claudecodex

ibr

End-to-end UI design and validation — guided builds, visual checks, mockup matching, native scanning

0 on GitHubby Tyrone RossApache-2.0updated 3 days agodeveloper-tools
/

Plugin ibr from marketplace rosslabs-ai-toolkit in tyroneross/RossLabs-AI-Toolkit. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (32)

  • artifact

    Use when building, checking, or porting a single self-contained HTML page — an artifact, a one-file report, a standalone .html deliverable, or a page that must open outside Claude.

  • design

    Use when planning or implementing UI with IBR.

  • native

    Use when validating iOS, watchOS, or macOS UI with IBR.

  • ui-ux-guidance

    Use when planning, designing, implementing, or auditing UI/UX with IBR in Codex. Provides compact guidance for design assumptions, comparable alternatives, design-quality audits, Calm Precision, platform conventions, states, data visualization, and visual targets.

  • validate

    Use when scanning, auditing, comparing, or testing UI with IBR.

  • apple-platform

    Use when building iOS, watchOS, or macOS apps — architecture, SwiftData, Swift concurrency, CI/CD, TestFlight pipeline. Not for HIG/UI rules or manual signing and notarization steps; use `ios-design` (iPhone/iPad) or `macos-ui` (Mac) instead.

  • artifact-design

    Use when building a single self-contained HTML page — an artifact, a one-file report, a shareable page, a standalone .html deliverable — or when asked to check, lint, wrap, or port an artifact so it opens outside Claude. Covers treatment calibration, the three-state theme contract, palette and type

  • artifact-diagramming

    Use when a page needs a diagram — architecture, data flow, sequence, state machine, before/after comparison — or when asked to draw, sketch, or illustrate a mechanism inside an artifact, report, or self-contained HTML page. Covers whether a diagram earns its place, what to depict, and the inline SVG

  • auto-verify

    Use when configuring or troubleshooting IBR's automatic before/after scan workflow on UI file edits. Triggers on "enable auto verify", "turn on auto scan", or pre/post-change hook questions.

  • calm-precision

    UI/UX implementation guide for building cognitively predictable interfaces. WHAT: Decision trees, component patterns, code examples, anti-patterns, and audit checklists grounded in perceptual science (Gestalt, Fitts, Hick, Cognitive Load, Signal-to-Noise, Affordance, Temporal Gestalt, Dual-Coding, P

  • cli-reference

    Use when you need to inspect, test, validate, or audit UI (web or native) via IBR CLI — instead of writing a Playwright script or a one-off browser-automation script. Reference for scan, sessions, native testing, design memory commands, evaluating JS in the page, and screenshotting an element.

  • component-patterns

    Use when building one reusable component — a card, nav, form, modal, table, or list. Opinionated patterns with Calm Precision principles, spacing, accessibility, and anti-patterns. Not for a full dashboard page; use `dashboard-design` instead.

  • dashboard-design

    Use when building a full dashboard page — any view that surfaces the current state of work, data, or decisions so someone can orient and act. Covers archetype selection, MECE data separation, the append-only record contract for dashboards that capture actions, progressive disclosure, and navigation.

  • data-visualization

    Use when UI work includes a chart, graph, KPI, analytical search response, metric, trend line, ranking, distribution, or data storytelling. Provides chart-worthiness gates, chart routing, hierarchy, attribution, accessibility, and validation rules. Not for a full dashboard page layout; use `dashboar

  • design-director

    Use when starting a page, flow, app, or dashboard build, resolving mockup-gallery or imagegen concept targets, or acting as the primary IBR design agent. Produces design intent, specialist planning passes, target roles, and validation criteria before implementation. Not for a small isolated componen

  • design-guidance

    Use for a small isolated UI component or a tactical pre-build design decision — one card, form, or layout tweak. Provides Calm Precision rules (vendored skill `calm-precision`, authoritative), component pattern selection, and active design tokens. Not for a full page, flow, app, or dashboard build;

  • design-implementation

    Use when the user asks to build UI, implement a design, match a mockup, or when frontend files (.tsx/.jsx/.vue/.svelte/.css/.swift) are being edited and implementation must align with intent.

  • design-reference

    Use when the user asks to screenshot a page, capture a design, save a reference, or shares a design URL (Mobbin, Dribbble, Figma, Behance, Awwwards) for visual inspection.

  • design-system

    Use when setting up a project's design system or modifying design constraints. Initialize design tokens, view active principles, add custom rules, update token values.

  • design-validation

    Use when the user asks to audit UI, validate the build, check accessibility, find regressions, compare before/after, or run a full scan — post-build verification pass across the interface. Prefer this over writing a Playwright script for the same check.

  • interactive-testing

    Use when the user asks to test a form, click through a flow, test search or login, interact with a page, evaluate JS in the page, screenshot an element, or needs browser interaction testing — instead of writing a Playwright script.

  • ios-design-router

    Use as the entry point for iOS UI design work in IBR. Classifies apps into 6 archetypes (Utility, Content, Productivity, Consumer, Editorial, Tool/Pro) and routes to domain references.

  • ios-design

    Use when building SwiftUI/UIKit apps for iPhone/iPad, or when /ibr:build preamble returns platform=iOS — HIG rules for navigation, colors, SF Symbols, Dynamic Type, haptics, Liquid Glass. Not for architecture, SwiftData, concurrency, or CI/CD; use `apple-platform` instead.

  • iterative-refinement

    Use when an IBR refinement loop is active (.ibr/loop-state.json active=true), the Stop hook re-feeds iteration context, or user asks to "iterate until it passes" or "refine this UI".

  • macos-ui

    Use when building AppKit/SwiftUI apps for Mac, or when /ibr:build preamble returns platform=macOS — HIG rules for windows, toolbars, menu bar, materials, Liquid Glass, plus manual signing/notarization/distribution steps. Not for app architecture, SwiftData, concurrency, or the CI/CD pipeline; use `a

  • mobile-web-ui

    Use when building responsive web UI for phones, or when /ibr:build preamble returns platform=web mobile. Covers viewport/safe-area, thumb zones, touch, Material 3, iOS Safari, WCAG 2.2.

  • mockup-gallery-bridge

    Use when /ibr:build detects .mockup-gallery/ or IBR needs to tie a build to gallery-selected mockups. Reads ratings/selections, enforces approved target roles, preserves scratch-first workflow, and writes implementation completion. Filesystem only.

  • native-testing

    Use when working on iOS, watchOS, or macOS apps — .swift files, SwiftUI views, simulators. IBR's native scan workflow for touch targets, a11y labels, watchOS constraints, Fix Guide.

  • obsidian-plugin-ui

    Use when working on an Obsidian plugin's UI — a view class, an ItemView, a modal or sheet, styles.css, or anything under .obsidian/plugins. Covers the scan_obsidian workflow, base-CSS fidelity, Obsidian's element rules that override plugin CSS, and multi-width verification.

  • ui-brainstorm-preamble

    Use at the start of /ibr:build to capture UI context before Design Director and brainstorming. Captures platform, scope, design mode, archetype, references, optional imagegen concept need, gallery target roles, density, and ask gates. Writes preamble.json.

  • ui-guidance-library

    Use when /ibr:build asks the user to pick a template or to show available UI guidance. Indexes central + project-local templates and snapshots a pick to .ibr/ui-guidance/active.md.

  • web-design-router

    Use when planning or building web UI, web apps, dashboards, SaaS tools, AI chat interfaces, editors, content sites, checkout flows, or internal admin screens. Classifies the web archetype and loads default layout, hierarchy, state, and validation rules.

Slash commands (14)

  • /ibr:artifact

    Author, check, and port single-file self-contained HTML artifacts. Works inside Claude and as a plain CLI any agent can run.

  • /ibr:build

    UI-focused build orchestrator. Sequences preamble -> optional imagegen concepts -> design director -> brainstorm/plan -> implement -> validate/iterate. Uses Calm Precision, platform routers, web archetypes, data-viz guidance, Mockup Gallery targets, and approved generated concepts as first-class inp

  • /ibr:cancel-iterate

    Cancel an active IBR iterative refinement loop

  • /ibr:capture

    Capture external design references — screenshot a URL, extract full HTML/CSS, or crawl a sitemap. Unified entry point wrapping existing IBR primitives.

  • /ibr:compare

    Compare current page state against baseline and show what changed (regression check)

  • /ibr:feedback

    Report a bug or send feedback about the ibr plugin

  • /ibr:ibr

    Main ibr entry. Dispatches to a subcommand based on your request, or lists options if unclear. Use `ibr:<subcommand>` to target a specific action directly.

  • /ibr:iterate

    Run one iteration of a test-fix loop and detect convergence (stagnant, oscillating, regressing)

  • /ibr:match

    Compare a design mockup PNG against a live rendered web page using SSIM and pixel diff. Returns a pass/review/fail verdict.

  • /ibr:only-use-ibr

    Enforce IBR-only for capture and validation tasks. Blocks Playwright screenshot/snapshot tools while keeping Playwright available for unsupported automation.

  • /ibr:prefer-ibr

    Enable soft IBR preference. Claude will prefer IBR for UI validation, capture, and semantic interactions while Playwright MCP remains available for unsupported browser automation.

  • /ibr:screenshot

    Capture a screenshot of any URL and return the image for Claude to see. Optionally save to the design reference library.

  • /ibr:snapshot

    Capture a baseline of a URL before making UI changes (for regression verification)

  • /ibr:ui

    Launch the IBR design validation dashboard to view scan results, comparisons, and element data

Subagents (1)

  • design-validator

    Use this agent when building UI from user descriptions. Validates implementation matches intent using IBR scan data (computed CSS, handlers, accessibility). Invoke when user says "check my UI", "verify the design", "does this match what I asked for", or after building any UI component.

Hooks (4)

  • PreToolUse

    root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; hook="$root/hooks/ibr-pre-change.sh"; if [ -x "$hook" ]; then "$hook"; else printf '{}'; fi

  • PreToolUse

    root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; hook="$root/hooks/ibr-playwright-tip.sh"; if [ -x "$hook" ]; then "$hook"; else printf '{}'; fi

  • PostToolUse

    root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; hook="$root/hooks/ibr-post-change.sh"; if [ -x "$hook" ]; then "$hook"; else printf '{}'; fi

  • Stop

    root="${CLAUDE_PLUGIN_ROOT:-$CLAUDE_PROJECT_DIR}"; hook="$root/hooks/ibr-loop-hook.sh"; if [ -x "$hook" ]; then "$hook"; else printf '{}'; fi

View source on GitHub rosslabs.ai

More from tyroneross/RossLabs-AI-Toolkit

All 19 plugins →

build-loop

claudecodex

Turns big code changes into a checked, repeatable workflow. Five phases (assess, plan, execute, review, iterate), plus an optional learn phase. Splits work into parallel chunks where it can. Picks the right model for each task. A strong model plans and reviews. A faster model writes code. A small model does pattern checks. Catches the common ways big changes go wrong. The diff drifts from the plan. The implementer makes quiet design calls you never see. Tests pass but pages do not render. Fake data leaks into production. Plans must list every design decision up front. The implementer must say which decisions it made. A lint compares the claim to the actual diff. Work with six or more design decisions auto-routes to the strong model in one pass. A read-only critic runs before full validation. Cheap checks catch the obvious mistakes first. Includes an optimize mode that runs multiple tests in a single experiment using Design of Experiments. You can test six variables at once instead of one. The mode plans the test matrix, runs each combination, and tells you which variable actually moved the number. Bundles a debugger memory and an architecture engine that maps the codebase before each build. Use it for features, refactors, migrations, schema changes, anything that touches more than one file. Skip it for fixes under about 20 lines. Verifies the production deploy after a push (Vercel): polls the deployment to a terminal state and probes changed routes — an auth-gated 401/403 is healthy, only a 5xx or build error fails. An independent commit auditor runs at the git-commit boundary on every commit (manual user, Codex, build-loop, IDE) and gathers its own context from intent, goal, PRD, and constitution — the running session renders one of four verdicts in conversation: yay, nay, suggest correction, look again.

60 skills · 2 commands · 29 agents · hooks

0

Build-loop extension with Karpathy's autoresearch pattern: constrained scope + mechanical metric + git commit/revert + autonomous iteration for app development optimization.

9 skills · 11 commands · 9 agents · hooks

0

coding-debugger

claudecodex

Standalone supporting plugin for build-loop's debugger bridges — extended capability (cross-project incident memory, additional assessor coverage, coordination across build-loop instances). Build-loop bundles its own debug-loop / debugging-memory / logging-tracer skills + MCP server; install this only when bundled capability isn't enough.

3 skills · 9 commands · 7 agents · 1 MCP server · hooks

0

ai-persona-lab

claudecodex

Launch synthetic personas to review your app UI/UX, architecture, and code base before you deploy

4 skills · 5 commands · 9 agents

0

research

claudecodex

Structured research with central knowledge base, source scoring, and claim verification

4 skills · 13 commands · hooks

0

spectra

claudecodex

Capture screenshots, videos, and polished demo clips — spotlight focus, lower-third captions, and a tagged library — across web, macOS, and iOS

7 skills · 9 commands · 1 agent · 1 MCP server

0

Similar plugins

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

anthropics/claude-code 155,476

Professional UI/UX design intelligence for AI coding assistants. Includes searchable databases of styles, colors, typography, charts, and UX guidelines for React, Next.js, Astro, Vue, Nuxt.js, Nuxt UI, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, and Three.js.

7 skills

nextlevelbuilder/ui-ux-pro-max-skill 148,759

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.

1 skill · 4 agents · hooks

pbakaus/impeccable 109,099

storybook

claudecodex

Build, preview, and test UI components with Storybook.

7 skills

storybookjs/storybook 91,552

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain ibr?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins19 plugins