Social Audience Personas

Audience personas

by Ootto-AI · MIT license · ★ 139 on GitHub

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

---
name: audience-personas
description: Build evidence-led social audience personas from customer interviews, comments, reviews, or CRM notes.
user-invokable: true
argument-hint: "[paste customer evidence]"
license: MIT
metadata: { author: Ootto, version: "1.0.0", category: marketing }
---
# 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

Overview

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.

Manual install (npx, ZIP)

Claude Codenpx skills add Ootto-AI/claude-content-skills --skill audience-personas -g -a claude-code

Claude Code (degit)npx degit Ootto-AI/claude-content-skills/skills/audience-personas#main ~/.claude/skills/audience-personas

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.1 KB

Read SKILL.md here

Ootto-AI/main1 file shown

SKILL.md2.1 KB

Browse every file on GitHub↗

SKILL.md

Show the full text47 lines

audience-personas/SKILL.md47 lines · 2.1 KB

PreviewCode

Outline

RawView on GitHub

Audience Personas

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

Symptom	Cause	Fix
Generic personas	source has no concrete language	ask for verbatim comments or interviews
False certainty	inference appears as fact	label it as a hypothesis
Too many segments	minor differences treated as groups	merge 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.

1	---
2	name: audience-personas
3	description: Build evidence-led social audience personas from customer interviews, comments, reviews, or CRM notes.
4	user-invokable: true
5	argument-hint: "[paste customer evidence]"
6	license: MIT
7	metadata: { author: Ootto, version: "1.0.0", category: marketing }
8	---
9	# Audience Personas
10
11	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.
12
13	## 1. Establish the evidence
14
15	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.
16
17	## 2. Group observable patterns
18
19	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.
20
21	## 3. Produce a usable segment
22
23	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.
24
25	## 4. Hold claims for review
26
27	Flag any demographic statement, outcome claim, or customer quote that needs approval before public use.
28
29	## Hard rules
30
31	- Do not infer demographics, income, identity, or intent not present in the source.
32	- Do not turn one loud comment into a market-wide claim.
33	- Keep observed language distinct from suggested copy.
34	- If evidence is thin, ask for more comments, reviews, or interviews.
35
36	## Failure modes
37
38	\| Symptom \| Cause \| Fix \|
39	\|---\|---\|---\|
40	\| Generic personas \| source has no concrete language \| ask for verbatim comments or interviews \|
41	\| False certainty \| inference appears as fact \| label it as a hypothesis \|
42	\| Too many segments \| minor differences treated as groups \| merge around the shared job-to-be-done \|
43
44	## Where it sits
45
46	`social-listening` gathers recurring conversation → audience-personas groups it → `positioning-audit` turns it into a message.
47