Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
majiayu000 avatar

Design Systems

  • 1 installs
  • 534 repo stars
  • Updated August 4, 2026
  • majiayu000/claude-skill-registry

Produces a Design System Operating Pack: charter, token model, component inventory and roadmap, blockframe mapping, docs, and governance plan.

About

Builds or evolves a design system by producing a Design System Operating Pack covering charter, design tokens, component inventory, documentation, and governance. A developer uses it when creating component libraries, design tokens, UI kits, or pattern libraries.

  • Delivers a token model including depth/elevation and a component inventory plus roadmap
  • Includes blockframe-to-component mapping and a governance and adoption plan

Design Systems by the numbers

  • 1 all-time installs (skills.sh)
  • Ranked #1,609 of 1,880 Design & UI/UX skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/majiayu000/claude-skill-registry --skill design-systems

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1
repo stars534
Last updatedAugust 4, 2026
Repositorymajiayu000/claude-skill-registry

What it does

Produces a Design System Operating Pack: charter, token model, component inventory and roadmap, blockframe mapping, docs, and governance plan.

Files

SKILL.mdMarkdownGitHub ↗

Design Systems

Scope

Covers

  • Creating or upgrading a design system (tokens + components + guidelines)
  • Using blockframes (lo-fi, system-aware wireframes) to lock logic before hi-fi execution
  • Designing a future-ready visual foundation (depth/elevation, motion, texture) without breaking consistency
  • Making the system easy for non-experts to use (guardrails, examples, starter templates)
  • Driving adoption + governance (contribution model, champions, release cadence)

When to use

  • “We need a design system / component library and a plan to build it.”
  • “Our UI is inconsistent—define tokens + components + documentation to standardize.”
  • “We want to refresh our UI style (more depth/texture/motion) without chaos.”
  • “We need to scale design across teams or support enterprise customers with customization.”
  • “We want faster hi-fi output by locking flows in lo-fi first.”

When NOT to use

  • You’re defining a brand identity or logo system (different process).
  • You need user research/discovery to decide what to build.
  • You only need to ship one isolated UI change (just implement it).
  • You’re doing pure front-end architecture unrelated to UI consistency.

Inputs

Minimum required

  • Product + surfaces: web/iOS/Android; key flows
  • Current state: existing UI kit/design system (if any), design tool (e.g., Figma), code stack (if relevant)
  • Goals: speed, consistency, accessibility, scalability, customization, enterprise adoption
  • Constraints: timeline, team ownership, level of engineering support, compliance/a11y needs

Missing-info strategy

  • Ask up to 5 questions from references/INTAKE.md, then proceed with explicit assumptions.
  • If platform/stack is unknown, assume a modern web product with a component library and design tokens.
  • Do not request secrets or credentials.

Outputs (deliverables)

Produce a Design System Operating Pack in Markdown (in-chat by default; write to files if requested):

1) Context snapshot (goals, constraints, success signals) 2) Design system charter (mission, scope, principles, audiences, in/out) 3) UI audit + operational blockers (what’s slowing teams down; what must standardize first) 4) Blockframe-to-component map (lo-fi flows + mapping to components/tokens) 5) Token model (taxonomy, naming rules, and initial token backlog—include elevation/depth) 6) Component inventory + roadmap (tiers, prioritization, milestones) 7) Documentation + enablement plan (non-designer-friendly, “teaches by structure”) 8) Governance + adoption plan (contribution workflow, decision rights, champions, release cadence) 9) Quality gate (checklists + rubric score) + Risks / Open questions / Next steps

Templates: references/TEMPLATES.md

Workflow (7 steps)

1) Intake + success definition (who is this for?)

  • Inputs: User context; references/INTAKE.md.
  • Actions: Confirm primary users of the system (designers, engineers, PMs, “non-designers”). Define success signals (cycle time, consistency, adoption, fewer UI bugs, faster onboarding).
  • Outputs: Context snapshot (draft).
  • Checks: Success is measurable or at least falsifiable (e.g., “80% of new screens use system components”).

2) Audit the current UI and find the operational “hook”

  • Inputs: Screens/flows, existing components, pain points, enterprise needs (if any).
  • Actions: Inventory inconsistencies (spacing/type/color/components), identify the operational blocker the system will remove (e.g., slow production, inconsistent UI, customization needs). Choose the first high-leverage slice.
  • Outputs: UI audit + operational blockers list; initial scope slice.
  • Checks: The first slice is narrow enough to ship but broad enough to set patterns.

3) Lock logic with blockframes (separate thinking from styling)

  • Inputs: Key flows; current IA; constraints.
  • Actions: Create or specify “blockframes” (lo-fi, system-aware wireframes). Map each block to intended components and token usage so hi-fi execution becomes faster and more consistent.
  • Outputs: Blockframe-to-component map (v1).
  • Checks: A reviewer can validate flow/IA without debating visual details.

4) Define the token model (make the future style changeable)

  • Inputs: Brand constraints, accessibility targets, desired direction (e.g., depth/texture/motion).
  • Actions: Define token taxonomy + naming; include elevation/depth and state tokens. If doing a visual refresh, design the token model so style can evolve without rewriting components.
  • Outputs: Token model + token backlog (v1).
  • Checks: Tokens support theming and states; accessibility constraints are addressed (contrast, focus, motion).

5) Define the component model + delivery plan

  • Inputs: Audit + blockframes + token model; engineering constraints.
  • Actions: Tier components (primitives → composites → patterns). Prioritize by reuse and user impact. Define milestones, owners, and acceptance criteria.
  • Outputs: Component inventory + roadmap (milestones).
  • Checks: Milestone 1 ships within 1–2 weeks and establishes “golden path” patterns.

6) Make it easy to use (guardrails for non-experts)

  • Inputs: Target user types; common mistakes; documentation needs.
  • Actions: Design documentation and component guidelines so they “teach by structure”: sensible defaults, constrained options, examples, do/don’t. Provide starter templates for common layouts.
  • Outputs: Documentation + enablement plan (v1).
  • Checks: A non-expert can assemble a consistent screen using templates with minimal training.

7) Governance + adoption + quality gate

  • Inputs: Draft pack; stakeholder map; toolchain (Figma/Storybook/etc.).
  • Actions: Define decision rights, contribution workflow, review gates, and release cadence. Create a champion/office-hours plan to drive adoption. Run references/CHECKLISTS.md and score with references/RUBRIC.md. Finalize Risks / Open questions / Next steps.
  • Outputs: Final Design System Operating Pack.
  • Checks: Ownership is unambiguous; adoption plan exists; quality bar is explicit and repeatable.

Quality gate (required)

  • Use references/CHECKLISTS.md and references/RUBRIC.md.
  • Always include: Risks, Open questions, Next steps.

Examples

See references/EXAMPLES.md.

Related skills

Design & UI/UXuibranding

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.