Skill Claude CodeCodex
Audits a codebase across seven dimensions, from architecture to code health, scoring each finding with evidence. Use for a full codebase review, tech-debt assessment, or post-incident analysis.
Skill Claude CodeCodex
Routes a code investigation to one of four modes — bug, test gap, architecture, implementation — and runs the query sequence that mode needs. Use when asked to investigate, trace, or debug code.
Plugin Claude Code
UI design validation. Compares a rendered screen against its reference by pixel diff, then reviews the result for spacing, hierarchy and design-system consistency.
Agent
Compare a reference design (Figma URL, image file, or browser URL) against an implementation screenshot. Produces structured diff report with pixel-level comparison and optional AI semantic analysis. Use when validating that implementation matches design spec.
Agent
Reviews a screen for usability, WCAG accessibility and design-system consistency, reading the screenshot directly. Use when asked what is wrong with a UI, for an accessibility audit, or to implement a Figma design.
Command
Interactive wizard to create and update project design style guides. Supports reference image capture, style updates, and visual reference management. Actions: create, update, capture, add-reference, remove-reference, list-references.
Command
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
Command
UI design review from a screenshot or Figma file, covering usability and accessibility.
Skill Claude CodeCodex
Detects the browser-use@magus plugin and captures screenshots of URL-based references. Use when designer agents need browser screenshot capture and claude-in-chrome is unavailable.
Skill Claude CodeCodex
Provides the compare.ts CLI invocation pattern, semantic comparison prompt template, severity thresholds, and model selection guide for UI design comparison.
Skill Claude CodeCodex
Provides design system references — Material 3, Apple HIG, Tailwind UI, Ant Design, Shadcn/ui. Use when reviewing UI against an established design system.
Skill Claude CodeCodex
Reviews a UI screenshot — usability, WCAG, design-system consistency, design-vs-implementation diff. Prompting patterns, depth tiers and severity guidelines. Analysis only; pair with dev:frontend-implement to apply.
Skill Claude CodeCodex
Specifies the UI design style file format and schema for .claude/design-style.md and .claude/design-references/. Use when creating, validating, or parsing project design styles.
Plugin Claude Code
Universal development assistant. Detects the project stack and routes work to specialist agents for architecture, implementation, debugging, review and research, enforcing design-system guardrails on every UI change.
Agent
Plans system architecture in any language, weighing trade-offs and naming what each choice costs. Use before building a new system or subsystem, for a major refactor, or when comparing two designs.
Agent
Traces an error to its root cause across files, in any language, and reports the evidence for the diagnosis. Use when a bug is not obvious from the stack trace, or when a failure spans several modules.
Agent
Implements features spanning multiple files, then iterates write-test-fix-lint until every check passes. Use for new modules, subsystems, or any change needing 3+ files with test coverage.
Agent
Handles infrastructure work — CI pipelines, containers, deploys, observability — and reasons through the trade-offs before changing anything. Use when setting up or debugging a pipeline, a deploy, or a runtime environment.
Agent
Writes, analyses, and fixes documentation. Pass mode=write|analyze|fix. Use for READMEs, API docs, tutorials, changelogs, or a documentation quality audit.
Agent
Builds and revises React components against the project's design system, with optional vision review of screenshots. Use when implementing UI, reworking a component, or matching a reference design.
Agent
Multi-round web research with convergence detection — searches 10+ sources, assesses their quality, and returns a cited report. Use for technology evaluations, library comparisons, and best-practice surveys.
Agent
Reviews recent changes in three passes — security, correctness, maintainability — returning severity-calibrated findings and a PASS/CONDITIONAL/FAIL verdict. Use before merging or when asked to check code quality.
Agent
Appends Q&A to an interview log, updates checkpoints and maintains session state — a small, fast file writer. Use when recording an interview turn, not for analysis or synthesis.