agentleFS
authrain-cloud-abdullahformuliauthrain-cloud-abdullahformuli/carousel-builder/skills/carousel-builder/SKILL.md

carousel-builder

Skill0 starsChanged 43 days agoMITView on GitHub

Build branded Instagram carousels end-to-end: Higgsfield generates a theme-locked cover + middle images, character budgets keep copy on-template, and Canva assembles the deck.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    Write all slide text + per-slide image prompts into a markdown file with locked character budgets.

    line 10
  2. Distinctive:

    Check Canva template ID and brand context configuration.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 6 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Carousel Builder

Build an Instagram carousel end-to-end:

  1. Generate slide-1 cover image with Higgsfield MCP (4:5).
  2. Write all slide text + per-slide image prompts into a markdown file with locked character budgets.
  3. Generate theme-matched 16:9 images for the middle slides (passing the chosen cover as reference).
  4. Assemble the deck by duplicating a fixed Canva template and replacing text spans and image fills.
  5. Finish by running /short-form-caption for the post copy.

Requirements

  • Higgsfield MCP: nano_banana_2 model for cover and pillar images.
  • Canva MCP: https://mcp.canva.com/mcp for templated deck assembly.
  • Canva Template: 8-page carousel template.

Character Budgets (Hard Caps)

  • Pillar headline: 45–58 characters (including The [Role]:, exactly 1 highlighted word).
  • Pillar body: 65–80 characters (ends with 1 word in ALL CAPS).
  • Cover headline: ≤ 22 characters.
  • Cover subtext: 3–4 short italic lines.
  • Caption: ≤ 500 characters total with exactly 5 hashtags.

Workflow Execution

  1. Check Canva template ID and brand context configuration.
  2. Interview the topic into 4–6 pillars and CTA keyword.
  3. Generate 3–4 4:5 cover options with Higgsfield; user selects the anchor.
  4. Draft copy and validate character counts before image generation.
  5. Generate 16:9 pillar images using the chosen cover as style reference.
  6. Assemble in Canva via duplicate and update_fill.
  7. Generate copy-paste caption with short-form-caption skill.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.