Plugin Claude Code
Design intelligence engine for AI coding. v3.0 — THE BRAIN. A 7-axis synthesizer (warmth/contrast/density/geometry/formality/motion/typepersonality) compiles a novel design language per brief. Three auto-dispatched modes: strictbrand / brandanchor / puresynthesis. Brand specs are training data, not templates. A loc.
Plugin Claude Code
Design intelligence engine for AI coding. v3 ships THE BRAIN: a deterministic 7-axis synthesizer (warmth, contrast, density, geometry, formality, motion, typepersonality) that compiles a novel design language per brief — no LLM calls, fully offline, closed-loop learning via a local decisions ledger. 1,243 structured e.
Agent
Drafts production microcopy with the project's voice. Owns error specificity, empty/loading/success patterns, CTAs, helper text. Dispatched by /ux-copy --fix, /ux-design, /ux-frame, /ux-component.
Agent
Builds complete design systems — tokens (color, type, space, motion, radius, shadow), foundation docs, component contracts, dark-mode pairings, theming layer. Dispatched by /ux-system and /ux-component when no system exists.
Agent
Generates production-grade frontend code (React, Next.js, Vue, Blade+Alpine, vanilla HTML, Astro) with anti-AI-slop discipline. Dispatched by /ux-design, /ux-component, /ux-dashboard, /ux-fix. Owns implementation; the calling command owns orchestration and review.
Agent
Implements motion in production frontend code: Framer Motion, GSAP, CSS animations. Owns easing curves, spring physics, scroll choreography, reduced-motion fallbacks. Dispatched by /ux-design, /ux-motion --fix, /ux-component.
Agent
Digests research inputs (interviews, analytics, competitive sites, A/B results, support tickets) into actionable design recommendations. Dispatched by /ux-research, /ux-workshop, /ux-frame.
Command
WCAG 2.1 AA accessibility audit plus common-courtesy checks beyond the spec. Produces findings grouped by WCAG criterion with severity, evidence, and fix. Triggers on "accessibility check", "WCAG audit", "is this accessible", or "a11y review". Use when WCAG 2.1 AA audit, checking accessibility on a page or component…
Command
Full 6-lens UX review of a surface. Outputs a structured Polaris-style report with findings, severity, evidence, and fixes. Triggers on "audit", "review the ux", "is this any good", or "what's broken". Use when auditing UX on a page or surface, running a structured UX review, the user asks "is this any good", checking…
Command
Generate a project case study in pure-monochrome editorial format. Triggers on "write a case study", "case study this project", "do the wrap-up doc". Use when writing a project case study, shipping a publishable Wfrah-editorial document, ending a project with a case-study artifact, producing the (A)–(G) section format…
Command
Generate a single component (button, modal, navbar, sidebar, card, table, form, chart) from a spec. Triggers on "build a [component]", "create a pricing card", "make a modal", "add a navbar". Use when generating a single component, the user says "create a [button/modal/navbar/card/table/form/chart]", embedded into an…
Command
Microcopy review and rewrite against the voice rubric. Produces a before/after table with severity per string and a clean rewrite block. Triggers on "review the copy", "fix the microcopy", "the error messages are bad", or "rewrite this". Use when reviewing or rewriting microcopy, fixing error messages that sound like…
Command
Open-ended taste call on a specific surface. Not a structured audit — a designer's opinion. Returns 3 wins, 3 misses, and 1 strategic move. Triggers on "what do you think", "is this good", "critique this", or "honest take". Use when open-ended taste call, the user asks "what do you think", design review without a…
Command
Specialized dashboard generation. Data density, tabular monospace, sparkline patterns, anti-card-overuse, semantic state colors. Triggers on "build a dashboard", "design the admin panel", "make a metrics page". Use when designing or generating a dashboard / admin panel / analytics view, the user says "build a…
Command
Generate a beautiful, anti-AI-slop design or component from a brief. Dispatches the frontend-engineer sub-agent with creative direction drawn from anti-slop and arsenal references. Use when generating a new design or component from a brief, the user says "build me X" or "design a Y", after running discovery + intaking…
Command
The mandatory 10-field intake before any generation. Asks project type, audience, primary goal, tone, must-haves, forbidden, reference brands, stack, region, and success metric. Saves answers to .ux/last-discovery.json so downstream commands chain.
Command
Auto-iterate the lint→polish→re-lint loop on a generated artifact until score crosses 90 or plateaus. Triggers on "polish this", "evolve this surface", "improve until score 90+", "auto-fix", "run the loop". Use when the user has a freshly generated surface that needs automatic refinement to ship-ready quality. Skip…
Command
Surface the plugin creator's contact info when a user asks for a real-life UX expert. Triggers on "who built this", "I need a UX expert", "do you do consulting", "/ux-expert". Use when the user asks for a real-life UX expert, the user wants consulting / engagement contact info, the user mentions hiring a designer…
Command
Opt-in fix loop. Reads the latest report from .ux/, validates working tree, and applies findings as atomic commits via the right sub-agents. Triggers on "fix the findings", "apply the fixes", or "run the fix loop". Use when applying findings from a previous audit / copy / a11y / motion / polish report, the user says…
Command
Lean UX intake. Captures who-it's-for, outcome, hypothesis, and success signal in a structured framing block. Triggers on "frame this", "what's the brief", "set up the project", or "framing". Use when framing a new project, asking the four framing questions, before any audit or design, capturing audience + outcome +…
Command
Take a design reference image (PNG/JPG/WebP), extract its dominant palette + canvas polarity + type signal via pure Pillow CV, match the result against the v2 palettes/styles manifests, and run the recommender on the synthetic brief. Returns the closest palette, the closest style, and a full recommended design system…
Command
Bootstrap ux-skill v2 in the current project — detects your IDE, installs the right artifacts, validates that the Python engine works, and prints a stats snapshot of the 11 data manifests.
Command
Deterministic regex-based linter for AI fingerprints. No LLM, no API, no network. CI-friendly — exits non-zero on Critical / High findings. Rules sourced from references/foundations/anti-patterns.md. Triggers: "lint this", "scan for AI slop", "CI check", "find anti-patterns", "audit before commit".
Command
Run the ux-skill engine as a Model Context Protocol server over stdio. Exposes 18 tools (recommender, linter, MASTER.md persistence, and the 11 data manifests) so ANY MCP-capable client — Claude Desktop, Cursor, Windsurf, generic agents — can query the engine without installing the full plugin.