agentleFS
emotixcoemotixco/claude-skills-founder/skills/persona-gen/SKILL.md

persona-gen

Skill796 starsChanged 40 days agoMITView on GitHub

Create 3 distinct user personas with a day in the life, quotable pain points, current workarounds, buying behavior, and a priority matrix showing who to build for first. Use when a founder needs to decide or describe who their customer is.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md and follow it.

    line 14
  2. Distinctive:

    If the product is B2B, include at least one technical buyer and one economic buyer.

    line 73
  3. Distinctive:

    Keep each persona under 400 words.

    line 74

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are a user research lead. You write personas that read like people a founder could go and find, not demographic summaries.

Input: $ARGUMENTS

Before you start

Read ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md and follow it.

  • Reads: founder/facts.md, founder/product-brief.md, founder/user-interviews.md
  • Needs: the product and the market it serves
  • Saves to: founder/persona-gen.md

These personas are hypotheses until interviews confirm them. Say so in one line at the top of the output. If the founder's input includes real interview notes, build from those and quote them.

Instructions

Generate 3 distinct user personas. For each persona, provide:

Persona template

1. Identity

  • Name (realistic, not "Startup Steve")
  • Age, location, job title
  • Company size and stage (if B2B)
  • Annual income range

2. Day in the life 3-4 sentences describing a typical workday. Include the tools they use, meetings they attend, and frustrations they hit.

3. Goals and motivations

  • Primary goal (what they're trying to achieve this quarter)
  • Secondary goal (what they care about but can't prioritize)
  • Underlying motivation (why they care: career growth, financial pressure, personal mission)

4. Pain points Exactly 3 frustrations related to the problem space. Each should be:

  • Observable (you could see them doing this)
  • Quotable (written as something they'd say in an interview)
  • Actionable (the product could address it)

5. Current workarounds What tools or processes do they use today to solve this problem?

  • Tool name and what they use it for
  • What's broken about this workaround
  • How much time or money they lose on it per week (an estimate, with reasoning)

6. Decision-making

  • How do they discover new tools? (X, Product Hunt, peer recommendations, Google search)
  • What would make them try the product? (free trial, case study, a peer's recommendation)
  • What would make them pay? (a specific trigger or pain threshold)
  • Who else is involved in the buying decision? (for B2B)

7. Product fit score

  • Urgency (1-5): How badly do they need this solved right now?
  • Willingness to pay (1-5): How much budget and authority do they have?
  • Reachability (1-5): How easy is it to find and market to them?
  • Overall priority: Primary / Secondary / Tertiary

After all 3 personas

Persona priority matrix: a small table ranking the 3 personas by urgency, willingness to pay, and reachability. Recommend which persona to build for first and why.

Rules

  • Each persona must be clearly different, not three versions of the same person.
  • If the product is B2B, include at least one technical buyer and one economic buyer.
  • Keep each persona under 400 words. Total output under 1500 words.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.