agentleFS
SamRome1SamRome1/showrunner/.claude/skills/assets/SKILL.md

assets

Skill1 starsChanged 2 months agoMITView on GitHub

Run the assets batch for a brief — add each official logo to assets.json, fetch into public/assets/, render the AssetCheck contact sheet, report, and stop. Use when a brief's asset list is ready or the user types /assets.

9 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, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 0

    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
  1. Very specific:

    Read the brief in docs/briefs/ and list every asset it names.

    line 6
  2. Very specific:

    Add entries to assets.json (file, url, note).

    line 8

“Common” is measured: kept by at least 6 in 10 of the 7 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
  1. Read the brief in docs/briefs/ and list every asset it names.
  2. For each: query https://api.svgl.app?search=<name> and pick the variant the brief asks for (_dark routes are the light marks for dark canvases). Fall back to the company brand kit, then https://cdn.simpleicons.org/<slug>. If nothing official exists, STOP and ask — never draw a substitute.
  3. Add entries to assets.json (file, url, note). Run npm run setup.
  4. Inspect each file's fill colors (grep -oE 'fill="[^"]+"') to confirm the variant.
  5. Render npx remotion still AssetCheck out/asset-check.png, view it, and confirm every mark reads on the canvas background.
  6. Reply with a table of requested asset → file → variant, note anything surprising, and stop. Do not build scenes until the user says go.

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.