agentleFS
Sign inStart free
codeotter0201codeotter0201/design-system-skills/AGENTS.md

design-system-skills

AGENTS.md0 starsChanged 7 days agoMITView on GitHub

For agents and developers maintaining this repository. Two skills in the Agent Skills format: Run after every change: With Docker, also run the tests on Linux:

  • 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 31,439 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 repository3 other files it gives its agents.

The file

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

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not name tools from a particular agent harness (such as a specific Read or Edit tool).

    line 25
  2. Very specific:

    Must run on the bash 3.2 that ships with macOS (BSD grep, BSD awk) and on Linux (bash 5, GNU grep, mawk or gawk): no associative arrays, no …

    line 32
  3. Very specific:

    When you add or change a check, update tests/design-check/fixtures/ and the expectations in run.sh.

    line 33
  4. Distinctive:

    Run after every change:

    line 37

≈ “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

AGENTS.md

For agents and developers maintaining this repository.

What this repository is

Two skills in the Agent Skills format:

  • skills/design-system-build: creates, adopts, extends and updates a design system, and builds pages by page type.
  • skills/design-system-review: reviews UI changes against the design system and keeps the two in sync.

Editing rules

Skill format

  • name: lowercase letters, digits and hyphens, 1–64 characters, no leading or trailing hyphen, no consecutive hyphens, identical to the directory name.
  • description: 1–1024 characters, covering both what the skill does and when to use it, with the keywords users are likely to say.
  • metadata values are always strings.
  • SKILL.md stays under 500 lines. Details go in references/, linked only one level deep.
  • Templates and scripts live in the skill's own assets/ or scripts/. Installers copy only the skill directory, so files anywhere else in the repository are missing after installation.

Content

  • Everything is written in English.
  • Do not name tools from a particular agent harness (such as a specific Read or Edit tool); any agent must be able to follow the instructions. External tools are always optional: "use it when available; otherwise do this by hand".
  • Templates contain only structure and TODO(design) placeholders, never aesthetic defaults (typefaces, palettes, radius values).
  • Documents describe the current state only. No "previously…" notes or version comparisons; history lives in git.
  • Both skills must describe shared concepts the same way (path conventions, the TODO(design) marker, how findings are classified). When you change one, search the other for the same content.

design-check.sh

  • Must run on the bash 3.2 that ships with macOS (BSD grep, BSD awk) and on Linux (bash 5, GNU grep, mawk or gawk): no associative arrays, no grep -P, no awk interval expressions ({3}).
  • When you add or change a check, update tests/design-check/fixtures/ and the expectations in run.sh.

Validation

Run after every change:

python3 scripts/validate_skills.py
tests/design-check/run.sh
tests/design-check/run.sh /bin/bash

With Docker, also run the tests on Linux:

docker run --rm -v "$PWD":/repo:ro -w /repo debian:stable-slim tests/design-check/run.sh

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