Agent skill

Design System

by genkovich in genkovich/sdd

A skill your agent uses to establish the project's design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown), the platform posture (mobile-first /…

MITAuto-check passedFrontend & Design

Install Design System

skills CLI
$ npx skills add genkovich/sdd --skill design-system -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install genkovich/sdd design-system --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/genkovich/sdd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/design-system .claude/skills/design-system && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
design-system
GitHub stars
171
Token cost
~2.3k tokens
SKILL.md length
980 words
Files
2
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses to establish the project's design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown), the platform posture (mobile-first /…

  • Works in 7 steps: Check existing. If docs/design-system.md… → Scan the code side. Read… → Detect tools + ask ONE question set.… → …
  • Establish the projects design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown)
  • SKILL.md covers Owner, Inputs, Protocol and Definition of Done, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design System is an agent skill from genkovich/sdd. Use to establish the project's design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown), the platform posture (mobile-first / desktop-first / responsive), the token source, and the reusable component inventory. Once per repo, like survey. Triggers on "set up the design system", "design canon", "which design tool", "establish the UI foundation", "/sdd:design-system", "налаштуй дизайн-систему", "дизайн-канон проєкту", "яким інструментом малюємо". Read by ux-flows…

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `templates/design-system.md`).

It sits in Frontend & Design, covering Design systems and Responsive design. It works with Figma and Model Context Protocol. The repository describes itself as: Spec-Driven Development for Claude Code: 12 atomic Socratic skills + a TDD implement engine (agent-team & dynamic-workflow modes). The licence is MIT.

When your agent uses it

  • Establish the projects design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown)
  • The platform posture (mobile-first / desktop-first / responsive)
  • The token source
  • The reusable component inventory

Example prompts

  • “set up the design system”
  • “design canon”
  • “which design tool”
  • “/design-system”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Check existing. If docs/design-system.md exists, show its tool + posture + inventory
  2. Scan the code side. Read architecture-map.md §Frontend / UI foundation + the frontend
  3. Detect tools + ask ONE question set. Detect which design-tool MCPs the session actually has
  4. Write the canon. Fill ./templates/design-system.md →
  5. Bootstrap the tool library (tool: pencil only — figma links an existing file, code
  6. Structural self-check — per ../_shared/self-check.md: re-read
  7. Commit + handoff. Propose commit design-system: establish canon (on pencil —

What it can do on your machine

Read from SKILL.md and the folder at commit 4403913. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Design System loads about 2.3k tokens when it runs. Until then it costs about 226 tokens; SKILL.md has 980 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~226
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from genkovich/sdd at commit 4403913, republished under its MIT licence (© genkovich). 980 words, ~2,250 tokens.

Download SKILL.mdSave it as .claude/skills/design-system/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
design-system
description
Use to establish the project's design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown), the platform posture (mobile-first / desktop-first / responsive), the token source, and the reusable component inventory. Once per repo, like survey. Triggers on "set up the design system", "design canon", "which design tool", "establish the UI foundation", "/sdd:design-system", "налаштуй дизайн-систему", "дизайн-канон проєкту", "яким інструментом малюємо". Read by ux-flows (posture) and screens (tool + inventory); implement registers NEW components back into it. On tool: pencil it also bootstraps the .pen library itself — creates the file, walks the user through opening it, and seeds tokens + a foundations frame via the pen-keeper agent. Utility — not a backbone stage; run it before the first UI feature (ux-flows recommends it when absent).
model
inherit
effort
medium
agents
explorer, pen-keeper

Skill: design-system

The design-side twin of survey: once per repo it fixes the design canon in docs/design-system.md — which tool screens are drawn with (figma / pencil / code), the platform posture, where tokens come from, and the component inventory new screens must compose. architecture-map.md §Frontend stays the inventory of the code; this file is the design canon the design pipeline (ux-flows → screens) and implement/review read. The tool choice is committed here — never in .claude/sdd.local.md (that file is per-developer and gitignored; the canon is team-wide).

Question phrasing → ../_shared/ask-style.md. Canon prose follows artifact_language — frontmatter keys/values (tool:, figma_file:, …), component names and file anchors stay English → ../_shared/artifact-language.md.

Owner

Whoever owns the product's look (designer / frontend lead / the solo maintainer).

Inputs

  • (Optional) docs/architecture-map.md §Frontend / UI foundation + the frontend: machine key — the code-side inventory this canon cites.
  • (Optional) an existing docs/design-system.md — updated, never silently overwritten.
  • The design-tool MCPs available in this session (Figma / Pencil), if any → detected in step 3.

Protocol

  1. Check existing. If docs/design-system.md exists, show its tool + posture + inventory summary and ask: reuse as-is (STOP — nothing to do) / update (continue, edits land in place) / rebuild. Never overwrite silently.
  2. Scan the code side. Read architecture-map.md §Frontend / UI foundation + the frontend: key. Map absent, stale, or frontend: "" on a repo that visibly has UI code → dispatch the explorer agent — subagent_type: "sdd:explorer" (fallback subagent_type: "Explore", per ../_shared/agent-roster.md) — for the component library / tokens / styling approach / shared primitives, each with a file:line. A repo with no UI code at all is fine — the canon can start tool-side or empty (greenfield: the inventory grows as implement registers components).
  3. Detect tools + ask ONE question set. Detect which design-tool MCPs the session actually has (Figma / Pencil — probe the available tools, don't assume). Then one AskUserQuestion call (up to 3 questions in it, phrased per ../_shared/ask-style.md): (a) tool — options from what's detected, the detected one first as «(Recommended)»; code (markdown wireframes in screens.md) is always offered — it needs no MCP and never blocks; (b) platform posture — mobile-first / desktop-first / responsive-both; (c) token source — the code file(s) found in step 2 / the tool's variables / «none yet».
  4. Write the canon. Fill ./templates/design-system.md → docs/design-system.md: frontmatter tool + figma_file/pen_file (the one matching the tool; the other stays ""), posture, token source, the component inventory — each row citing file:line (code) or the node/URL (tool-side) — and the cross-screen conventions.
  5. Bootstrap the tool library (tool: pencil only — figma links an existing file, code needs nothing). The canon naming a pen_file that doesn't exist or is an empty stub is the #1 way this skill «did nothing» — so materialize it: a. File. Absent → write the minimal stub to pen_file ({"version": "2.17", "children": []}). b. Open + verify. The Pencil MCP ignores filePath — it writes into whatever document is active in the app. Ask the user to open the file (macOS: open -a Pen <pen_file>), then verify via get_app_state that the active canvas IS pen_file. Mismatch → stop and repeat the ask; never write into a foreign document. c. Seed. Dispatch the pen-keeper agent — subagent_type: "sdd:pen-keeper" (no fallback: without the Pencil MCP this step degrades to code mode per ../_shared/tool-adapters.md) — with the canon path, pen_file, and the token source files. It re-checks the active document, seeds the variables (light + dark), ensures the foundations frame, and returns a reconcile report. d. Persist. Relay the report's user actions — always «Cmd+S in Pencil»: the app holds changes in memory and the MCP cannot save; confirm the file on disk actually changed (size/mtime) before calling the canon done.
  6. Structural self-check — per ../_shared/self-check.md: re-read the file from disk and verify 5 items: (1) tool ∈ {figma, pencil, code}; (2) the tool ↔ file fields agree — figma ⇒ figma_file non-empty, pencil ⇒ pen_file non-empty, code ⇒ both ""; (3) every inventory row carries a source anchor (file:line or node/URL); (4) no <placeholder> stubs survive; (5) tool: pencil ⇒ the pen_file exists on disk and is larger than the empty stub (step 5 ran and the user saved). Fix + re-check ≤2 cycles; surface anything unresolved.
  7. Commit + handoff. Propose commit design-system: establish <tool> canon (on pencil — including the seeded pen_file). Then emit the stage-handoff block per ../_shared/handoff.md (utility variant) — What I did (incl. «self-check: 4/4 pass») + Review (docs/design-system.md) + Run next: resume your backbone stage (typically /sdd:ux-flows <slug> for the UI feature in flight); /clear optional.
Show full SKILL.md (283 more words)Show less

Definition of Done

  • docs/design-system.md exists with tool ∈ {figma, pencil, code}, a stated platform posture, a token source, and an inventory whose every row cites its source.
  • The tool ↔ figma_file/pen_file fields are consistent; the file is committed (team-wide canon, not a local setting).
  • tool: pencil ⇒ the .pen library exists on disk, holds the seeded token variables, and the user has saved it (the canon never points at a file that was never created).

Anti-patterns

  • The tool choice in sdd.local.md. That file is per-developer and gitignored — two teammates would draw in different tools. The canon is committed, in this one file.
  • Re-asking the tool per feature. ux-flows/screens read the canon; the question is asked once, here.
  • Duplicating architecture-map.md §Frontend. The map inventories the code; this file cites it and adds the design-side canon — never a second copy of the same rows.
  • Blocking on a missing MCP. No Figma/Pencil in the session → code mode is always available; degrade, don't block (→ ../_shared/tool-adapters.md).
  • An inventory with no anchors. A component row that cites nothing is a guess — cite file:line or the tool node, or leave it out.
  • A canon that names a pen_file nobody created. tool: pencil without step 5 is a dangling pointer — downstream screens opens nothing and silently degrades.
  • Writing into whatever document is open. The Pencil MCP targets the ACTIVE document and ignores filePath — skipping the get_app_state identity check pollutes a foreign file.
  • Assuming the MCP saved to disk. It edits in-memory; only the user's Cmd+S persists. Verify the file changed before committing.

References & template

© genkovich, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/design-system of genkovich/sdd.

  • SKILL.md
  • templates/design-system.md

Open the folder on GitHubat commit 4403913

Compare with similar skills

Design System next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Design System compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design System this skillgenkovich/sdd171—~2.3kAutomated safety check: PassMIT
Refero Designreferodesign/refero_skill297—~5.3kAutomated safety check: PassMIT
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma Code Connect Componentswarpdotdev/warp65k2 repos~4.2kAutomated safety check: PassAGPL-3.0
Figma Screen Generatorwarpdotdev/warp65k2 repos~5kAutomated safety check: PassAGPL-3.0
Material Design 3 UI/UX Guideskydashnet/material-design-3-ui-skill135—~3kAutomated safety check: PassMIT

Similar skills

  • Refero Design

    referodesign/refero_skill

    Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive…

    297 GitHub stars~5.3k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Maps published Figma components to their code implementations with Code Connect, using the Figma MCP suggestion and mapping tools.

    65k GitHub starsUsed in 2 repos~4.2k tokens
    Frontend & DesignAuto-check passed
  • Figma Screen Generator

    warpdotdev/warp

    Builds or updates full Figma screens from code or a description by reusing the file's published design system components, variables and styles.

    65k GitHub starsUsed in 2 repos~5k tokens
    Frontend & DesignAuto-check passed
  • Material Design 3 UI/UX Guide

    skydashnet/material-design-3-ui-skill

    Guides designing, reviewing or implementing interfaces that follow Google's Material Design 3 system: semantic tokens, component states, adaptive layout and accessibility.

    135 GitHub stars~3k tokensUpdated 8 days ago
    Frontend & DesignAuto-check passed
  • Build Figma

    cursor/plugins

    Official

    Guides an agent through turning a Figma node into production UI with the repo's own components, then checks the result visually before finishing.

    10k GitHub stars~961 tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from genkovich/sdd

All 21 skills in this repo
  • Fix

    genkovich/sdd

    A skill your agent uses to fix a reported bug spec-first: reproduce it, trace the symptom to the owning feature's acceptance criteria, pin it with a failing (RED) test, apply the minimal GREEN fix…

    171 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Implement

    genkovich/sdd

    A skill your agent uses to implement a feature from its tasks.json with test-driven development — writes a failing test first, makes it pass, refactors, gates, and commits per task.

    171 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Interview

    genkovich/sdd

    Use BEFORE roadmap or specify to get the idea OUT OF YOUR HEAD and onto disk — a Socratic interview that surfaces hidden assumptions, names tradeoffs, exposes imprecisions and proposes fresh angles…

    171 GitHub stars~3.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Classify Size

    genkovich/sdd

    A skill your agent uses to classify a feature into XS/S/M/L/XL and write docs/features/{slug}/.size plus the pipeline route docs/features/{slug}/.route (quick|standard|full) so later skills know how…

    171 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Decide Adr

    genkovich/sdd

    A skill your agent uses to record a post-hoc or asynchronous architecture decision as a MADR ADR when it was NOT captured during the synchronous design pass — a choice made in code, in a chat, on a…

    171 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Tasks

    genkovich/sdd

    A skill your agent uses to break a designed feature into atomic, ≤1-day tasks with a dependency graph, a per-task Definition of Done, and a machine-readable tasks.json that the implement engine…

    171 GitHub stars~4.8k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Design System

What does Design System do?

A skill your agent uses to establish the project's design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown), the platform posture (mobile-first /…. Design System is an agent skill from genkovich/sdd.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown), the platform posture (mobile-first / desktop-first / responsive), the token source, and the reusable component inventory.

When should I use Design System?

Design System fits situations like: establish the projects design canon — docs/design-system.md: the design-tool choice (Figma MCP / Pencil MCP / code-only markdown); the platform posture (mobile-first / desktop-first / responsive); the token source; the reusable component inventory.

How do I install Design System in Claude Code?

Run `npx skills add genkovich/sdd --skill design-system -a claude-code`. Or copy the skill folder (skills/design-system in genkovich/sdd) into .claude/skills/design-system in your project. Claude Code loads it when a task matches its description.

How do I install Design System in Codex?

Run `npx skills add genkovich/sdd --skill design-system -a codex`. Or copy the skill folder (skills/design-system in genkovich/sdd) into .agents/skills/design-system in your project. Codex loads it when a task matches its description.

Can I use Design System in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add genkovich/sdd --skill design-system -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-system, .gemini/skills/design-system, .github/skills/design-system and .opencode/skills/design-system in your project.

What does Design System need to run?

SKILL.md names no scripts, command-line tools or credentials: Design System is instructions for the agent only.

Does Design System access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Design System safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Design System use?

Design System is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Design System use?

About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Design System?

Skills that share tags, products or a category with Design System: Refero Design (referodesign/refero_skill, 297 stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Code Connect Components (warpdotdev/warp, 65k stars) and Figma Screen Generator (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design System?

genkovich (a GitHub user) maintains it in genkovich/sdd, which has 171 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 5, 2026.

Source: genkovich/sdd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.