analyze-feedback — Claude Code command: what it does, how to install
analyze-feedback processes reviews, NPS surveys, and support tickets into structured markdown reports with sentiment metrics and recurring themes.
MIT ★ 28,211 updated 2026-10-16
/plugin marketplace add phuryn/pm-skills
/plugin install pm-market-research@pm-skillsWhat analyze-feedback does
The command ingests feedback from CSV or Excel files, support exports, or pasted text. It asks about user segments and analysis goals before running. Next, it scores sentiment per record, clusters repetitive issues into themes, and calculates mention frequencies.
The output report delivers high-level sentiment distribution, a theme breakdown with representative quotes, and segment comparisons. For NPS datasets, the command isolates Detractors, Passives, and Promoters.
Sentiment classification remains approximate and struggles with sarcasm or mixed phrasing. If you supply tabular input, the command saves an enriched CSV containing sentiment scores alongside the markdown summary.
What it helps with
- cluster user reviews and support tickets into recurring themes
- measure positive, neutral, and negative sentiment distribution
- break down NPS survey responses across user segments
- export enriched CSV datasets with individual sentiment scores
Example prompts for the agent
- /analyze-feedback nps_responses_q3.csv
- /analyze-feedback review text pasted from app store
- /analyze-feedback support_tickets_export.csv
How to install analyze-feedback
1Plugin marketplace
/plugin marketplace add phuryn/pm-skills/plugin install pm-market-research@pm-skills2Manually: put the files in place
.claude/commands/analyze-feedback.mdCall it with /analyze-feedback. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/analyze-feedback.mdCall it with /prompts:analyze-feedback. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/analyze-feedback.prompt.mdManually: put the files in place
.gemini/commands/analyze-feedback.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about analyze-feedback
How do I install analyze-feedback in Claude Code?
Add the repository with /plugin marketplace add phuryn/pm-skills and install the package with /plugin install pm-market-research@pm-skills. You can also place the command file directly into .claude/commands/analyze-feedback.md.
What does the analyze-feedback command do?
It processes feedback records from text or spreadsheets into structured insights. It extracts key problem areas, measures sentiment, and outputs an action-oriented markdown report.
How does it handle NPS survey data?
The command separates responses into Detractors, Passives, and Promoters based on ratings from 0 to 10. It then analyzes themes for each cohort individually.
Source text
analyze-feedback.md · MIT
--- description: Analyze user feedback at scale — sentiment analysis, theme extraction, and segment-level insights argument-hint: "<feedback data as CSV, text, or file>" --- # /analyze-feedback -- User Feedback Analysis Process large volumes of user feedback (reviews, surveys, support tickets, NPS responses) into structured insights with sentiment analysis and segment-level patterns. ## Invocation ``` /analyze-feedback [upload a CSV of NPS responses] /analyze-feedback [paste app store reviews or survey responses] /analyze-feedback [upload support ticket export] ``` ## Workflow ### Step 1: Accept Feedback Data Accept in any format: - CSV/Excel with feedback text (and optional metadata: date, segment, rating) - Pasted text (reviews, survey responses, Slack messages) - Uploaded documents or exports from feedback tools Ask: - What kind of feedback is this? (NPS, reviews, support tickets, survey, etc.) - Any segments to analyze separately? (user tier, plan, geography) - What are you looking for? (general themes, specific issues, trends over time) ### Step 2: Analyze Apply the **sentiment-analysis** skill: - **Sentiment scoring**: Classify each piece of feedback (positive, neutral, negative) - **Theme extraction**: Identify recurring topics and cluster related feedback - **Frequency analysis**: Count how often each theme appears - **Segment analysis**: Break down sentiment and themes by user segment (if data available) - **Trend detection**: If dates are available, identify sentiment shifts over time ### Step 3: Generate Analysis Report ``` ## Feedback Analysis Report **Date**: [today] **Feedback analyzed**: [count] responses **Source**: [NPS survey / app reviews / support tickets / etc.] **Period**: [date range if available] ### Overall Sentiment - Positive: [X%] | Neutral: [Y%] | Negative: [Z%] - Average sentiment score: [X/10] - Trend: [improving / stable / declining] ### Top Themes | # | Theme | Mentions | Sentiment | Segments Most Affected | |---|-------|----------|-----------|----------------------| ### Theme Deep-Dive #### Theme 1: [Name] — [X] mentions, [sentiment] - **What users are saying**: [summary with representative quotes] - **Root cause**: [what's driving this feedback] - **Impact**: [how this affects retention, satisfaction, or revenue] - **Recommendation**: [what to do about it] [Repeat for top 5-8 themes] ### Segment Analysis | Segment | Volume | Avg Sentiment | Top Theme | Key Difference | |---------|--------|-------------|-----------|---------------| ### Notable Quotes > "[quote]" — [segment, sentiment] ### Trends Over Time [If date data available: chart-ready data showing sentiment shifts] ### Actionable Insights 1. [Insight + recommended action] 2. ... ### Gaps [What this feedback doesn't tell you — suggested follow-up research] ``` Save as markdown. If input was structured data (CSV), also save enriched data with sentiment scores as CSV. ### Step 4: Offer Next Steps - "Want me to **create user personas** from these feedback patterns?" - "Should I **triage the top themes as feature requests**?" - "Want me to **design an interview script** to go deeper on a specific theme?" ## Notes - Sentiment analysis is approximate — flag edge cases (sarcasm, mixed sentiment, non-English text) - Theme extraction should look for needs behind requests, not just surface-level topics - If sample sizes are small per segment, note limited confidence - For NPS data specifically, analyze Detractors (0-6), Passives (7-8), and Promoters (9-10) separately - Output enriched CSV when input is structured, so the user can use it in their own tools
© Paweł Huryn · MIT · phuryn/pm-skills