Framework for running design reviews using feedback hierarchy and structured critique.
Works with
Prioritize feedback by value first (does it solve the problem?), then usability, then delight; defer aesthetic concerns until core value is validated
Assign senior leaders as project sponsors to oversee quality through live demos and review 100% of shipped screens before launch
Structure reviews around specific feedback requests; ask presenters exactly what type of input they need rather than openi
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionrunning-design-reviewsExecute the skills CLI command in your project's root directory to begin installation:
Fetches running-design-reviews from refoundai/lenny-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate running-design-reviews. Access via /running-design-reviews in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
616
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
616
stars
Help the user run effective design reviews and critiques using frameworks from 8 product leaders.
When the user asks for help with design reviews:
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.
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.
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.
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.
Jessica Hische: "Always think big picture before you think minutiae, because sometimes people think that... They'll throw a bunch of minutiae stuff at me, but it's because they don't know what's really bugging them." Ask "What is the overall thing that's bothering me?" before commenting on specific elements.
Jessica Hische: "Use 'blurred eyes' to look at a brand's overall cohesiveness rather than focusing on individual pixels." Step back from details to assess whether the overall design holds together.
For all 10 insights from 8 guests, see references/guest-insights.md
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
anthropics/claude-code
leonxlnx/taste-skill
sickn33/antigravity-awesome-skills
erichowens/some_claude_skills
hyperb1iss/hyperskills
omer-metin/skills-for-antigravity
Keeps context tight: running-design-reviews is the kind of skill you can hand to a new teammate without a long onboarding doc.
running-design-reviews has been reliable in day-to-day use. Documentation quality is above average for community skills.
running-design-reviews is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
running-design-reviews is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
running-design-reviews reduced setup friction for our internal harness; good balance of opinion and flexibility.
Useful defaults in running-design-reviews — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
running-design-reviews reduced setup friction for our internal harness; good balance of opinion and flexibility.
running-design-reviews is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
I recommend running-design-reviews for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
running-design-reviews reduced setup friction for our internal harness; good balance of opinion and flexibility.
showing 1-10 of 68