Skip to content
SkillModel-led764 tokens in use

user-segmentation

Groups feedback, tickets and usage data into at least three user segments by behavior and jobs to be done, with fit, churn risk and priority.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-market-research/skills/user-segmentation
claude plugin marketplace add phuryn/pm-skills claude plugin install pm-market-research@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing user-segmentation costs

49tokens idle
764tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure22/25
  • Examples3/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

user-segmentation guides the agent to read the user feedback you provide, such as interviews, support tickets, usage logs and surveys, and cluster users into at least three segments. The clusters rest on behavior, jobs to be done and unmet needs, with demographics as a supporting detail.

For every segment the agent writes an overview with estimated size, behavioral traits, jobs and motivations, needs and pain points, current product fit, a differentiated value proposition and a recommendation to invest, maintain or de-prioritize.

What You Get

  • At least three named segments with an estimated share of the user base
  • Behavioral profile per segment: usage depth, journey, sophistication and tool integrations
  • Jobs to be done, motivations and what success looks like for each segment
  • Unmet needs, workarounds and churn risk per segment
  • A tailored value proposition and messaging angle per segment
  • A prioritization verdict of invest, maintain or de-prioritize with strategic and effort reasoning

Common Use Cases

  • Segmenting a user base from a pile of support tickets and survey answers
  • Deciding which user group to serve first on the roadmap
  • Finding underserved groups that are quiet in the feedback data
  • Giving marketing a segment-by-segment message set

What Makes It Unique

The skill treats behavior and jobs to be done as the basis of a segment and adds a prioritization step that ends in an invest, maintain or de-prioritize call. It also asks the agent to flag segments that may be underrepresented in the feedback and to validate emerging segments against usage data when it exists. The sibling user-personas skill produces three narrative personas, while this one produces sized segments with a strategic recommendation each.

Under The Hood

A single SKILL.md of instructions with no scripts. The agent reads the feedback files you attach with its own file tools and writes the segmentation in the conversation. The skill does not tell the agent to fetch web pages, call APIs, run commands or write files. The product name you pass is substituted for $ARGUMENTS in the prompt.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers