user-segmentation — Claude Code skill: build user segments
Turns reviews, interviews and usage logs into at least three behavior-based user segments. Useful when your user base looks like one big blob.
npx skills add phuryn/pm-skills --skill user-segmentation -a claude-codeWhat user-segmentation does
Feed it support tickets, interview transcripts, survey answers or product logs, and the skill sorts users into groups by what they actually do rather than who they are. Each group gets a profile: how those people use the product, the job they hired it for, and where they get stuck.
The workflow runs in stages. Data prep first, then behavioral patterns, needs and pain points, clustering, a check that segments do not overlap, and finally profiles backed by quotes from the source material. It closes with prioritization — which segment to invest in, which to keep as is, which to drop down the list.
The skill needs real input. Thin or one-sided feedback produces fuzzy segments, so check what you have before running it. The target product goes in through $ARGUMENTS.
What it helps with
- sort a pile of feedback into groups that mean something
- surface usage patterns demographics would hide
- spot needs that only part of your users have
- pick which segment to build for next
- check that your segments do not overlap
Example prompts for the agent
- Segment our task tracker users from the data in
feedback.csv - Read the interviews in
interviews/and split users by jobs-to-be-done - Analyze support tickets and profile three segments with pain points and quotes
How to install user-segmentation
1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill user-segmentation -a claude-code2Manually: put the files in place
~/.claude/skills/user-segmentation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/user-segmentation/
1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill user-segmentation -a codex2Manually: put the files in place
.agents/skills/user-segmentation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill user-segmentation -a cursor2Manually: put the files in place
.cursor/skills/user-segmentation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install phuryn/pm-skills user-segmentation2Manually: put the files in place
.github/skills/user-segmentation/SKILL.md1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill user-segmentation -a gemini-cli2Platform CLI
gemini skills install https://github.com/phuryn/pm-skills --path pm-market-research/skills/user-segmentationManually: put the files in place
.devin/skills/user-segmentation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill user-segmentation -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about user-segmentation
How do I install user-segmentation in Claude Code?
Run npx skills add phuryn/pm-skills --skill user-segmentation -a claude-code. The skill lands in ~/.claude/skills/user-segmentation/SKILL.md.
What does user-segmentation do?
It reads your user data and splits the base into at least three segments based on behavior and needs. Every segment comes with pain points, quotes and a priority call.
What input does it need?
Feedback, interviews, support tickets, usage logs or surveys. The skill reads them directly, so the more varied the material, the sharper the segment boundaries.
Source text
SKILL.md · MIT
--- name: user-segmentation description: "Segment users from feedback data based on behavior, JTBD, and needs. Identifies at least 3 distinct user segments. Use when segmenting a user base, analyzing diverse user feedback, or building a segmentation model." --- # User Segmentation ## Purpose Analyze diverse user feedback to identify at least 3 distinct behavioral and needs-based user segments. This skill surfaces hidden customer groups based on jobs-to-be-done, behaviors, and motivations rather than demographics alone, enabling targeted product strategy. ## Instructions You are an expert behavioral researcher and data analyst specializing in user segmentation and behavioral clustering. ### Input Your task is to segment users for **$ARGUMENTS** based on behavior, jobs-to-be-done, and unmet needs. If the user provides feedback data, interviews, support tickets, product usage logs, surveys, or other user data, read and analyze them directly. Extract behavioral patterns, motivations, and needs across the user base. ### Analysis Steps (Think Step by Step) 1. **Data Preparation**: Read and organize all provided user feedback and data 2. **Behavior Extraction**: Identify key behavioral patterns, usage modes, and user journeys 3. **Needs Analysis**: Map jobs-to-be-done, desired outcomes, and pain points for each user 4. **Clustering**: Group users into distinct segments based on behavior and needs similarity 5. **Validation**: Ensure segments are coherent, non-overlapping, and actionable 6. **Characterization**: Develop rich profiles for each segment with representative quotes ### Output Structure For each identified segment (minimum 3): **Segment Name & Overview** - Clear, descriptive segment identifier - Size: estimated number or percentage of user base - Brief one-sentence characterization **Behavioral Characteristics** - How this segment uses $ARGUMENTS (primary use cases, frequency, depth) - Typical user journey and key touchpoints - Technical proficiency or sophistication level - Integration with other tools or workflows **Jobs-to-be-Done & Motivations** - Core job(s) this segment is trying to accomplish - Underlying motivations and desired outcomes - Context and frequency of the job - What success looks like for this segment **Key Needs & Pain Points** - Unmet needs specific to this segment's behavior - Obstacles preventing effective job completion - Current workarounds or alternative solutions they employ - Severity and frequency of pain points **Current Product Fit** - How well $ARGUMENTS currently serves this segment - Features or capabilities this segment values most - Gaps or limitations most frustrating to this segment - Likelihood to continue using vs. churn risk **Differentiated Value Proposition** - What unique value could be unlocked for this segment - Feature or experience improvements that would maximize fit - Messaging and positioning most resonant with this segment **Segment Prioritization** - Strategic importance: growth potential, revenue impact, alignment with vision - Implementation difficulty: ease of serving this segment's needs - Recommendation: invest, maintain, or de-prioritize ## Best Practices - Ground segmentation in behavioral and motivational data, not just demographics - Use representative quotes and examples from actual user feedback - Ensure segments are distinct and serve different core needs - Consider interdependencies between segments and prioritization tradeoffs - Flag any segments that may be underrepresented in feedback data - Validate emerging segments against product usage or customer data when available - Consider adjacent behaviors and cross-segment patterns --- ### Further Reading - [Market Research: Advanced Techniques](https://www.productcompass.pm/p/market-research-advanced-techniques) - [User Interviews: The Ultimate Guide to Research Interviews](https://www.productcompass.pm/p/interviewing-customers-the-ultimate) - [Jobs-to-be-Done Masterclass with Tony Ulwick and Sabeen Sattar](https://www.productcompass.pm/p/jobs-to-be-done-masterclass-with) (video course)
© phuryn · MIT · phuryn/pm-skills