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 cnfeat/top-pm-skills --skill running-design-reviewsgit clone --depth 1 https://github.com/cnfeat/top-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/cnfeat/top-pm-skills/running-design-reviews)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/running-design-reviews"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/running-design-reviews/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/cnfeat/top-pm-skills/running-design-reviews"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/running-design-reviews.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 | $0.00043 | $0.00827 |
| Opus 5 | $0.00022 | $0.00413 |
| Sonnet 5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
running-design-reviews 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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Design Reviews
Help the user run effective design reviews and critiques using frameworks from 8 product leaders.
How to Help
When the user asks for help with design reviews:
- Understand the review context - Ask what stage the design is at and what kind of feedback is needed
- Establish the hierarchy - Help them prioritize feedback by value, then usability, then delight
- Structure the critique - Guide them on how to frame feedback constructively
- Set the quality bar - Help them define what "good enough to ship" means
Core Principles
Follow the feedback hierarchy: Value, then Ease of Use, then Delight
Julie Zhuo: "The first thing that's most important to address is, well, is this thing actually valuable, is this solving the problem? Then once we do that, then let's focus on the next layer which I think about as ease of use... And then finally... delight." Disregard feedback about aesthetics until the core value proposition is validated.
Assign sponsors for major projects
Karri Saarinen: "We are basically the sponsors for the projects. So then we are responsible reviewing the work. And so we might just have a meeting where we go through, okay..." Assign a founder or senior leader as a sponsor for every major project to oversee quality through live demos rather than static slide decks.
Review 100% of shipped screens
Dmitry Zlokazov: "Founders of the company, they still review a hundred percent of screens that are being shipped and everything that you will see in the app pass this review." Maintain a high quality bar by having senior leaders review every user-facing screen before shipping.
Structure reviews around specific feedback requests
Geoff Charles: "Any large rock that we have on the roadmap needs to be brought into the product review process... but it needs to be structured in a way where you are asking specifically for what type of feedback you want." Only bring high-risk decisions to formal reviews and require presenters to specify exactly what feedback they need.
What ships with it
1 file 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.
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.
- 9d ago First seen · 65 lines · 43 tokens per session scan A 341490136d49
running-design-reviews is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 827 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 2026-09-03.
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 $ultragoal 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.