Skills for Real Engineers. Straight from my .agents directory.
ux-extract
Agent skill fromjezweb/claude-skills
Exhaustively extract UX patterns from a reference web app. Walks every screen, captures screenshots of every state, records interaction patterns, copy verbatim, keyboard shortcuts, responsive treatments, motion, and empty/error/loading states. Produces a reusable pattern library that other audits can compare against. The inverse of ux-audit — asks 'what is the bar?' rather than 'does this match the bar?'. Trigger with 'learn from X', 'extract patterns from X', 'study X's UX', 'reverse engineer the UX of X', 'build a pattern library from X'.
How to install ux-extract
npx skills add jezweb/claude-skills# or add only this skill to Claude Code: copy the folder
plugins/dev-tools/skills/ux-extract/
# into
~/.claude/skills/ux-extract/ (all projects)
.claude/skills/ux-extract/ (one project)
1# UX Extract23Exhaustively study a reference web app and produce a reusable pattern library. Goes everywhere, captures everything, then organises it into a document another audit or build can reference.45The inverse of `ux-audit`:6- **Audit** asks: *does this match a bar?*7- **Extract** asks: *what is the bar?*89Audits without extracts implicitly compare to "my memory of other apps" — fragile and inconsistent. Extracts turn that memory into a concrete, navigable artifact. An audit can then say: *"Empty state on /app/clients shows no CTA. Reference (claude.ai) shows 3 keyboard shortcuts plus 'New chat' in the same position"* instead of *"feels a bit sparse"*.1011## When to use1213- **Before building a new feature** — study how best-in-class apps handle it14- **Benchmarking a build** — extract the reference, then audit against it15- **Onboarding designers or engineers** — here's what good looks like, concretely16- **Competitor research** — document the competitor's UX so you can meaningfully differentiate17- **Refreshing an old app** — extract patterns from modern equivalents to guide the update1819## Scope and ethics2021Before starting, confirm the target is fair game:22231. **Use your own account** — don't scrape anything that requires credentials you don't legitimately hold242. **Respect `robots.txt`** for unauthenticated crawling253. **Rate-limit** — act like a human user, not a crawler. Pause between pages.26…
Excerpt shown under the repository's MIT license.
More skills in claude-skills
Similar skill repositories
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
