MCPInstall

plan-design-review

Senior designer review of a PLAN before implementation, from Garry Tan's gstack. Interactive: rates the plan's design dimensions 0-10, finds missing design decisions and adds them to the plan, and calls out generic AI-slop patterns.

Installs
220
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/podo/design-agent-skills --skill plan-design-review
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads plan-design-review automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

plan-design-review

Catalogue stub — part of garrytan/gstack (plan-design-review)

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->

Decision tree

  1. Is the full skill already installed?

    • f=~/.claude/skills/gstack/plan-design-review/SKILL.md; [ -e "$f" ] && ! grep -qs "^das:" "$f" && echo "installed" || echo "pointer"
    • installed → invoke it and proceed
    • pointer → go to step 2
  2. Install (the skills CLI cannot install this one):

    This skill is part of gstack and calls gstack's shared tooling (~/.claude/skills/gstack/bin/…), so install gstack itself rather than the single skill (--skill plan-design-review fails because the CLI only sees gstack's root router; the subpath form npx skills add garrytan/gstack/plan-design-review installs the instructions without the tooling). ./setup needs Bun, builds binaries, downloads Chromium and registers a Stop hook in your Claude settings (opt out with ./setup --no-timeline-stop-hook); ask the user before running it. Upstream's README also tells agents to add a gstack section to CLAUDE.md after setup.

    git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack
    cd ~/.claude/skills/gstack && ./setup
    

Heads-up

  • Requires: Bun (setup refuses versions older than 1.3.3; upstream tests 1.4.2+), Git and Claude Code; Optional: the gstack design binary plus an OpenAI API key for mockups; Codex CLI for outside design voices
  • License: MIT
  • Download size: ~98 MB.
<!-- das:install:end -->

Invoke after install

  • Skill name: plan-design-review
  • Trigger phrases: "plan design review", "design plan review", "review ux plan", "check design decisions", "AI slop detection"

What it does

A designer's-eye review of a plan, not of a live site: the agent rates the plan's overall design completeness on a 0-10 scale, explains what a 10 would look like, then works through seven passes (information architecture, interaction states, user journey and emotional arc, AI-slop risk, design-system alignment, responsive and accessibility, unresolved decisions), asking you about each gap and adding the decisions you accept to the plan before any code is written. It can optionally render visual mockups (needs gstack's design binary and an OpenAI API key) and ask outside voices for an independent design opinion.

gstack behaviour to know about, per its README: outside reviews are on by default and send the review prompt and the relevant plan or code to a second model provider (Codex, under your own login; turn off with gstack-config set codex_reviews disabled); an update check against GitHub runs by default; usage telemetry is opt-in and asked once.

When NOT to use

  • Reviewing or fixing a live, running UI — use design-review-garrytan
  • Building a design system from scratch — use design-consultation
  • When you do not want to install gstack's tooling (Bun, binaries, Chromium, a Stop hook)

FAQ

What does the plan-design-review skill do?

Senior designer review of a PLAN before implementation, from Garry Tan's gstack. Interactive: rates the plan's design dimensions 0-10, finds missing design decisions and adds them to the plan, and calls out generic AI-slop patterns.

How do I install plan-design-review?

Run npx skills add https://github.com/podo/design-agent-skills --skill plan-design-review in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/plan-design-review/ (personal) or .claude/skills/plan-design-review/ (project).

Which AI agents can use plan-design-review?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is plan-design-review safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains plan-design-review?

It is published by podo in podo/design-agent-skills. It has 220 recorded installs.

More from podo/design-agent-skills

View all →

distinctive-frontend

podo/design-agent-skills

Generates distinctive interfaces that avoid generic AI aesthetics, using extreme typography, cohesive themes (Cyberpunk, Brutalist, Vaporwave, Nordic Minimalism), orchestrated staggered animations, and layered backgrounds. Originally published as Koomook/claude-frontend-skills; installed from a verbatim mirror.

Frontend & Design589 installs

taste-skill

podo/design-agent-skills

Anti-slop frontend art direction (tasteskill v2). Deals researched design directions for a page or app screen from a library built from curated gallery sites, enforces a strict no-generic-AI-UI house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Works in any web stack.

Frontend & Design266 installs

emilkowalski-skill

podo/design-agent-skills

Emil Kowalski's design engineering skills. Creator of Sonner, Vaul, and animations.dev. Covers the animation decision framework, custom easing curves, component interaction principles, and typography rules, plus skills to review, audit, and improve motion, performance, and native-feeling mobile web UI.

Frontend & Design239 installs

ui-craft

podo/design-agent-skills

Design engineering skill for AI coding agents: opinionated rules for how interfaces should look, move, and feel, a required discovery phase before coding, domain references, three style variants (minimal, editorial, dense-dashboard), and an anti-slop approach that flags generic patterns such as centered hero sections, Inter-only typography, and three-column card grids. Covers premium UI taste, component patterns, and design-engineering workflows.

Frontend & Design231 installs

color-expert

podo/design-agent-skills

A large color-science knowledge base applied to UI/UX design. Covers OKLCH/OKLAB color spaces, palette generation, accessibility contrast ratios, color naming, pigment mixing, and historical color theory. By meodai, creator of color-names.

Frontend & Design230 installs

apple-hig-skills

podo/design-agent-skills

Apple Human Interface Guidelines as agent skills covering iOS, macOS, visionOS, watchOS, and tvOS. From raintree-technology, makers of the Apple HIG compliance website.

AI & Agents224 installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.