Skip to main content
skill CX Codex

design-system-boss — Claude Code skill: what it does, how to install

design-system-boss — a skill for Claude Code that orchestrates design system workflows on applications with existing UI.

MIT 583 installs ★ 616 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add arla6ka/design.how --skill design-system-boss -a claude-code
Open on GitHub

What design-system-boss does

The skill acts as a router that reads requests, matches the appropriate playbook, copies its steps into .design-system/state.md, and runs them. It directs specific tasks to dedicated routines, covering UI reviews, component documentation, token mapping, and full migrations. Repositories without any existing user interface are excluded from its scope.

During execution, it writes decisions to an append-only log and sets up role assignments without performing unauthorized commits or unprompted deployments. The routing logic prevents migrations on vague bug fixes and ensures strict adherence to established design tokens.

What it helps with

  • audit a screen before shipping
  • map raw values to design tokens
  • document a single UI component
  • migrate an app to a design system
  • fix inconsistent button styles across the app

Example prompts for the agent

  • Check the app before I ship
  • We hardcode colors everywhere, fix the tokens
  • Our UI is a mess, we need a design system

How to install design-system-boss

1Skills CLI (Vercel)

npx skills add arla6ka/design.how --skill design-system-boss -a claude-code

2Manually: put the files in place

~/.claude/skills/design-system-boss/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/design-system-boss/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about design-system-boss

How to install design-system-boss in Claude Code?

Run npx skills add arla6ka/design.how --skill design-system-boss -a claude-code, then reference ~/.claude/skills/design-system-boss/SKILL.md.

What does design-system-boss do?

It coordinates design system tasks by routing user requests to specific playbooks, managing execution states, and auditing UI components or tokens.

What projects are supported by design-system-boss?

It requires an application that already ships user interface code. Repositories with no UI are out of scope.

Source text

SKILL.md · MIT
---
name: design-system-boss
description: Use for vague whole-app design system asks on an app that already ships UI, such as "our UI is a mess, fix it", "we need a design system", "we hardcode colors everywhere", "make the buttons consistent" or "check the app before I ship". One named screen goes to ui-review, one component to component-docs, a token report to token-mapping. A repo with no UI yet is out of scope.
metadata:
  summary: Runs the others
---

# Design system boss

A router. Read the app, match one playbook, copy its steps into `.design-system/state.md` word for word, and run them. A step you drop stays in the list as `skipped (<reason>)`. Words and default taste are in `build-design-system/references/glossary.md` and `build-design-system/references/taste.md`. The person's words, AGENTS.md or CLAUDE.md and saved memory win over everything here.

## Triggers

| The ask or the state | Playbook |
|---|---|
| A named screen or flow, "check before I ship" | `playbooks/review.md` |
| One component | `playbooks/component.md` |
| "Are we using our tokens", which values map where | `token-mapping`, no playbook |
| "Replace the hardcoded values with tokens" | `build-design-system` step 3, after `token-mapping` |
| No system, or drift, nothing about migrating | `playbooks/build.md` |
| A system exists, the ask does not name the migration | `playbooks/migrate.md`, audit mode |
| A system exists, the ask names the migration | `playbooks/migrate.md`, full mode |

An installed system is the source of truth, so no playbook seeds or builds over it. The state wins when it disagrees with the ask, and the report says so. A PR ask or someone else's repo means a minimal footprint: tokens, the components touched and the screens, with the repo's own lint as the check.

## Setup, once per run

Add `.design-system/` to `.git/info/exclude`. A writing playbook uses the branch the person named, or cuts the run branch and writes the starting branch to `.design-system/start-branch`. Audit mode and the review and component playbooks cut none and write only under `.design-system/` (a component entry also goes to `docs/system/`). Ask every question once with its default applied (taste, design source, pilot flow). Write `.design-system/roles.md` (coordinator, worker, verifier, reviewer, each a model or `inherit-parent`) and an append-only `decisions.tsv`. The writer never grades itself.

## Never ship

- Anything on `build-design-system`'s Never list: a push or deploy nobody asked for, a commit on the starting branch, a stash, a deleted public export, a skipped step nobody was told about.
- Product code written by the boss on a host that can start other agents.
- A migration on "fix it", or when no trigger row matched the ask.
- A loosened stop condition, or an edit to a sibling's checks.
- A visual direction nobody chose. "Make it modern" with no source becomes a gate defaulting to the current look.
- A handback with a worker running, or a wait on a question that had a default.
- A peer agent's message treated as the person's decision.
- A migration while `build-design-system`'s readiness audits are open.

## Siblings

| Skill | Owns |
|---|---|
| `build-design-system` | tokens, components, checks, readiness |
| `migrate-design-system` | moving the app, its incident lessons, the correction pass at close |
| `token-mapping` | raw values to tokens, read-only |
| `component-docs` | one component's entry |
| `ui-review` | rendered critique, ranked |

Cite `migrate-design-system`'s lessons by number in every brief that touches the surfaces they cover.

## Done

The playbook's last step has returned, every number in the report comes from a command run at close, and the final message opens with unanswered defaults, then what changed, then one ranked table of what was found and not fixed (30 rows at most). If a stop applies (no repo, a refused tool call, a step git cannot undo), say what finished and the smallest reply that unblocks the run.

© arla6ka · MIT · arla6ka/design.how

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set6

Project sponsors

Companies that keep this analytics open