Agent Skill · Amplitude

analyze-feedback

Synthesizes customer feedback into actionable themes including feature requests, bugs, pain points, and praise. Use when planning product roadmap, understanding user sentiment, investigating specific issues, or preparing voice-of-customer reports.

Provider: Amplitude Path in repo: analytics-skills/skills/analyze-feedback/SKILL.md

Skill body

Analyze Feedback

Perform comprehensive feedback reviews, investigate specific feature requests, understand customer sentiment, then prepare concise but actionable voice-of-customer presentations

Instructions

Step 1: Understand Available Sources

Use Amplitude:get_feedback_sources to see which feedback channels are connected (surveys, support, app reviews, etc.).

Step 2: Get Themed Insights

Use Amplitude:get_feedback_insights with appropriate filters:

Step 3: Drill Into Specific Themes

For top insights, use Amplitude:get_feedback_mentions to see the actual user feedback driving each theme.

Step 4: Connect to User Segments

Use Amplitude:get_cohorts to understand if feedback themes correlate with:

Step 5: Present Findings

Structure as:

  1. Summary: Concise one-liner explaining the number of feedback sources and mentions analyzed along with the key takeaways from the analysis.
  2. Urgent Issues 🚩: Top bugs, issues, or pain-points noted by customers. Share 3-4 themes here unless prompted otherwise.
  3. Top Feature Requests 💡: Top feature requests noted by customers. Share 3-4 themes here unless prompted otherwise.
  4. Praises ❤️: Top praises or loved features noted by customers. Share 1-2 themes here unless prompted otherwise.
  5. Sentiment Analysis: Share a very concise overview of the themes, sentiment on a scale from 1-5 (5 being highest), and snippets of evidence.
  6. Prioritized Recommendations: Very concise section recapping the top 3-7 specific actionable recommendations (unless prompted otherwise) to follow-up on. Inlcude [p0],[p1],[p2],[p3] in front of each title to help size priority with p0 being most urgent and p3 being least.

Best Practices

Skill frontmatter

suggest_when: User asks about customer feedback, NPS, complaints, feature requests, "what are customers saying", voice of customer, or wants to understand user sentiment.