agentleFS
Sign inStart free
Evan-Kim2028Evan-Kim2028/agent-skills/skills/frontend/design-system/SKILL.md

design-system

Skill1 starsChanged 3 months agoMITView on GitHub

Stay on project design-system rails — tokens, typography, components, chart contracts, and brand locks. Use only when the task is already about tokens, DESIGN.md / design-system docs, or agents inventing fonts/colors/spacing. Prefer over generic aesthetic skills. Prefer product-design when multi-step product UX/craft is unclear; frontend-design for full FE implementation. Not for greenfield brand invention, marketing storytelling, general layout polish (product-ui-craft), or pure QA/verify (quality-check).

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

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

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search, in order, and cite paths in your plan:

    line 38
  2. Distinctive:

    If none exist: draft a minimal token table *with the user* before freestyling — or route to ui-explore for exploration only.

    line 46
  3. Distinctive:

    Before writing JSX/CSS, state:

    line 51
  4. Distinctive:

    Keep brand accents for stats/links/CTAs if the system reserves them that way

    line 66
  5. Very specific:

    If design/DESIGN-DIRECTION.md + frontend/docs/design-system.md are present:

    line 78
  6. Very specific:

    Use ~/components/ui/*, PAGE_H1_CLASS, chart tokens — not neo-brutalist experiments

    line 82

“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

Design system fidelity

Job: Make agents implement this product, not a random pretty UI.

Sources (attribution)

  • Project-local law: whatever the repo names as design source of truth (design/DESIGN-DIRECTION.md, frontend/docs/design-system.md, DESIGN.md, tokens.css, theme @theme blocks, Storybook, Figma tokens).
  • Constraint-before-code practice popularized by Anthropic’s frontend design skill write-up (Improving frontend design through Skills) — adapted here to mean “commit to project constraints,” not “pick a new aesthetic each time.”
  • Token + primitive discipline common to mature design systems (no magic hex / arbitrary spacing in product UI).

When to load

  • Touching production UI in a repo that already has a look
  • Card detail, chat, dashboards, trade floors, pricing — product surfaces
  • Agent output keeps introducing Inter-only stacks, new purples, or off-token radii

Workflow

1. Locate the law (read before coding)

Search, in order, and cite paths in your plan:

  1. design/DESIGN-DIRECTION.md, DESIGN.md, docs/design*
  2. frontend/docs/design-system.md or equivalent
  3. Token files: tokens.css, theme/tokens.css, index.css @theme
  4. Typography constants / shared layout components
  5. Canonical UI kit path (components/ui/*, design-system package)

If none exist: draft a minimal token table with the user before freestyling — or route to ui-explore for exploration only.

2. Lock the palette of moves

Before writing JSX/CSS, state:

DecisionRule
ColorOnly token classes / CSS variables
TypeOnly project font stacks (e.g. serif H1 + mono prices)
SpaceSpacing scale only — no p-[13px]
RadiusToken radii only
ComponentsPrefer kit primitives over new one-offs
ChartsOnly approved chart shell/option builders if the repo has them

3. Implement

  • Reuse existing primitives; extend with variants, don’t fork
  • Match surface language: glossy interactive vs flat data panels if the system defines tiers
  • Keep brand accents for stats/links/CTAs if the system reserves them that way

4. Self-check

  • No new font families without explicit product decision
  • No raw hex in className (unless repo exempts chart canvas colors)
  • No parallel button/card styles when kit ones exist
  • Dark-first / theme parity respected if documented
  • ESLint design-system rules pass if present

SilphCo-shaped example (when that repo is the workspace)

If design/DESIGN-DIRECTION.md + frontend/docs/design-system.md are present:

  • Brand: Master Ball Void purple + Literata / JetBrains Mono — not “ban purple”
  • Product: dual flagship chat + analytics; shared chart shell
  • Use ~/components/ui/*, PAGE_H1_CLASS, chart tokens — not neo-brutalist experiments

Anti-patterns

  • Loading generic “frontend-design” aesthetic skills that ban the brand color
  • “Refreshing” type/color because AI defaulted to Inter
  • One-off glass cards on marketing while product uses flat panels (or vice versa) without a system rule

Hand off

NeedNext skill
Density / polish after tokensproduct-ui-craft
Mobile chromemobile-product-ux
Match a mockupmockup-implement
A11y auditweb-quality

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