agentleFS
TJM-NZTJM-NZ/claude-skills/design-system/SKILL.md

design-system

Skill0 starsChanged 10 days agoMITView on GitHub

Establish or audit a project's design foundations - colour, type, spacing, shape, elevation, motion and core component states - as layered tokens with contrast checked in light and dark. Produces a short reference doc and applies it through the project's own token mechanism.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-level and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +2 more from CoralGame
  • +6 more from lilangMax

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Ask only what the repo can't answer: audience and mood, brand assets that must be kept (logo colours, fonts), platforms, themes needed …

    line 32
  2. Distinctive:

    If a look already exists and works, codify it with improvements.

    line 34
  3. Distinctive:

    Verify (build, light and dark screenshots if a browser is available, leftover hard-coded values).

    line 46
  4. Distinctive:

    Don't change visual design as a side effect of an audit.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 175 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

Establish the visual foundation every later design task builds on. Run once per project, or to recalibrate. Present a draft for approval before writing any file or touching any style.

Modes: Create (no system yet) | Audit (styles exist but are inconsistent) | Extend (add dark mode, density, motion, a new component family). Infer from the repo; ask if unclear.

Related: design consumes the system | accessibility audits the result | de-slop finds generic defaults | copywrite voice.md for a matching verbal voice.

Step 1: Context

Read product docs and any existing design, convention or voice docs. Detect how styling is done: utility CSS config (Tailwind and similar), CSS custom properties, CSS modules, CSS-in-JS theme, a component library theme, or native/platform styles. Express tokens in the project's existing mechanism. Don't add a parallel system.

Step 2: Audit what exists

Count distinct values per category across stylesheets and 5-10 key components:

grep -rhoE '#[0-9a-fA-F]{3,8}\b|rgba?\([^)]*\)|hsla?\([^)]*\)' <src> | sort | uniq -c | sort -rn | head -40
grep -rhoE 'font-size: *[^;]+|border-radius: *[^;]+|box-shadow: *[^;]+' <src> | sort | uniq -c | sort -rn | head -40

Adapt the patterns to the stack (utility classes, theme objects). Report the number of distinct colours, font sizes, radii, shadows and spacing values, and the clearest inconsistencies (three greys for muted text, two radii on cards). Those are what the system fixes. Note existing contrast failures.

Step 3: Brief

Ask only what the repo can't answer: audience and mood, brand assets that must be kept (logo colours, fonts), platforms, themes needed (light, dark, both), density (data-heavy tool vs marketing site), accessibility target (default WCAG 2.2 AA).

If a look already exists and works, codify it with improvements; don't replace it with something unrecognisable.

Step 4: Draft the system

Load references/foundations.md (tokens, colour, type, spacing, shape, elevation, motion, layout) and references/components.md (states and patterns). For every colour pairing, run the contrast check in foundations.md and put the results in the draft.

Step 5: Present, refine, save

Load references/output.md. Show the full draft with a swatch or sample for each decision and the contrast results. Refine with the user. After approval:

  1. Save the reference doc in the project's docs location and add a pointer in its agent or context file.
  2. Apply the tokens to the project's mechanism. Only with approval, and in batches.
  3. Verify (build, light and dark screenshots if a browser is available, leftover hard-coded values).

Rules

  • Specific values, not "a nice blue".
  • Name by role, not value. action, not blue-600; roles survive palette changes.
  • Contrast is checked, not assumed, in both themes.
  • Restraint is a decision, not a rule. Each extra colour, typeface or radius must earn its place by a distinct job.
  • Keep the doc under 150 lines. One nobody reads is worse than none.
  • Don't change visual design as a side effect of an audit. Report first.

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.