agentleFS
sankar2codesankar2code/Claude-Skill_SubAgent-Builder-Collections/skills/design-system/SKILL.md

design-system

Skill2 starsChanged 36 days agoMITView on GitHub

Enforces the project's design system on every UI component, page, and style decision. Always apply this skill when writing any frontend code — components, layouts, pages, CSS, Tailwind classes, or inline styles. Trigger when the user asks to build a page, component, UI, screen, layout, or anything visual. Also trigger when the user says "make it look like the design", "follow the design system", "use our colors", or "style this properly". Never use arbitrary colors, spacing, or typography that are not defined in the design system. Part of the PRD → Production pack (always on during feature work).

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

8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All design tokens, colors, typography, spacing, components, and rules live in:

    line 19
  2. Very specific:

    Before writing any UI code, read docs/design.md in full.

    line 23
  3. Very specific:

    If docs/design.md does not exist yet, create it by asking the user the following questions with AskUserQuestion, then write the file:

    line 25
  4. Very specific:

    Never use colors, spacing, or fonts not defined in docs/design.md

    line 38
  5. Distinctive:

    Never hardcode hex values — always reference the named token

    line 39
  6. Very specific:

    Always use the component specs from docs/design.md for buttons, cards, forms, and tables

    line 40
  7. Very specific:

    Always use the icon library and size specified in docs/design.md

    line 41
  8. Very specific:

    Always keep transitions at the duration and easing defined in docs/design.md

    line 42

“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

PRD → Production pack · always on. Apply this skill whenever UI code is written, from Stage 4 (frontend-setup) onward.

Design System Source of Truth

All design tokens, colors, typography, spacing, components, and rules live in:

docs/design.md

Before writing any UI code, read docs/design.md in full. Every decision — colors, spacing, fonts, component styles, layout — must come from that file.

If docs/design.md does not exist yet, create it by asking the user the following questions with AskUserQuestion, then write the file:

  1. What is the product name and visual personality? (e.g. "enterprise SaaS", "consumer app", "developer tool")
  2. What are the primary brand colors? (provide hex values if known, or describe the mood)
  3. What fonts should be used? (or should we default to Inter for UI and JetBrains Mono for code?)
  4. Are there any existing designs, Figma files, or brand guidelines to reference?

Once you have the answers, generate docs/design.md with the full design system — including color tokens (brand, semantic, surface, text), typography scale, spacing scale, layout zones, component specs (buttons, cards, inputs, tables), icon library, motion, and accessibility rules.


Rules (always apply, regardless of project)

  1. Never use colors, spacing, or fonts not defined in docs/design.md
  2. Never hardcode hex values — always reference the named token
  3. Always use the component specs from docs/design.md for buttons, cards, forms, and tables
  4. Always use the icon library and size specified in docs/design.md
  5. Always keep transitions at the duration and easing defined in docs/design.md
  6. WCAG AA compliance minimum — maintain 4.5:1 text contrast ratio
  7. Keyboard navigation and visible focus states on all interactive elements

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.

Reviews can't be read right now.

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.