agentleFS
Sign inStart free
authrain-cloud-abdullahformuliauthrain-cloud-abdullahformuli/carousel-builder/AGENTS.md

carousel-builder

AGENTS.md0 starsChanged 43 days agoMITView on GitHub

This repository contains the Carousel Builder plugin, commands, and open skills standard implementation for building branded Instagram carousels and high-converting short-form captions end-to-end directly in AI coding CLIs (Claude Code, Cursor, Codex, OpenCode, Antigravity CLI). Maintained by Abdullah Formuli (@abdullahformuli).

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Never commits until the user reviews and confirms the preview link.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.

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

Carousel Builder — AI Coding Agent Guide

This repository contains the Carousel Builder plugin, commands, and open skills standard implementation for building branded Instagram carousels and high-converting short-form captions end-to-end directly in AI coding CLIs (Claude Code, Cursor, Codex, OpenCode, Antigravity CLI).

Maintained by Abdullah Formuli (@abdullahformuli).

Core Concepts & Invariants

  1. Character Budget Enforcement:
    • Pillar headlines: 45–58 characters (exactly one highlighted orange word).
    • Pillar body: 65–80 characters (ending with one word in ALL CAPS).
    • Cover headline: ≤ 22 characters.
    • Cover subtext: 3–4 short italic lines.
    • Captions: ≤ 500 characters hard cap total (including CTA, body, and exactly 5 hashtags).
  2. Image Consistency (Higgsfield MCP):
    • Cover image generated at 4:5 aspect ratio.
    • Chosen cover is passed as reference to all pillar images (16:9 aspect ratio) to lock theme, palette, and lighting without visual drift.
  3. Canva Assembly (Canva MCP):
    • Duplicates the 8-page template.
    • Updates text spans in-place without breaking formatting.
    • Updates images with update_fill so the frame glow styling remains intact.
    • Never commits until the user reviews and confirms the preview link.

Directory Structure

PathPurpose
commands/carousel.mdClaude Code /carousel command prompt
commands/short-form-caption.mdClaude Code /short-form-caption command prompt
skills/carousel-builder/SKILL.mdUniversal Open Agent Skill (agentskills.io standard)
skills/short-form-caption/SKILL.mdUniversal Open Agent Skill for captions
config/Brand context and voice fingerprint templates
examples/template-reference/8-slide reference deck images (1.png - 8.png)
index.htmlLive interactive carousel preview & character budget validator
.claude-plugin/Claude Code plugin and marketplace manifests

Development & Testing

# Run local verification test
node test.mjs

# Serve the web preview
npx serve -l 8080 .

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.

Check your setup, free