Customer Persona Builder logo

Customer Persona Builder

Community
travisjneuman
customer-persona-builder

Data-driven customer persona development combining market research, user behavior analysis, and segmentation frameworks. Use when creating buyer personas, ideal customer profiles (ICPs), or user archetypes.

Overview

Publishertravisjneuman
Repository.claude
Skill namecustomer-persona-builder
Stars
98
Forks
22
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by travisjneuman on GitHub. Read the source before you install it.

Installation

Install the Customer Persona Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/travisjneuman/.claude.git /tmp/.claude
mkdir -p .claude/skills
cp -r /tmp/.claude/skills/customer-persona-builder .claude/skills/customer-persona-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Customer Persona Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Customer Persona Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Customer Persona Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Customer Persona Builder

Structured frameworks for creating data-driven customer personas, ideal customer profiles, and user archetypes.

Persona vs ICP Distinction

When to Use Which

IDEAL CUSTOMER PROFILE (ICP):
- Company-level / account-level description
- Used by: Sales, marketing (targeting), product (roadmap)
- Answers: "What companies should we sell to?"
- Firmographic: industry, size, revenue, tech stack

BUYER PERSONA:
- Individual-level description
- Used by: Sales (conversations), marketing (messaging), content
- Answers: "Who are the people making buying decisions?"
- Behavioral: goals, pain points, decision process

USER PERSONA:
- End-user description (may differ from buyer)
- Used by: Product, design, engineering
- Answers: "Who uses the product daily?"
- Task-based: workflows, jobs-to-be-done, frustrations

RELATIONSHIP:
ICP (company) contains multiple Buyer Personas (people)
who may differ from User Personas (daily users).

Ideal Customer Profile Template

ICP Framework

IDEAL CUSTOMER PROFILE:

FIRMOGRAPHICS:
- Industry:        [specific verticals]
- Company Size:    [employee range]
- Annual Revenue:  [revenue range]
- Geography:       [regions/countries]
- Growth Stage:    [startup/growth/enterprise]

TECHNOGRAPHICS:
- Current Stack:   [tools they use today]
- Infrastructure:  [cloud, on-prem, hybrid]
- Maturity:        [early adopter, mainstream, laggard]

BUSINESS CHARACTERISTICS:
- Pain Intensity:  [how acute is the problem we solve]
- Budget Authority:[does this level have budget]
- Buying Process:  [simple, committee, procurement]
- Contract Value:  [expected ACV range]

QUALIFYING SIGNALS:
- Positive: [hiring for X role, using Y tool, in Z market]
- Negative: [too small, wrong industry, already solved]

DISQUALIFYING CRITERIA:
- [specific reasons to exclude]

ICP Scoring Matrix

AttributeIdeal (5)Good (3)Poor (1)Weight
Industry[exact verticals][adjacent verticals][unrelated]20%
Company Size[sweet spot range][workable range][too small/large]15%
Pain IntensityActive seeking solutionAware of problemUnaware25%
BudgetDedicated budget existsCan find budgetNo budget20%
Tech FitPerfect stack matchPartial overlapIncompatible10%
ChampionIdentified internal advocatePotential championNo access10%
SCORING THRESHOLDS:
  4.0-5.0: Tier 1 — pursue aggressively
  3.0-3.9: Tier 2 — pursue selectively
  2.0-2.9: Tier 3 — qualify carefully
  < 2.0:   Disqualify

Buyer Persona Template

Full Persona Document

BUYER PERSONA:

──────────────────────────────────────────────
NAME:   [Representative name, e.g., "Marketing Maria"]
ROLE:   [Title / function]
REPORTS TO: [Their boss's role]
──────────────────────────────────────────────

DEMOGRAPHICS:
- Age Range:      [25-35, 35-45, etc.]
- Education:      [Degree, field]
- Career Stage:   [IC, manager, director, VP, C-level]
- Income Range:   [if relevant to pricing]

PROFESSIONAL CONTEXT:
- Team Size:      [who they manage]
- Budget Authority: [Y/N, amount range]
- KPIs They Own:   [what they're measured on]
- Tools They Use:  [current stack]
- Reports They Read: [information sources]

GOALS (what they're trying to achieve):
1. [Primary business goal]
2. [Secondary business goal]
3. [Personal career goal]

PAIN POINTS (what frustrates them):
1. [Primary pain point]
   Impact: [time, money, reputation]
2. [Secondary pain point]
   Impact: [time, money, reputation]
3. [Tertiary pain point]
   Impact: [time, money, reputation]

BUYING BEHAVIOR:
- Trigger Event:     [what initiates their search]
- Research Process:  [where they look for solutions]
- Decision Criteria: [ranked priorities]
  1. [e.g., ease of use]
  2. [e.g., integration with existing tools]
  3. [e.g., price/value]
  4. [e.g., vendor reputation]
  5. [e.g., implementation speed]
- Decision Timeline: [typical buying cycle length]
- Influencers:       [who else is involved]

OBJECTIONS:
1. [Common objection]
   Root Cause: [underlying concern]
2. [Common objection]
   Root Cause: [underlying concern]

MESSAGING THAT RESONATES:
- Value Prop:   "[specific statement that speaks to their goals]"
- Proof Point:  "[customer story or metric that builds credibility]"
- CTA:          "[appropriate next step for this persona]"

QUOTE:
"[A representative statement capturing their perspective,
  drawn from interviews or synthesized from research]"

Data Sources for Persona Building

Primary Research Methods

MethodBest ForSample SizeTime Investment
Customer interviewsDeep qualitative insights10-20 per persona2-4 weeks
Sales team interviewsPatterns from prospect conversations5-10 reps1 week
Customer success interviewsPost-purchase behavior, retention drivers5-10 CSMs1 week
Win/loss analysisDecision criteria and competitive dynamics15-30 deals2-3 weeks
SurveysQuantitative validation of qualitative findings100-500+2-3 weeks
On-site observationReal workflow and context understanding5-10 visits4-6 weeks

Secondary Research Methods

SourceData TypeActionability
CRM dataFirmographics, deal history, conversion ratesHigh
Product analyticsFeature usage, engagement patterns, drop-offHigh
Support ticketsPain points, confusion areas, feature requestsHigh
G2/Capterra reviewsBuying criteria, competitor sentimentMedium
Social mediaInterests, content consumption, influenceMedium
Census / industry dataMarket sizing, demographic baselinesLow-Medium
Job postingsRole responsibilities, tools, prioritiesMedium

Interview Question Bank

DISCOVERY QUESTIONS (for persona interviews):

ROLE & CONTEXT:
- "Walk me through a typical day in your role."
- "What are the top 3 things you're measured on?"
- "Who do you report to, and what do they care about most?"
- "What tools do you use every day?"

GOALS:
- "What are you trying to accomplish this quarter/year?"
- "What does success look like in your role?"
- "If you could wave a magic wand, what would change?"

PAIN POINTS:
- "What's the most frustrating part of [process we address]?"
- "How do you currently solve [problem we address]?"
- "What have you tried that didn't work?"
- "How much time/money does this problem cost you?"

BUYING BEHAVIOR:
- "When you last evaluated a new tool, how did you start?"
- "Who else was involved in that decision?"
- "What was the single most important factor in your decision?"
- "What almost stopped you from buying?"

INFORMATION SOURCES:
- "Where do you go to learn about new tools or approaches?"
- "Which blogs, podcasts, or communities do you follow?"
- "Whose opinion do you trust most when making decisions?"

Jobs-to-Be-Done Integration

JTBD Framework for Personas

JOB STATEMENT FORMAT:
When [situation/trigger],
I want to [motivation/goal],
so I can [expected outcome].

EXAMPLE:
When I'm preparing the monthly board report,
I want to pull real-time metrics from all our tools,
so I can present accurate data without 4 hours of manual work.

JOB MAP:
1. DEFINE    — What triggers the need?
2. LOCATE    — Where do they search for solutions?
3. PREPARE   — What setup is required?
4. CONFIRM   — How do they validate it works?
5. EXECUTE   — What does actual usage look like?
6. MONITOR   — How do they track ongoing results?
7. MODIFY    — What adjustments happen over time?
8. CONCLUDE  — What does completion look like?

Outcome-Driven Persona Layer

FOR EACH PERSONA, MAP:

FUNCTIONAL JOBS:
- [Core task they need to accomplish]
- [Supporting tasks around the core]

EMOTIONAL JOBS:
- [How they want to feel]
- [How they want to be perceived]

SOCIAL JOBS:
- [How they want others to see them]
- [Status or recognition they seek]

RELATED JOBS:
- [Adjacent tasks that affect their success]
- [Upstream/downstream dependencies]

Segmentation Approaches

Segmentation Decision Matrix

ApproachData NeededComplexityActionability
DemographicCRM / survey dataLowMedium
FirmographicCompany dataLowHigh (for B2B)
BehavioralProduct analytics, CRMMediumHigh
Needs-basedInterviews, surveysMedium-HighVery High
Value-basedRevenue, CLV dataMediumHigh
PsychographicSurvey, social dataHighMedium

Behavioral Segmentation Template

BEHAVIORAL SEGMENTS:

POWER USERS:
- Usage: Daily, multiple features
- Engagement: High (>X sessions/week)
- Value: High CLV, likely to expand
- Strategy: Upsell, advocacy program

REGULAR USERS:
- Usage: Weekly, core features
- Engagement: Moderate
- Value: Stable, predictable revenue
- Strategy: Feature education, expansion

AT-RISK USERS:
- Usage: Declining, sporadic
- Engagement: Low (dropping)
- Value: At risk of churn
- Strategy: Re-engagement, CSM outreach

NEW USERS:
- Usage: Onboarding phase
- Engagement: Variable
- Value: Unknown (measuring)
- Strategy: Guided onboarding, quick wins

Validation and Iteration

Persona Validation Checklist

Validation StepMethodStatus
Based on real data (not assumptions)Cite sources for each attribute[ ]
Validated with sales teamSales reps recognize and agree[ ]
Validated with CS teamMatches real customer behavior[ ]
Quantitatively sizedKnow how many of each persona exist[ ]
DifferentiatedEach persona triggers different actions[ ]
ActionableMarketing can write copy for each[ ]
PrioritizedClear tier 1 / tier 2 / tier 3 personas[ ]
Reviewed with productProduct roadmap aligns to persona needs[ ]

Persona Anti-Patterns

COMMON PERSONA MISTAKES:

1. OPINION-BASED PERSONAS
   Problem: Built on internal assumptions, not data
   Fix: Ground every attribute in interview/data evidence

2. TOO MANY PERSONAS
   Problem: 8+ personas dilute focus and confuse teams
   Fix: 3-5 primary personas maximum; merge similar ones

3. DEMOGRAPHIC-ONLY PERSONAS
   Problem: "Female, 35-45, suburban" tells you nothing useful
   Fix: Focus on goals, pain points, and buying behavior

4. STATIC PERSONAS
   Problem: Created once and never updated
   Fix: Quarterly review cadence with new data

5. PERSONAS WITHOUT PRIORITY
   Problem: All personas treated equally
   Fix: Rank by revenue potential and market size

6. PERSONA-MESSAGE DISCONNECT
   Problem: Personas exist but messaging ignores them
   Fix: Each persona gets specific value props and content

Iteration Cadence

QUARTERLY REVIEW:
- Validate against latest win/loss data
- Check product analytics for behavior shifts
- Interview 3-5 recent customers
- Update pain points and priorities
- Refresh proof points and quotes

ANNUAL REBUILD:
- Full primary research cycle
- Re-validate ICP and persona segments
- Check market shifts and new competitors
- Align with updated company strategy
- Present updated personas to full org

See Also

Frequently asked questions

What does the Customer Persona Builder AI skill do?

Data-driven customer persona development combining market research, user behavior analysis, and segmentation frameworks. Use when creating buyer personas, ideal customer profiles (ICPs), or user archetypes.

Why use Customer Persona Builder on TypingMind?

Because you install it once and use it with any model. Customer Persona Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Customer Persona Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/travisjneuman/.claude/tree/master/skills/customer-persona-builder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Customer Persona Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Customer Persona Builder?

As many as you like. As long as a model supports skills, you can use Customer Persona Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Customer Persona Builder AI skill free?

Yes. It is published on GitHub by travisjneuman under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇