product-design-review

product-design-review is a skill for Claude Code, Codex from fmind/dotfiles. It costs 47 tokens per session (947 once invoked), scanned A, original, MIT.

A review of a customer-facing interface and the steps users take to complete a task. It checks interaction, appearance, mobile layouts, keyboard and screen-reader access, content, and behavior while running.

In plain words
What is it for?
Use it for user-experience audits, design reviews, interface polish, onboarding, empty states, redesigns, and accessibility checks. It reviews the real product and its content before suggesting focused improvements.
Why use it?
It finds places where users may get confused, lose trust, or be unable to finish their task. It also checks states such as onboarding, empty screens, and errors instead of judging only a static screenshot.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for gstack. Also seen: built for gstack.

Good fit Use it for user-experience audits, design reviews, interface polish, onboarding, empty states, redesigns, and accessibility checks. It reviews the real product and its content before suggesting focused improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fmind/dotfiles/product-design-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add fmind/dotfiles --skill product-design-review
Clone the repo
git clone --depth 1 https://github.com/fmind/dotfiles

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for product-design-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dotfiles/product-design-review.svg)](https://agentmods.dev/skills/fmind/dotfiles/product-design-review)
Your own site
<a href="https://agentmods.dev/skills/fmind/dotfiles/product-design-review"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/product-design-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 947 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00947
Opus 5 $0.00023 $0.00474
Sonnet 5 $0.00009 $0.00189
Haiku 4.5 $0.00005 $0.00095

Measured 8d ago against content hash cbca2160106b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

product-design-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/product-design-review/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Design Review

Judge whether a real user can understand, trust, and complete the surface's primary job, then improve only what the requested scope authorizes.

Design Posture

  • Identify the audience, context, and single job of the surface before discussing aesthetics.
  • The brief and established product identity win. In Fmind work, use fmind-visuals for brand truth; do not replace Tokyo Night or existing tokens by habit.
  • Classify the task as preserve, refine, or redesign. A critique does not authorize code edits, factual copy changes, or a new visual identity.
  • Prefer one justified signature over decorative variety. Remove elements that do not encode meaning or help the task.
  • Review real content, states, and runtime behavior. A static happy-path screenshot is insufficient.
  • Bound iteration: one batched desktop/mobile review, one coherent fix pass when authorized, and one confirmation pass.

Workflow

  1. Recover product truth: Read the brief, existing product or design artifacts, tokens, components, user research, and representative content. Name any missing evidence.
  2. Map the journey: Identify entry points, primary action, decisions, exits, failure recovery, and time to first value.
  3. Inspect the live surface: Use quality-assurance to capture desktop and mobile states, DOM semantics, console/network errors, keyboard behavior, focus, reduced motion, and screenshots when a runnable app exists.
  4. Review comprehension: Check information architecture, hierarchy, labels, vocabulary, affordances, progressive disclosure, cognitive load, and whether the next action is obvious.
  5. Review every state: Cover first run, loading, empty, partial, success, validation, permission, error, offline, destructive confirmation, and recovery states that apply.
  6. Review craft: Evaluate typography, spacing, alignment, color, contrast, density, imagery, motion, consistency, and relationship to the subject. Flag generic defaults only when they weaken the brief.
  7. Review inclusion: Check semantic structure, keyboard access, focus visibility and restoration, touch targets, zoom/reflow, screen-reader names, contrast, motion preferences, localization, and plain-language copy.
  8. Review constraints: Identify performance, browser, device, content-length, data-density, privacy, and implementation constraints that change the design recommendation.
  9. Prioritize: Rank findings by blocked task, trust or accessibility harm, frequency, and effort. Recommend the smallest coherent improvement before aesthetic extras.
  10. Verify authorized changes: Re-run the same representative states at desktop and mobile sizes and record evidence without entering an unbounded polish loop.

Read the full file on GitHub · 55 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 55 lines · 47 tokens per session scan A cbca2160106b

Subscribe to this mod's changes

product-design-review is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 947 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.