]" / "Bookmark this"). No tweet may depend on the previous one to make sense.
Email newsletter block
Length: 200-400 words. Structure: 1-2 sentence personal intro → main insight in 2-3 short paragraphs → how it applies to the reader → one CTA. Provide 3 subject line options — short, curiosity-driven, no caps or punctuation tricks.
Blog post (only when requested)
Length: 800-1,500 words. Structure: H1 with target keyword; hook opening, no throat-clearing; 3-5 H2 sections with practical takeaways; specific examples from the business's real work; closing CTA tied to the relevant service. SEO basics: keyword in H1 and first 100 words; meta description under 160 characters; internal links to service pages.
Instagram/Facebook caption (only when requested)
Length: under 150 words. Hook line → brief insight → CTA. Include an image-concept suggestion (what visual pairs with this).
Step 4 — Save and present
Save all outputs to one file in the mode's content folder (mkdir -p on first use):
<mode-folder>/<YYYY-MM-DD>-<topic-slug>.md, one section per platform.
Present everything for review. The operator picks what posts and when.
Step 5 — Log it
Append to <mode-folder>/content-log.md:
| Date | Topic | Platforms | Status |
|------|-------|-----------|--------|Then push into the execution layer (mirrors content-calendar):
- If
<TASK SYSTEM>tasks exist for these calendar slots, attach the draft location and move status to Review. - If not, create one task per output batch, due on the intended post date, notes pointing at the saved file.
- Client mode: log the deliverable in the client's record before closing out.
Format strategy
Short-form (reels, tweets, carousels) = distribution/awareness — appetizers. Long-form (blog, newsletter, video) = conversion engine — the meal.
When repurposing, create the long-form version first, then extract shorts from it. Shorts drive traffic to longs; longs build enough trust to buy.
Suggested cadence (operator decides timing)
- LinkedIn: Tue or Wed morning · X/Twitter: Tue + Thu, threads in the morning
- Newsletter: weekly or bi-weekly, Friday morning · Blog: 1-2/month
- Long-form video: 1/week minimum if video is an active channel
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
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.

