design-with-claude
Catalogue stub — full package: imsaif/design-with-claude (MIT)
Decision tree
-
Is the full skill already installed?
f=~/.claude/plugins/cache/design-with-claude/design-with-claude; [ -e "$f" ] && ! grep -qs "^das:" "$f" && echo "installed" || echo "pointer"installed→ invoke it and proceedpointer→ go to step 2
-
Install (the skills CLI cannot install this one):
The skills CLI skips this repo because upstream's SKILL.md frontmatter does not parse as YAML, so the supported route is the Claude Code plugin. Run the two plugin commands in a terminal, or send the same two as slash commands inside Claude Code, then run /reload-plugins (without it the commands do not appear).
bashclaude plugin marketplace add imsaif/design-with-claude claude plugin install design-with-claude@design-with-claude
Claude Code plugin route:
/plugin marketplace add imsaif/design-with-claude /plugin install design-with-claude@design-with-claude
Heads-up
- Requires: Claude Code (plugin route). Commands are namespaced, for example /design-with-claude:design-brief; Optional audit CLI
npx dwic-audit(runs an npm package; it sends an anonymous run counter unless --no-telemetry or DWIC_TELEMETRY=off is set); Optional MCP server for interactive use needs a token from designwithclaude.com - License: MIT
Invoke after install
- Skill name:
design-with-claude - Trigger phrases: "design with claude", "audit my design system", "WCAG contrast audit", "dashboard design", "b2b SaaS design"
- Plugin commands are namespaced, for example
/design-with-claude:design-briefand/design-with-claude:accessibility-specialist. Run/reload-pluginsafter installing or they do not appear.
What it does
Two halves that work together.
Measure. npx dwic-audit runs a deterministic static scan across categories such as color, typography, spacing, accessibility, forms, navigation, motion, and copy. WCAG contrast math, token parsing, markup heuristics; no LLM runs. It prints a dashboard, writes a shareable .dwic/audit-<date>.md, and exits non-zero on errors so it works in CI. Your code stays on your machine; the CLI only sends an anonymous run counter with category-level counts (disable with --no-telemetry or DWIC_TELEMETRY=off). It needs no install and no token.
Fix. Design specialists as slash commands, each a domain expert in pure markdown with no runtime dependencies. The audit's categories map onto specialists (contrast failures → /color-specialist, unlabelled inputs → /form-designer, and so on), and /design-triage will read the audit report and work the findings in ranked order. /design-brief routes a plain-language brief when the problem spans several domains.
Use it when the request is vague ("improve our design", "is this any good?") — measure first, then invoke the specialist the findings point at, rather than guessing. An optional MCP server (set up with npx dwic-audit setup, needs a token from designwithclaude.com) adds project memory across sessions; it is not needed for the audit or the commands.
When NOT to use
- Non-visual work with no design component
- A one-line CSS change you already know how to make
- When a single focused skill already installed suffices — avoid installing the full suite for one-off needs
- Non-Claude agents (Cursor, Cline, Gemini CLI, ...): the skills CLI currently cannot read upstream's SKILL.md (YAML error), so use the
npx dwic-auditaudit on its own or follow the upstream README


