agentleFS
Sign inStart free
ucsandmanucsandman/claude-skills/og-assets/SKILL.md

og-assets

Skill5 starsChanged 2 months agoMITView on GitHub

Use when the user wants OG images, link-preview assets, animated OG loops, README GIFs, or social-card exports for any product (e.g. "/og-assets", "make an OG image and README gif").

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the hero PNG: dark, on-brand hue, no text/people/off-brand colors.

    line 21
  2. Very specific:

    Run the brand's statics renderer with --project <product>.

    line 23
  3. Distinctive:

    Verify one still (lockup sharp, CTA in the brand's positive color) + readme.gif legibility (extract frame 0 via ffmpeg if the gif exceeds …

    line 28
  4. Very specific:

    Run verify-og-wired <brand> --project <product> after deployment, then deliver per marketing-studio.

    line 32

≈ “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.

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

OG Assets

REQUIRED BACKGROUND: marketing-studio skill; also read C:/Projects/animations/docs/playbook/remotion.md. Work in C:/Projects/animations.

Produces product-owned og.mp4, og.gif, readme.gif, and social-card exports under <product>/marketing/assets/<brand>/, optionally backed by an approved ComfyUI texture.

Recipe

  1. Toolchain + brand check per marketing-studio. Background loop staged for the brand (Blender background_loop scene; seam rules in C:/Projects/animations/docs/playbook/remotion.md) — or run with it null.
  2. Optional AI hero: node feeders/comfy/client.mjs hero --project <product> --brand <brand> [--seed N] (needs ComfyUI Desktop up + a checkpoint; exit 2 = fine, procedural fallback is spec-compliant). Read the hero PNG: dark, on-brand hue, no text/people/off-brand colors; re-roll seeds until it passes. Prompt lives in the client; adapt per brand.
  3. Run the brand's statics renderer with --project <product>; it writes product-owned props/output and passes the workspace public directory to Remotion. The AnimatedOG loop is SEAMLESS by construction — if you touch the template, every animated value must stay periodic over the full duration (loop rules in C:/Projects/animations/docs/playbook/remotion.md).
  4. Verify one still (lockup sharp, CTA in the brand's positive color) + readme.gif legibility (extract frame 0 via ffmpeg if the gif exceeds Read limits).
  5. Size check: GIFs are heavy; prefer og.mp4 for social embeds. For READMEs going to GitHub keep the gif under ~10MB (--every-nth-frame=3, lower --scale).
  6. Run verify-og-wired <brand> --project <product> after deployment, then deliver per marketing-studio. This is a live wiring check, not permission to deploy.

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