claude

design

Skills for the design of a product's interface: review a screen or flow against usability heuristics, audit a page against WCAG 2.2 Level AA, set up design tokens, themes and component states, plan a small usability test with real people, write and review interface copy, structure a site's navigation and taxonomy, spec a design for build, and set the visual hierarchy, the responsive layout and the forms a screen is built from.

0 on GitHubby Serhii ZolotovMITupdated 2 days agodevelopment
/

Plugin design from marketplace greenblacked-ai in greenblacked/AI. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (16)

  • accessibility-audit

    Audit a page, flow or component against WCAG 2.2 Level AA: run the automated tools first because they are cheap, then the manual pass that automation cannot do (keyboard end to end, focus visible and not obscured, 200 percent zoom, 320 px reflow, screen reader names, reduced motion, target size), an

  • content-design

    Write and review the words in an interface — button and link labels, error and empty-state messages, confirmation and loading copy, and the tone that holds across a flow. Covers plain language, the action named in the label, errors that say what happened and what to do, and one voice whose tone shif

  • data-visualisation

    Turn data into a chart that is correct and readable in any medium (matplotlib, Vega-Lite, Plotly, D3 or a spreadsheet): pick the chart from the question and the data's shape, keep bars on a zero baseline, avoid dual axes and 3D, use a colour-blind-safe palette that holds 3:1 contrast on light and da

  • design-handoff

    Produce the spec that takes a design from approved to built: the states and edge cases, responsive and content extremes, the token and component mapping, accessibility annotations, and acceptance criteria an engineer can check against. Covers redlines, the handoff pack, and a review that catches wha

  • design-system

    Set up or tidy a design system's foundations: design tokens named by role (colour, type with fallbacks, spacing, radius, elevation, motion), light, dark and further themes that redefine the same role tokens, and component state rules so buttons and controls stay consistent. Covers where translucent

  • distinctive-page-design

    Design a new marketing or landing page so it does not come out as the default a code model converges on. Inherit any existing design system, ask once for the real material, audience, action and tone, choose a page shape by its fingerprint and a visual material by visible scoring, record the decision

  • form-design

    Design or redesign a form people can complete: label every field, order the questions the way the user thinks, validate inline and only after input, put errors next to the field and say how to fix them, and make the primary action obvious and the whole thing keyboard-operable. Use when designing or

  • information-architecture

    Structure a site or app so people can find things: the sitemap, the navigation, the taxonomy and the labels, and when to browse versus search. Covers grouping content by the user's mental model rather than the org chart, naming sections in the user's words, flattening deep hierarchies, and testing t

  • motion-showcase

    Turn a finished static design into motion, either a seamless looping showcase delivered as MP4 and GIF, or entrance and ambient animation written into a site's own code. Choose which first, then rebuild the design as separate layers instead of animating a flat picture, leave the backdrop alone, prov

  • problem-validation

    Validate whether a proposed customer problem is real and worth addressing before specifying a solution. Use when a team asks whether to build an idea, whether people actually experience a pain, how to interview prospective users without pitching, or what evidence would justify discovery moving forwa

  • product-design

    Build faux product UI visuals for marketing and docs: a simplified rendering of the user's own app or browser window, dashboard, phone screen, notification, terminal or bento grid of feature cards, cropped for a hero, feature card, docs page, changelog or social card, as a still or a short scene whe

  • responsive-design

    Design a layout that works across screen sizes: choose breakpoints from where the content breaks rather than from device names, decide what reflows, wraps or hides at each, and keep the primary task reachable and the touch targets large on the smallest screen. Use for any \"does this work on mobile\

  • ui-ux-review

    Review one screen or flow (a live URL, screenshot, Figma frame or its code) against usability heuristics and platform guidance, and return ranked findings that each carry the evidence, the consequence for a user and the smallest fix. Walks the primary task path and every state before any polish, and

  • usability-test-plan

    Plan and run a small usability test with real people: the question and the decision it feeds, who to recruit and how many, neutral task wording, a think-aloud script, the measures (task success, time, System Usability Scale), and turning observations into severity-rated fixes before the next round.

  • visual-design

    Review or set a screen's visual design: the hierarchy that tells the eye where to go, a type scale, colour and spacing systems, alignment, and the contrast of emphasis that makes one action primary. Use for any \"does this look right\" or \"make this screen work visually\" question. Casual asks incl

  • visual-review

    Review a rendered web UI from screenshots without trusting a vision model for what code can measure: pin the environment (browser image, fonts, animations off, seeded data, masked regions), capture a viewport and theme matrix, pixel-diff against a baseline, run contrast, overflow, bounding-box, DOM-

Slash commands (1)

  • /design:visual-review

    Review a rendered page from screenshots - pin the render, capture the viewport, theme and reduced-motion matrix, diff against an optional baseline, run the code checks, then have the screenshot-reader subagent read crops - and report measured and unverified findings separately.

Subagents (1)

  • screenshot-reader

    Read one or more screenshots of a UI, such as a page, a flow, a before and after pair or viewport captures, in its own context so the images never enter the caller's, and return findings that each name a file, a region (bounding box or element) and what is visibly wrong. Keeps what the image shows a

View source on GitHub

More from greenblacked/AI

All 29 plugins →

gamedev

claude

Skills for making games: build a playable prototype and take it to a finished game, hold a frame budget on the hardware you are shipping to, choose a multiplayer authority model and make it survive latency, tune numbers against telemetry instead of taste, and keep an asset pipeline from eating the build.

39 skills · 2 commands · 2 agents

0

security

claude

Skills for the defensive side of shipping software: review a change for the vulnerability classes that actually get exploited, reduce who can do what toward least privilege without breaking production, rotate or contain a credential, harden a container image and keep checking it, read a Terraform plan for what it destroys, preserve evidence and build an intrusion timeline after a compromise, respond to credential stuffing, write and test detection rules, prove tenant isolation, handle vulnerability reports from outside researchers, and reverse engineer the binaries, managed CIL assemblies, APK packages, packaged apps, firmware and WebAssembly you are authorised to examine — including de-bloating a smart-TV or streaming device you own.

31 skills · 2 commands · 5 agents

0

coding

claude

Skills for the daily loop of changing code: review a diff for the defects that actually break production, debug a failure down to a proven cause, decide what to test before writing tests, restructure code without changing behaviour, orient yourself in an unfamiliar codebase, review a regex for catastrophic backtracking, write documentation that stays true, scaffold new production-ready code, design an API you can still evolve, land a dependency upgrade, build a website, and author a skill that fires when it should.

29 skills · 1 command · 5 agents

0

Skills for keeping a running system alive: triage a red pipeline to its real cause, get a broken Kubernetes workload back before diagnosing it, design alerts where every page is actionable, instrument a service so the next incident is answerable, write the runbook a stranger can follow at 3am, rehearse failure on purpose, plan for load before it arrives, and find out why the bill grew.

19 skills · 2 commands · 7 agents

0

manager

claude

Skills for engineering leadership: take over a team and audit what you inherited, record decisions, write status updates, run postmortems and incident comms, read delivery health, review on-call load, design the team cadence, a reorganisation and goals, make the case for headcount or for paying down tech debt, map team skills and single points of knowledge, plan onboarding, hire, benchmark pay, evaluate vendors, handle retention, growth reviews, improvement plans and difficult conversations, and assess how a team uses AI. Also ships two subagents, for reading contracts and synthesising feedback, and two commands.

22 skills · 2 commands · 2 agents

0

Skills for code that runs on a user's browser or phone: field performance, hydration, memory, version skew, service workers, CSP and Safari bugs, dates and locales, crashes, hangs, startup, battery, bad networks, on-device migrations, deep links, pushes and app size.

22 skills · 1 agent

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain design?

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 plugins29 plugins