agentleFS
Sign inStart free
ldaumeldaume/agentic-engineering-harness/skills/design/design-systems/SKILL.md

design-systems

Skill3 starsChanged 3 months agoMITView on GitHub

Use whenever creating, extending, or auditing a design system - design tokens and their naming, color, typography, spacing and motion tokens, theming and dark mode, component specifications with states, keyboard and screen reader behavior, documentation, versioning, deprecation, migration, and design-to-code alignment (Designsystem, Design Tokens, Komponentenbibliothek, Theming). Checks token color pairs against WCAG contrast. Not for building one screen, which frontend-craft owns.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation 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.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • KirchliveSkill

    skill-routing

    Decides which of the installed skills a task needs and loads them before the work starts. This skill should be used at the beginning of any multi-step task — build, fix, refactor, migrate, review, plan, release, research, write, design, video — and again at every phase change, after context compaction, and when work moves into a different part of the codebase. Use it for requests like "let's build X", "fix this bug", "refactor Y", "plan the migration", "review this", and also when the user asks which skill applies, why a skill did not fire, or asks to check what is available.

    Also in 5 projects that use this

  • sublimotionSkill

    agent-runtime

    Launch and manage detached agent runs on EKS via the agent-runner CLI. Use when the user says "launch an agent run", "agent runtime", "agent-runner", "run this spec on the cluster", "check run status", "agent run logs", or "stop a run". Do NOT use for writing the agent-runner code itself (edit the sibling ../agent-runner repo), Terraform of the foundation (use terraform-automation), or GPU serving deployments (use infra-deployer).

    Also in 5 projects that use this

  • GoZippySkill

    repo-scout

    Also in 5 projects that use this

  • BenjaminGSkill

    harness-review

    Turn one PR's review comments into harness fixes — classify each cause by the most solid place it can live (codebase, lint, rules, skill), then draft the fixes in a separate PR.

    Also in 5 projects that use this

  • +6 more from naman10parikh

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    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. Very specific:

    Check color pairs: scripts/contrast.py --tokens tokens.json --pairs pairs.json (WCAG 2 ratio: 4.5:1 text, 3:1 large text and UI).

    line 28
  2. Very specific:

    Write each component spec with the template in references/components.md.

    line 36
  3. Distinctive:

    Keep design and code linked and reviewed (context-dependent) [SRC-PROD-027].

    line 39

“Common” is measured: kept by at least 6 in 10 of the 18 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 Systems

Grow a system from needs that recur, with accessibility written into every component contract, so that teams ship consistent, accessible UI faster without being forced into uniformity. Abstract too early and the system encodes a guess; never abstract and every team re-solves focus handling.

Golden path

  1. Inventory what exists: tokens, components, patterns, and where they diverge in code and design files.
  2. Name tokens in three tiers - primitive (raw values, hidden from consumers), semantic (role and intent, the public layer), component (only when a semantic token cannot express it) - because consumers who bind to raw values break at a rebrand (practice context-dependent, the reason a hypothesis) [SRC-PROD-019] [SRC-PROD-020]. A small single-theme system may stop at surface and foreground pairs (context-dependent) [SRC-PROD-023].
  3. Author tokens in the DTCG 2025.10 format, a stable Community Group report, not a W3C Standard; do not implement from the drafts URL (verified) [SRC-PROD-001] [SRC-PROD-002]. Keep themes as separate token sets until the resolver spec is stable (context-dependent) [SRC-PROD-003].
  4. Check color pairs: scripts/contrast.py --tokens tokens.json --pairs pairs.json (WCAG 2 ratio: 4.5:1 text, 3:1 large text and UI). APCA is informational only, because conformance is judged by WCAG 2.
  5. Promote a component when a pattern recurs with the same meaning; accessibility-critical widgets (dialog, menu, combobox) share from the first use, built on an APG-following primitive such as React Aria or Radix (hypothesis for the threshold; supported for primitives) [SRC-PROD-024] [SRC-PROD-025].
  6. Write each component spec with the template in references/components.md.
  7. Version and deprecate with a dated, per-component changelog and a breaking flag (supported) [SRC-PROD-029] [SRC-PROD-026].
  8. Keep design and code linked and reviewed (context-dependent) [SRC-PROD-027].

Load when

  • references/tokens.md - tokens, naming, theming, dark mode, motion tokens, build tooling.
  • references/components.md - a component spec or a decision whether to make one.
  • references/governance.md - versioning, deprecation, migration, contribution, design-to-code alignment.

Gates

Automated: scripts/contrast.py for token pairs (tests in tests/test_contrast.py); the token build (Style Dictionary v5 or the project's tool) in CI. Manual: component behavior with keyboard and screen reader; visual review in each theme.

Done when

Tokens resolve without cycles and pass the contrast gate, each shipped component has a complete spec, breaking changes are flagged and dated, and coherence is achieved without forbidding justified exceptions.

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