agentleFS
NiseelNiseel/ai-sdlc-starter/.claude/skills/design-system/SKILL.md

design-system

Skill1 starsChanged 58 days agoMITView on GitHub

The project's UI design system (rules, tokens, component recipes in design-system/). Use BEFORE creating or changing any UI - HTML, CSS, JSX/TSX, Vue/Svelte templates, Tailwind classes, landing pages, emails, charts. Also use to build or rebuild the design system from a reference website URL.

193 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

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

  • 0

    Common

    Most of the 176 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the request is a URL, go to B.

    line 15
  2. Very specific:

    Read design-system/DESIGN.md before writing markup or styles.

    line 19
  3. Distinctive:

    Before you finish, run the check and fix every hit:

    line 27
  4. Distinctive:

    Check the page at 375 px and 1440 px wide.

    line 31
  5. Very specific:

    Ask before overwriting an existing design-system/.

    line 35
  6. Very specific:

    Extract: - run the extract-design skill on the URL.

    line 38
  7. Very specific:

    Fonts: - if the source font is commercial, pick the closest Google Font that has every subset the project needs (for this repo: vietnamese).

    line 43
  8. Distinctive:

    Do / Don't, Gaps).

    line 54

“Common” is measured: kept by at least 6 in 10 of the 176 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

Design system

Files (source of truth, in this order):

  • design-system/DESIGN.md - rules and design language. Read it fully first.
  • design-system/tokens.css - every allowed color, font, size, space, radius, shadow, gradient, motion value.
  • design-system/components.css - base styles and component recipes built only from tokens.

Request: $ARGUMENTS

If the request is a URL, go to B. Build. Otherwise go to A. Apply.

A. Apply (every UI change)

  1. Read design-system/DESIGN.md before writing markup or styles.
  2. Load tokens.css then components.css in the page or app entry. Use the recipes (.btn, .tag, .card, .stat, ...) before writing new CSS.
  3. Style only with var(--token). No raw hex/rgb, font names, font sizes, radii, shadows or durations outside tokens.css. Layout-only values (grid tracks, widths of one element) are fine.
  4. A need the tokens do not cover: use the closest token, then report the gap in your reply and append it to the "Gaps" list in DESIGN.md. Never invent a token silently.
  5. Before you finish, run the check and fix every hit:
    grep -nE '#[0-9a-fA-F]{3,8}\b|rgba?\(' <changed files other than design-system/*>
  6. Check the page at 375 px and 1440 px wide. Check keyboard focus is visible.

B. Build from a reference URL

Ask before overwriting an existing design-system/. Tell the user: we borrow the design language only - never logos, brand names, copy or images.

  1. Extract - run the extract-design skill on the URL. Output goes to .design-extract/<host>/.
  2. Verify live - open the URL in a browser tool at 1440 x 900. Read computed styles for: body, h1-h4, main text sizes, primary and secondary buttons (and their inner elements), cards, tags, containers, section padding. Live computed values beat extractor numbers.
  3. Fonts - if the source font is commercial, pick the closest Google Font that has every subset the project needs (for this repo: vietnamese). Record the substitution in DESIGN.md.
  4. Write the three files:
    • tokens.css: primitives first (raw palette), then semantic tokens that point at primitives. Semantic names describe the role (--text-muted, --surface-card), not the color.
    • components.css: reset, base typography, then one recipe per component seen on the source.
    • DESIGN.md: keep the existing section order (Source, Principles, Color, Typography, Space and layout, Surfaces, Components, Motion, Accessibility, Do / Don't, Gaps).
  5. Prove it - build a small sample section with the recipes and screenshot it next to the source. Report what matches and what does not.

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.