Survey design framework grounded in product research best practices from nine leaders.
Works with
Prioritize CSAT over NPS for better statistical properties and business outcome correlation; use 5-7 item scales
Design single-variable questions only; avoid double-barreled phrasing that conflates multiple concepts
Target customers 3-6 months post-signup when memory of the \"before\" state is fresh and relevant
Use MaxDiff (Most/Least) methodology for feature prioritization rather than unlimite
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiondesigning-surveysExecute the skills CLI command in your project's root directory to begin installation:
Fetches designing-surveys 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 designing-surveys. Access via /designing-surveys 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 design effective surveys using frameworks from 9 product leaders who have built rigorous research and feedback systems.
When the user asks for help with surveys:
Judd Antin: "NPS is the best example of the marketing industry marketing itself. The consensus in the survey science community is that NPS makes all the mistakes. Customer satisfaction, a simple CSAT metric, is better. It has better data properties, it is more precise, it is more correlated to business outcomes." Use CSAT with 5-7 item scales instead.
Nicole Forsgren: "Let them pick three, just three. Of those three, how often does this affect you? Is this hourly? Is this daily? Is this weekly?" Limit respondents to their top barriers to keep data clean, then measure frequency to weight impact.
Gia Laudi: "Very importantly, they signed up for your product recently enough that they remember what life was like before. Generally, we say that's in the three to six-month range." Target customers who have been using the product 3-6 months so their memory of the 'before' state is fresh.
Laura Schaffer: "We just asked for forgiveness and put these questions into the signup flow. An improved conversion by like 5%, just improved signups." Adding 'good friction' in the form of targeted questions can increase conversion by reassuring users they're in the right place.
Nicole Forsgren: "You're asking four different questions there. If someone answers yes, was it the build? Was it the test? Was it slow or was it flaky?" Ensure each survey question only asks about one specific variable.
Madhavan Ramanujam: "Identify the most important for you, and the least important. If you do this a few times, you will be able to prioritize the entire feature set in a relative fashion." MaxDiff (Most/Least) surveys are superior to simple ranking for identifying value drivers.
For all 10 insights from 9 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
mblode/agent-skills
github/awesome-copilot
sickn33/antigravity-awesome-skills
leonxlnx/taste-skill
erichowens/some_claude_skills
We added designing-surveys from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in designing-surveys — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend designing-surveys for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
designing-surveys fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Registry listing for designing-surveys matched our evaluation — installs cleanly and behaves as described in the markdown.
Keeps context tight: designing-surveys is the kind of skill you can hand to a new teammate without a long onboarding doc.
designing-surveys has been reliable in day-to-day use. Documentation quality is above average for community skills.
Solid pick for teams standardizing on skills: designing-surveys is focused, and the summary matches what you get after install.
We added designing-surveys from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
designing-surveys is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
showing 1-10 of 58