agentleFS
Ootto-AIOotto-AI/claude-content-skills/skills/audience-personas/SKILL.md

audience-personas

Skill417 starsChanged 3 months agoMITView on GitHub

Build evidence-led social audience personas from customer interviews, comments, reviews, or CRM notes.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for the source, date range, decision owner, offer, and desired audience action.

    line 15
  2. Distinctive:

    Do not infer demographics, income, identity, or intent not present in the source.

    line 31
  3. Distinctive:

    Do not turn one loud comment into a market-wide claim.

    line 32
  4. Distinctive:

    Keep observed language distinct from suggested copy.

    line 33
  5. Distinctive:

    If evidence is thin, ask for more comments, reviews, or interviews.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Audience Personas

Turn supplied customer evidence into grounded audience segments. Use it when a marketer has interviews, comments, reviews, or CRM notes and needs to decide who a message is for. It is not for inventing demographics, market size, or personas from intuition.

1. Establish the evidence

Ask for the source, date range, decision owner, offer, and desired audience action. Keep direct quotes separate from summaries and name material that is missing.

2. Group observable patterns

Cluster the evidence by job-to-be-done, desired outcome, objection, exact language, and trigger. Cite the source for each cluster. Do not manufacture a segment just to reach a round number.

3. Produce a usable segment

For each evidence-backed segment, return its job, language, objections, useful message angles, and the question it is already asking. Label confidence and unresolved questions.

4. Hold claims for review

Flag any demographic statement, outcome claim, or customer quote that needs approval before public use.

Hard rules

  • Do not infer demographics, income, identity, or intent not present in the source.
  • Do not turn one loud comment into a market-wide claim.
  • Keep observed language distinct from suggested copy.
  • If evidence is thin, ask for more comments, reviews, or interviews.

Failure modes

SymptomCauseFix
Generic personassource has no concrete languageask for verbatim comments or interviews
False certaintyinference appears as factlabel it as a hypothesis
Too many segmentsminor differences treated as groupsmerge around the shared job-to-be-done

Where it sits

social-listening gathers recurring conversation → audience-personas groups it → positioning-audit turns it into a message.

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.