惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Engineering at Meta
Engineering at Meta
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
小众软件
小众软件
博客园_首页
T
Tailwind CSS Blog
美团技术团队
博客园 - 叶小钗
Microsoft Security Blog
Microsoft Security Blog
有赞技术团队
有赞技术团队
Apple Machine Learning Research
Apple Machine Learning Research
大猫的无限游戏
大猫的无限游戏
Microsoft Azure Blog
Microsoft Azure Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
I
InfoQ
MongoDB | Blog
MongoDB | Blog
The Cloudflare Blog
J
Java Code Geeks
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 聂微东
酷 壳 – CoolShell
酷 壳 – CoolShell
Blog — PlanetScale
Blog — PlanetScale
IT之家
IT之家
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Y
Y Combinator Blog

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
design-review: a senior design critique in your terminal
jprim · 2026-06-21 · via Hacker News - Newest: "AI"
Claude Code skill

A senior design
critique, in your terminal.

Point it at a URL, a screenshot, or a component. Get ranked, specific findings, then let it apply the fixes. 
Craft standards, not vibes.

What it does

Reviews like a design lead would.

Fix what matters first

Every finding ranked blocking → important → polish, so you ship the critical stuff and skip the bikeshedding.

Receipts, not opinions

Real numbers behind every call: WCAG contrast, 45–75ch line length, 44px tap targets. Never "make it pop."

Reviews anything you've got

A live URL, a screenshot, or a raw component. It reads the code and cites the exact line.

It flags. It fixes.

Run --apply and watch it rewrite contrast, focus states, alt text and motion, in place.

Accessibility, every pass

Contrast, semantics, focus order, labels, and reduced-motion. Caught automatically, not bolted on later.

Tells you what's working

Closes every review with your strengths and the one change that moves the needle most.

What it reviews

Ten dimensions, every pass.

01

Hierarchy & layout

Clear focal point, sensible scan path, grouping, alignment to a grid, whitespace as structure.

02

Typography

Limited type scale, line-height, 45–75ch measure, font pairing, no widows or orphans.

03

Spacing & rhythm

Consistent 4/8px scale, even vertical rhythm, symmetric padding. No arbitrary gaps.

04

Color & contrast

WCAG AA (4.5:1 text, 3:1 large/UI), restrained palette, never color alone for meaning.

05

Motion

Purposeful, fast timings, natural easing, and a prefers-reduced-motion variant.

06

Component states

Hover, focus-visible, active, disabled, loading, empty, error, plus ≥44px tap targets.

07

Accessibility

Semantic HTML, labels, alt text, logical focus order, full keyboard operability.

08

Responsiveness

Fluid type and spacing, no overflow or clipping from 320px up, touch-appropriate.

09

Content & copy

Clear headlines, scannable structure, descriptive CTAs, human microcopy and errors.

10

Consistency & brand

Reused design tokens, consistent radii, shadows, and icon style across screens.

See it work

Watch a real critique and apply the fixes.

Install

Up and running in 30 seconds.

1

Add the marketplace and install the plugin:

# in Claude Code
/plugin marketplace add Superfuture/design-review
/plugin install design-review@superfuture

# …or drop the folder in manually
git clone https://github.com/Superfuture/design-review /tmp/dr
cp -r /tmp/dr/design-review/skills/design-review ~/.claude/skills/

2

Then just ask: "design review officialjp.com" or "critique this paywall screenshot."

Pricing

Free to try. Pay if it earns its place.

Free

$0

forever

  • The full skill + rubric
  • URL, image & code review
  • Community updates

Install free

Recommended

Pro

$12

one-time

  • Everything in Free
  • Expanded mobile & SwiftUI rubric
  • Brand-token consistency checks
  • Priority updates

Get Pro →

Team

$49

per team

  • Everything in Pro
  • Shareable team config
  • Custom rubric tuning
  • Email support

Get Team

FAQ

Questions, answered.

What is design-review?

A Claude Code skill that runs a senior-level design critique of any URL, screenshot, or component, ranked from blocking to polish, each finding with a specific fix you can auto-apply.

What's the difference between Free and Pro?

Free is the full skill and rubric, run locally in your terminal. Pro adds depth the free tier doesn't cover: an expanded mobile & SwiftUI rubric and brand-token consistency checks, generated server-side so it stays current.

How do I activate Pro?

After checkout you get a license key on the activation page. In Claude Code run /design-review:activate <your-key>, or paste the key when Crit first asks on a Pro review. Your Pro reviews then include the extra depth.

Is it a subscription?

No. Pro is a one-time $12 unlock. Team is a separate plan, currently by waitlist.

I lost my key.

It's tied to your email. Get in touch and we'll resend it.

Refunds?

If Pro isn't earning its place, contact us within 14 days for a refund.