agentleFS
juju-wjuju-w/card-creator-skill/AGENTS.md

card-creator-skill

AGENTS.md11 starsChanged 26 days agoMITView on GitHub

This repository is intentionally limited to the card-creator Codex skill.

  • 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 33,315 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 repositoryOne other file it gives its agents.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Do not add a web application, online editor, database, auth system, or deployment runtime unless the user explicitly reopens platform work.

    line 5
  2. Very specific:

    Keep the short aspect-ratio and layout guidance in references/card-rules.md as the single source of truth.

    line 6
  3. Distinctive:

    Keep the installed skill script-free.

    line 11
  4. Very specific:

    Every reference picture must have a concrete index entry and a source record in root-level SOURCES.md, including inherited attribution.

    line 12
  5. Very specific:

    Test packaging and reference coverage, and validate the skill with quick_validate.py before handoff.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Repository Instructions

This repository is intentionally limited to the card-creator Codex skill.

  • Do not add a web application, online editor, database, auth system, or deployment runtime unless the user explicitly reopens platform work.
  • Keep the short aspect-ratio and layout guidance in references/card-rules.md as the single source of truth.
  • Image generation is the default and only card-art creation path. Do not draw card artwork with SVG, HTML, Canvas, or deterministic logo compositing.
  • PNG logo files are visual references for ImageGen, not stickers to paste onto the finished card. Open only references relevant to the requested card.
  • AI may transform or redraw a payment, transit, bank, or city-card logo as part of an artistic card-face composition. Label the result as a non-official stylized interpretation and never claim brand-guideline accuracy, authorization, interoperability, or endorsement.
  • Contactless/payment indicators are opt-in only. Do not add one unless the user explicitly requests it, and distinguish generic decorative NFC motifs from exact licensed acceptance marks.
  • Keep the installed skill script-free. Packaging and repository checks may live outside it; never add a card-rendering or export pipeline.
  • Every reference picture must have a concrete index entry and a source record in root-level SOURCES.md, including inherited attribution. Keep source histories and disclaimers outside the installed Skill. Preserve required third-party attribution in PNG metadata as well for standalone installs.
  • Test packaging and reference coverage, and validate the skill with quick_validate.py before handoff.

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.