Skip to content
SkillModel-led566 tokens in use

user-personas

Turns survey, interview and usage research into three user personas with jobs to be done, pains, gains and one unexpected insight each.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-market-research/skills/user-personas
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-personas costs

49tokens idle
566tokens 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
  • Examples0/15
  • Output12/15
  • 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-personas guides the agent through building three distinct personas from research data you supply, such as CSV or Excel files, survey responses and interview transcripts. It reads the files directly, finds recurring goals, pains and behaviors, and groups users by shared motivations.

Each persona comes with demographics, a primary job to be done, three pains, three desired gains, an unexpected insight from the data and a product fit assessment. The skill tells the agent to ground every claim in the research, quote users where possible and flag gaps that need more research.

What You Get

  • Three distinct personas with name, age range, role and company size for B2B
  • A primary job to be done per persona, with context and frequency
  • Top three pains and top three desired gains for each persona
  • One unexpected, data-derived insight per persona and why it matters for decisions
  • A product fit assessment with friction points and unmet needs
  • A list of data gaps that need more research

Common Use Cases

  • Building personas from a survey export before a roadmap review
  • Turning a set of interview transcripts into profiles the whole team can use
  • Checking whether a product serves its different user types equally well
  • Preparing segment-specific messaging by starting from real motivations

What Makes It Unique

Personas here are built from jobs to be done and behavior patterns, with a required unexpected insight for each one and a product fit check. The instructions say to cite direct quotes where available, keep personas distinct and flag data gaps, which ties the output to the research files and keeps stereotypes out. It sits beside user-segmentation in the same plugin, which clusters users by behavior and needs and sizes each segment.

Under The Hood

The skill is a single SKILL.md of instructions with no scripts. When active, the agent reads whatever research files you attach (CSV, Excel, transcripts) using its own file tools and writes the personas into the chat. It does not fetch web pages, call APIs or run commands, and it tells the agent nothing about writing files. The product name you pass in is substituted into the prompt where it says $ARGUMENTS.

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