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.
npx skills add exiao/pm-skills --skill design-reviewgit clone --depth 1 https://github.com/exiao/pm-skillsWrote 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.
[](https://agentmods.dev/skills/exiao/pm-skills/design-review)<a href="https://agentmods.dev/skills/exiao/pm-skills/design-review"><img src="https://agentmods.dev/badge/skills/exiao/pm-skills/design-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/exiao/pm-skills/design-review"><img src="https://agentmods.dev/badge/skills/exiao/pm-skills/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.02720 |
| Opus 5 | $0.00034 | $0.01360 |
| Sonnet 5 | $0.00013 | $0.00544 |
| Haiku 4.5 | $0.00007 | $0.00272 |
Grade A, and why
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
Run a full product design review. Walk through the product as a first-time user, answer 13 design questions, run a heuristic evaluation, and deploy a shareable before/after report to Surge.
Inputs
| Parameter | Required | Description |
|---|---|---|
| URL or feature | Yes | A live URL, local HTML file, or description of the feature to review |
| Context | No | Any additional context about the product, audience, or goals |
Start immediately with defaults. Do not ask clarifying questions. Make your best assumptions for anything you don't know.
Workflow
1. Walk Through as a New User
Open the URL in the browser. Navigate screen by screen, taking screenshots. React to what you see out loud:
- What am I being asked to do?
- Is it clear WHY I'd do it?
- Where would I get confused or frustrated?
- What would I expect to happen next?
Pay special attention to:
- Time to wow: How quickly does a new user think "this is why I came here"?
- Dead ends: Places where the user finishes something and there's no clear next step.
- Empty states: Screens that look broken when there's no data yet.
2. Answer the 13 Design Questions
For each question, provide a specific answer based on what you observed. Do not ask the user. Make your best assumption.
- What is the objective of this feature? What problem does it solve? What outcome does it drive?
- Who is this for? Specific user persona, not "everyone."
- When and why would they use it? The trigger moment. What just happened that brings them here?
- What are they thinking about? Their mental state, concerns, expectations when they arrive.
- How did they get here? The previous step in their journey. What screen or action preceded this?
- What do we want users to feel? The emotional response we're designing for.
- What would they do without this feature? The alternative. Manual workaround, competitor, nothing?
- What do they do next? The next step after using this feature. Is it clear?
- Are we confident this is better than what already exists? Compared to the current state or competitors.
- What can we remove to have it work just as well? Strip to the essential. What's decorative vs functional?
- If we throw away our constraints, would we still design it this way? Imagine unlimited time and resources.
- Will most users realize the value of this feature? Is the benefit obvious or hidden?
- Is this for user growth, engagement, or retention? Which metric does this primarily serve?
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/before-after-vs-dogfood.md 3.2 KB
- references/in-context-preview.md 4.8 KB
- references/multi-lens-prototype-and-surge-reconstruct.md 5.3 KB
- references/reviewing-live-products.md 4.3 KB
- references/screenshot-before-after-and-deploy-fallback.md 3.1 KB
- references/surge-deploy-down-fallback.md 2.4 KB
- references/surge-down-gh-pages-fallback.md 2.6 KB
- references/third-party-site-review.md 3.9 KB
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.
- 11d ago First seen · 205 lines · 67 tokens per session scan A f49671a751f0
design-review is a skill published in the GitHub repository exiao/pm-skills (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,720 once invoked, about $0.0003 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.