Agent skill · data analytics · refoundai
analyzing-user-feedback
Help users convert massive volumes of qualitative and quantitative feedback into high-confidence product decisions through rigorous synthesis and internal immersion.
Why this skill is useful
Provides frameworks and methodologies for analyzing user feedback that the AI wouldn't reliably generate on its own.
What it needs
About 4k tokens when loaded. Last updated 2026-07-16. 1,223 stars on the source repository.
What this skill does
Analyzing User Feedback Transform raw signals into actionable insights by scaling empathy and synthesis. Help the user with analyzing user feedback using insights from 19 guests and posts across Lenny's Podcast and Newsletter. How to Help 1. Categorize signals - Help the user group disparate feedback into themes or segments based on user influence and frequency. 2. Assess representativeness - Determine if feedback reflects a vocal minority or a broad user need using representation frameworks. 3. Set up dogfooding - Design internal processes to experience friction firsthand through audits and mandatory usage programs. 4. Apply AI synthesis - Guide the user in using LLMs to process large datasets like transcripts, reviews, and support tickets. Core Principles Experiential Empathy Jeff Weinstein: "We show up four to eight people total pretend to be some company with some outcome problem. Rule one is you do not work at Stripe and rule two is we're not here to solve any problems. This is just about practicing empathy for the customer." Build deeper empathy by having internal teams experience product friction firsthand without the distraction of immediate problem solving. Mandatory Service Participation Keith Yandell: "We have a program called WeDash, where, four times, a year all employees are required to go do deliveries. And I love doing it. I do it more than four times a year, and I usually take my daughters with me." Require every employee to perform the core service of the business to build authentic empathy and surface operational bugs. Creator Mindset Immersion Maya Prohovnik: "If they talk to users all the time, they see the data, but all of them, once they finally start doing their podcast, they're like, I get it. Something clicked and now I feel like I really understand what they need. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills refoundai/analyzing-user-feedback