content-studio
Skill1 starsChanged 8 days agoMITView on GitHub
Use for any content creation request when it is not obvious which skill applies, or when one idea must become several formats: posts, carousels, stories, thumbnails, memes, GIFs, LinkedIn documents, slides, threads, long posts, newsletters, reels, launch videos, explainers, animations, edited footage, clips, podcasts, screen recordings, live streams, AI images, AI video, voice, music. Routes each part to social-content-studio, motion-video-studio, footage-edit-studio or generative-media-studio, and plans a campaign across formats from one story.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- CatCatUncle/openworkbuddytheir own version, first seen Nov 5, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- CatCatUncle/openworkbuddy★ 398same 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.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- footage-edit-studioSkill
- generative-media-studioSkill
- motion-video-studioSkill
- social-content-studioSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Every skill reviews the exported file, not the code or the prompt.
- Distinctive: line 46
Ask before anything outward or paid: publishing, uploads to cloud services, paid generation, accounts.
≈ “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.
Files
Content Studio
One package for every kind of content. This skill decides which skill does what, in which order, and keeps one story, one brand and one set of facts across all the pieces.
Route the request
| The user wants | Skill | Reference to open first |
| A post, carousel, story, status, quote card, infographic, flyer | social-content-studio | references/static-production.md |
| A YouTube thumbnail, a cover for a reel, short or podcast | social-content-studio | references/formats.md |
| A meme, reaction image, sticker, GIF | social-content-studio (static), motion-video-studio (animated GIF from code) | references/formats.md |
| A LinkedIn document carousel (PDF), slides, a deck | social-content-studio | references/formats.md |
| A thread, a long post, a LinkedIn article, a newsletter, a blog post, captions and comments | social-content-studio | references/text-formats.md, references/voice-and-hooks.md |
| A reel, ad, launch film, explainer, UI animation, kinetic type, data story, logo reveal, animated captions or lower thirds, made from code | motion-video-studio | references/story-and-spec.md |
| Editing real footage: rough cut, silences, captions, music, reframing, clips from a long video | footage-edit-studio | references/cutting.md |
| A podcast (audio or video), an audiogram | footage-edit-studio | references/podcasts-and-recordings.md |
| A screen recording, product demo, live stream, clips from a VOD | footage-edit-studio | references/podcasts-and-recordings.md |
| An AI-generated image, video clip, avatar, voice-over, cloned voice, music, sound effect, dubbing | generative-media-studio | the medium's reference |
| Text that reads as AI, a design that looks generated | unslop-anything, if installed |
When a piece needs two skills, the one that owns the final deliverable leads, and the others supply assets: a launch film is motion-video-studio with a voice-over and generated b-roll from generative-media-studio; a carousel with a generated product scene is social-content-studio with one image from generative-media-studio.
One idea, many formats
For a campaign or a launch, plan the set before producing any piece:
- One story. Goal, reader, one idea, the real facts and the action wanted, settled once (
social-content-studio, Gate A). Every piece takes its claims from the same facts file. - One brand profile. Colors, fonts, logo files, voice, banned defaults, in one file next to the project, used by every skill.
- A format plan. Which pieces, for which platform, in which order, and what each one does: for example a 25 s launch film (hook on the result), its 9:16 and 1:1 versions, a 7-slide carousel that explains the how, a thread with the story behind it, five clips from the founder's recorded demo, a thumbnail, a newsletter section. Each piece is adapted to its platform, not stretched or cropped from another.
- Shared assets first. Generate or prepare what several pieces reuse (product shots, the voice-over, the music bed, the key frame) once, log them, and approve them before building the pieces.
- Produce, then review each piece with its own skill's checks.
- Deliver the set: files per platform, copy and captions per piece, credits, AI labels where they apply, and a publishing order. Publishing and scheduling need the user's explicit yes.
Rules for the whole package
- Real assets and real facts beat generated ones; nothing is invented.
- The brand profile and the user's corrections win over any default in the skills.
- Every skill reviews the exported file, not the code or the prompt.
- Ask before anything outward or paid: publishing, uploads to cloud services, paid generation, accounts.
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.