agentleFS
ryanschueryanschue/automated-product-engineer/skills/design-system/SKILL.md

design-system

Skill0 starsChanged 26 days agoMITView on GitHub

Extend or maintain design-system infrastructure including semantic tokens, primitives, variants, editable variables, catalog metadata, interactive previews, inspector support, and visual-regression coverage.

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

11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 9

    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:

    Use this skill when a visual rule should become shared infrastructure.

    line 8
  2. Distinctive:

    Read references/system-extension.md for the token-to-component pipeline, catalog and inspector contracts, migration sequencing, and …

    line 10
  3. Very specific:

    Use governed-component-contract in ../codebase-upgrade/references/pattern-atlas.md to connect component work to a repeated product …

    line 14
  4. Distinctive:

    If the repository supports editable variables or an inspector, keep code tokens, editor controls, metadata, and preview rendering …

    line 37
  5. Distinctive:

    Use deterministic fixtures for default, interactive, disabled, loading, error, dense, and responsive states that materially affect the …

    line 42
  6. Distinctive:

    Keep preview controls, labels, and inspectable values derived from the same metadata when possible.

    line 43
  7. Distinctive:

    Avoid preview wrappers that alter the production component's layout participation or measurement.

    line 44
  8. Distinctive:

    Test variant selection, keyboard and screen-reader behavior, token resolution, and any metadata-to-preview mapping.

    line 48
  9. Distinctive:

    Add targeted visual coverage at stable dimensions and inspect diffs before approving baselines.

    line 49
  10. Distinctive:

    Document migration guidance and remove superseded tokens or variants only when all consumers are accounted for.

    line 51
  11. Very specific:

    Use design-polish for one product surface and responsive-design when the primary problem is fluid layout behavior.

    line 53

“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

Use this skill when a visual rule should become shared infrastructure. Keep feature-specific data and orchestration in feature code.

Read references/system-extension.md for the token-to-component pipeline, catalog and inspector contracts, migration sequencing, and visual-baseline discipline. Read references/component-library-onboarding.md when introducing the library to a team, documenting why it matters, or planning adoption from existing product screens.

For a repository-wide assessment of repeated UI and adoption friction, start with codebase-upgrade. Use its component-infrastructure pattern to choose a real product slice before extracting tokens or components.

Use governed-component-contract in ../codebase-upgrade/references/pattern-atlas.md to connect component work to a repeated product behavior, deliberate variants, state coverage, compact pressure, accessibility, and adoption evidence.

Intake and pushback

Inspect existing tokens, primitives, variants, consumers, documentation, and visual baselines before proposing a parallel system. Establish the target consumers, semantic role, themes, accessibility requirements, supported states, extension axis, and ownership or migration expectations.

Ask one to three focused questions only when a missing decision would change the public token or component contract. If design source or governance input is missing, generate a tailored request that lists the observed foundations, the conflicting or absent decisions, and the exact token, component, state, or approval artifact required.

Establish the source of truth

  • Inspect existing tokens, variables, primitives, component variants, metadata, previews, and tests before adding a parallel mechanism.
  • Confirm reuse across real surfaces or a strong near-term need. Do not promote every one-off element.
  • Map design values to semantic intent rather than copying raw color, spacing, or typography values into consumers.
  • Preserve the project's theme, accessibility, and naming conventions.

Build by layer

  • Foundations: semantic color, type, spacing, radius, shadow, motion, and responsive values.
  • Primitives: small accessible elements with explicit states and variants.
  • Patterns: repeatable combinations whose layout and interaction contract is stable.
  • Composites: production components that accept domain-neutral inputs while leaving business behavior to callers.

If the repository supports editable variables or an inspector, keep code tokens, editor controls, metadata, and preview rendering synchronized. Metadata describes the production API; it must not invent a second component model.

Preview real behavior

  • Render the production component in catalogs and workbenches rather than a preview-only imitation.
  • Use deterministic fixtures for default, interactive, disabled, loading, error, dense, and responsive states that materially affect the contract.
  • Keep preview controls, labels, and inspectable values derived from the same metadata when possible.
  • Avoid preview wrappers that alter the production component's layout participation or measurement.

Validate

  • Test variant selection, keyboard and screen-reader behavior, token resolution, and any metadata-to-preview mapping.
  • Add targeted visual coverage at stable dimensions and inspect diffs before approving baselines.
  • Exercise production consumers at representative widths; a catalog-only pass is insufficient.
  • Document migration guidance and remove superseded tokens or variants only when all consumers are accounted for.

Use design-polish for one product surface and responsive-design when the primary problem is fluid layout behavior.

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.