social-carousel
Skill8 starsChanged 4 months agoMITView on GitHub
Turn a post, article, or idea into a complete slide-by-slide carousel script for Instagram or LinkedIn, with a hook cover, one-idea-per-slide content slides, a recap, and a CTA slide. Use when someone says "make a carousel", "carousel about", "slide deck post", or "LinkedIn document post". Every slide ships with its copy plus a design note and an image-generation prompt a designer or image model can execute directly. Instagram feed carousels and LinkedIn document posts follow different size, density, and cover conventions, so the script adapts to the platform chosen. Reads social-context.md for brand voice and audience setup so slides sound like the brand and land with the right readers.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- feimacode/open-design-agent-kittheir own version, first seen Nov 11, 2026
- thegentlehours/claude-skillstheir own version, first seen Nov 8, 2026
- shutckin/aivfx-content-kittheir own version, first seen Oct 8, 2026
- BryceYuuu/open-workflow-skillstheir own version, first seen Sep 5, 2026
- jpoindexter/theft-kittheir own version, first seen May 20, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- feimacode/open-design-agent-kit★ 1.1ksame name
- BryceYuuu/open-workflow-skills★ 1same name
- jpoindexter/theft-kit★ 1same name
- shutckin/aivfx-content-kit★ 1same name
- thegentlehours/claude-skills★ 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.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- idkSkill
- social-adSkill
- social-auditSkill
- social-calendarSkill
- social-checkSkill
- social-contextSkill
- social-crosspostSkill
- social-hookSkill
- social-postSkill
- social-replySkill
- social-repurposeSkill
- social-threadSkill
- social-voiceSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
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
- Very specific: line 28
Read social-context.md (also check .agents/social-context.md) before drafting.
- Very specific: line 36
If the file is missing, offer to run the social-context skill first — but do not block.
- Distinctive: line 55
Keep every note executable by someone who never read the source: "left-aligned headline top-third, iceberg illustration lower-right, the …
- Distinctive: line 74
No slide may require the previous slide to parse.
“Common” is measured: kept by at least 6 in 10 of the 4 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
Given source material or a topic, produce a full carousel script — cover hook, 6–10 content slides, recap, CTA — with a design note and image prompt per slide.
Context
Read social-context.md (also check .agents/social-context.md) before drafting. You need:
- Brand voice: vocabulary, capitalization habits, whether slides may joke
- Audience: expertise level, which determines how much a single slide can assume
- The Never list, if present: red lines that disqualify a slide or a caption
social-context.md does not carry visual identity, so ask the user directly for colors, type feel, and illustration-vs-photo — one question alongside the platform question in step 1.
If the file is missing, offer to run the social-context skill first — but do not block. Ask two or three quick questions inline (Instagram or LinkedIn? Who reads this? Any visual style words — minimal, bold, hand-drawn?) and proceed.
Workflow
- Ask the platform first. Instagram (1080×1350 portrait, tap-through, big type) and LinkedIn (document/PDF, often landscape or square, denser text tolerated) are different media. Do not draft a generic script and relabel it. If the user already named the platform, skip ahead.
- Extract one narrative arc from the source. A carousel carries exactly one argument: problem → tension → resolution, or claim → evidence → payoff. If the source contains three arguments, pick the strongest and say which two you dropped.
- Write the cover slide. It is a hook, not a title: eight words or fewer of large text, optionally a small kicker line. "5 onboarding mistakes" is a title; "Your onboarding is losing users on day one" is a cover. The cover must work as a standalone feed image, because that is how most people will encounter it.
- Outline the content slides before writing them. One idea per slide, in escalating order — strongest point second-to-last, never first. Instagram: 6–8 content slides. LinkedIn: 8–10 is fine; readers expect more substance in a document post. Show the outline as one line per slide and let the user cut or reorder before you invest in full drafts.
- Draft each content slide at ≤25 words. Constraints that keep slides swipeable:
- Self-contained: each slide parses without its neighbors, because screenshots travel alone.
- Pull-through: end slides on tension or an open loop where the material allows it.
- Front-load the slide's noun; no slide begins with "Also", "And", or "Another thing".
- One number or one image concept per slide — a slide that needs both is two slides.
- Write the recap slide. Compress the arc into 3–5 checklist lines the reader can screenshot. This is the most-saved slide; make it worth saving.
- Write the CTA slide. Instagram: ask for a save or a share ("Save this for your next launch"), plus follow. LinkedIn: ask a discussion question that invites comments, plus follow. One ask primary, never three equal asks.
- Attach a design note to every slide. Three parts, all concrete:
- Layout — text position, alignment, margins ("headline top-third, left-aligned, generous bottom margin").
- Visual metaphor — the one image or diagram that carries the idea ("iceberg with 'signup' above the waterline, 'activation' below").
- Text placement — what is large, what is small, and the single emphasis word or number that gets the accent treatment. Keep every note executable by someone who never read the source: "left-aligned headline top-third, iceberg illustration lower-right, the phrase 'day one' in accent color".
- Attach an image-generation prompt to every slide that a designer or image model can run as-is:
- Subject and composition ("flat illustration of a doorway with a welcome mat, centered, seen straight-on")
- Style and palette hint, consistent across all slides — one visual system, not ten
- The explicit instruction to leave clear negative space where the slide text sits
- Swipe-check the whole script. Read only the slide texts in order, ignoring the design notes. The argument must survive on copy alone; if it does not, fix the copy, not the visuals. Then check the reverse: would the visuals alone tell roughly the same story? Finally, check the full script and the caption against every row of the Quality bar and against the Never list — fix any slide or caption that fails a row or trips a red line.
- Write the accompanying caption or post text last. Its first line is a second hook (do not repeat the cover verbatim); it adds one piece of context the slides omit, then hands off: "swipe through".
Quality bar
| Canvas | 1080×1350 (4:5 portrait) | Document/PDF; square or landscape pages |
| Total slides | 8–10 (cover + 6–8 + recap + CTA) | 10–12 (cover + 8–10 + recap + CTA) |
| Words per slide | ≤25, display-sized type | ≤25 headline; a short support line is acceptable |
| Cover | Feed-stopping image + ≤8 words | Bold typographic cover; reads at thumbnail size |
| Hashtags | In the caption, never on slides | None on slides; 0–3 in the post text |
- Text on slides must be legible at thumbnail size — if a design note implies more than ~3 lines of large text, split the slide.
- No slide may require the previous slide to parse.
- Numbers, arrows, and simple diagrams beat stock-photo metaphors.
- One emphasis element per slide: a single accent word, number, or arrow — two emphases is zero emphases.
- Slide transitions earn the swipe: at least a third of content slides should end on tension or an open loop.
- Alt-text-friendly: every image prompt describes a concrete scene, not "abstract vibes".
- The recap slide is screenshot bait — checklist formatting, no new information, no cleverness.
Deliverable
Return, in order:
- One line naming the platform, the narrative arc, and the slide count.
- The script as a numbered list, one block per slide: Slide N — [role], then Text: (the exact copy), Design: (layout + metaphor + text placement), Image prompt: (ready to run as-is).
- The post caption (Instagram) or post text (LinkedIn), hook line first.
Nothing else — end there.
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.

