From Unslop
Score an existing React + Tailwind site against the anti-slop checklist and produce DESIGN-AUDIT.md with evidence. Use when the user says their site "looks AI-generated", "looks generic", "feels off", asks "why is my site ugly", or wants a design audit/score before improving it. Read-only — never edits source.
How this skill is triggered — by the user, by Claude, or both
Slash command
/unslop:auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Audit the current project's visual design and produce a scored, evidence-backed
Audit the current project's visual design and produce a scored, evidence-backed
DESIGN-AUDIT.md. This skill is strictly read-only on source code — it writes
only the audit report and screenshots.
tailwind.config.* or the
Tailwind v4 CSS import, plus React in package.json). If it isn't, stop and say:
v1 of unslop supports React + Tailwind only.npm run dev or equivalent)
and the port. Start it in the background if not already running.Capture. Run the bundled screenshot script against the running site:
node "${CLAUDE_PLUGIN_ROOT}/scripts/screenshot.mjs" <url> ./unslop/screenshots
It captures 375 / 768 / 1024 / 1440 px full-page shots and reports horizontal overflow per viewport. If Playwright is missing, it prints install instructions — follow them, then re-run.
Deterministic checks.
node "${CLAUDE_PLUGIN_ROOT}/scripts/slop-scan.mjs" .
node "${CLAUDE_PLUGIN_ROOT}/scripts/contrast-check.mjs" <url>
slop-scan greps the source for slop tells (stock palette, transition-all,
arbitrary px values, uniform radius, weight sprawl) with file:line evidence.
contrast-check reports WCAG AA failures on the rendered page.
Visual evaluation. Read all four screenshots. Walk
${CLAUDE_PLUGIN_ROOT}/rules/anti-slop-checklist.md item by item — every item
is PASS / FAIL / N-A with evidence (file:line from the scans, or a screenshot
observation named precisely, e.g. "1440px: hero is centered headline + two
buttons + 3-col icon grid → L1 FAIL"). Read key source files to confirm
suspected failures; do not guess.
Report. Write unslop/DESIGN-AUDIT.md:
Tell the user their score, the 2–3 most damning findings in plain language,
and the next step: run /unslop:interview to define a design lane, then
/unslop:retheme to fix it.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub aahil62/unslop --plugin unslop