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.