content-ops
Skill0 starsChanged 4 months agoMITView on GitHub
Writes platform-native social copy, hooks, hashtags, carousels, email sequences, and posting calendars, then scores drafts against platform rules before publishing. Use when writing captions, posts, threads, video titles, thumbnails, email sequences, or planning a content calendar for TikTok, Instagram, YouTube, X, LinkedIn, Pinterest, or Facebook.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- LazyIsEfficient/agentic-ostheir own version, first seen Oct 22, 2026
- matteotitta/claude-marketing-contenttheir own version, first seen Oct 20, 2026
- varunk130/ai-marketing-claude-skillstheir own version, first seen May 18, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- LazyIsEfficient/agentic-os★ 17same name
- varunk130/ai-marketing-claude-skills★ 1same name
- matteotitta/claude-marketing-content★ 0same name
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.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
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
- Distinctive: line 13
Do not write until these are known.
- Very specific: line 23
If the repo has a BRAND.md, VOICE.md, or similar, read it first and only ask for gaps.
- Distinctive: line 51
Read only what the task needs.
- Distinctive: line 70
Front-load the hook: Every platform truncates. The first line is the only line guaranteed to be read.
- Distinctive: line 77
One platform's best post is another's worst: Never reuse copy verbatim across platforms.
“Common” is measured: kept by at least 6 in 10 of the 3 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 Ops
Turn one idea into platform-native content, then check it before it ships.
First: establish voice
Do not write until these are known. Ask the user only for what is missing, in one message.
| Need | Why it matters |
| Who is posting | Determines authority and pronouns |
| What they sell or promote | Determines the soft CTA |
| Audience | Determines vocabulary and pain points |
| Tone | Determines sentence length and formality |
| Platforms | Determines format and constraints |
If the repo has a BRAND.md, VOICE.md, or similar, read it first and only ask for gaps.
Workflow
- [ ] 1. Establish voice (above)
- [ ] 2. Pick the platforms actually needed
- [ ] 3. Read references/platforms.md for those platforms only
- [ ] 4. Draft three variations of the highest-leverage asset
- [ ] 5. Score with scripts/critic.py
- [ ] 6. Fix what it flags, re-score, then deliverStep 5 is not optional. Drafts that skip it ship with avoidable reach penalties.
Scoring drafts
python3 scripts/critic.py --platform tiktok --file draft.txt
python3 scripts/critic.py --platform linkedin --text "your caption here"It checks length limits, reach-suppressing phrases, hashtag counts, hook strength, and CTA style, then prints a score with specific fixes. Exit code is non-zero when the draft would be penalized, so it can gate a publishing pipeline.
Reference material
Read only what the task needs.
| File | Contents |
| references/platforms.md | Per-platform format, length limits, hashtag rules, what suppresses reach |
| references/hooks.md | Hook formulas with worked examples, and why each works |
| references/hashtags.md | Tag-mix strategy, rotation, tags that hurt |
| references/seo.md | YouTube titles, app store listings, page SEO |
| references/email.md | Sequence structures: onboarding, launch, re-engagement |
| references/calendar.md | Cadence planning and repurposing one asset across platforms |
Rules that apply everywhere
Write three variations, not one. The user picks or A/B tests. A single draft is a guess presented as an answer.
Reference the actual content. Generic copy that would fit any video is worthless. Pull specific claims, moments, or numbers from the source material.
Front-load the hook. Every platform truncates. The first line is the only line guaranteed to be read.
Close with a question, not a command. Questions drive replies, which drive reach. Hard CTAs ("link in bio", "buy now") are penalized on most platforms. See references/platforms.md for the per-platform list.
One platform's best post is another's worst. Never reuse copy verbatim across platforms. Adapt format, length, and register every time.
Output
Deliver as markdown with one section per platform, three variations each, and the critic's score for the chosen variation. Write to a file only if the user asks, and ask where rather than assuming a path.
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.