← Back to Skills Marketplace
okaris

Customer Persona

by Ömer Karışman · GitHub ↗ · v0.1.5
cross-platform ⚠ suspicious
942
Downloads
0
Stars
7
Active Installs
2
Versions
Install in OpenClaw
/install customer-persona
Description
Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and...
README (SKILL.md)

Customer Persona

Create data-backed customer personas with research and visuals via inference.sh CLI.

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

# Research your target market
infsh app run tavily/search-assistant --input '{
  "query": "SaaS product manager demographics pain points 2024 survey"
}'

# Generate a persona avatar
infsh app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot photograph of a 35-year-old woman, product manager, friendly confident expression, modern office background, natural lighting, business casual attire, realistic portrait",
  "width": 1024,
  "height": 1024
}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Persona Template

┌──────────────────────────────────────────────────────┐
│  [Avatar Photo]                                      │
│                                                      │
│  SARAH CHEN, 34                                      │
│  Product Manager at a Series B SaaS startup          │
│                                                      │
│  "I spend more time making reports than making       │
│   decisions."                                        │
│                                                      │
├──────────────────────────────────────────────────────┤
│  DEMOGRAPHICS          │  PSYCHOGRAPHICS             │
│  Age: 30-38            │  Values: efficiency, data   │
│  Income: $120-160K     │  Personality: analytical,   │
│  Education: BS/MBA     │    organized, collaborative │
│  Location: Urban US    │  Interests: productivity,   │
│  Role: Product/PM      │    leadership, AI tools     │
├──────────────────────────────────────────────────────┤
│  GOALS                 │  PAIN POINTS                │
│  • Ship features       │  • Too many meetings        │
│  faster                │  • Manual reporting (15     │
│  • Data-driven         │    hrs/week)                │
│  decisions             │  • Stakeholder alignment    │
│  • Team alignment      │    is slow                  │
│  • Career growth to    │  • Tool sprawl (8+ apps)   │
│    Director            │  • No single source of      │
│                        │    truth                    │
├──────────────────────────────────────────────────────┤
│  CHANNELS              │  BUYING TRIGGERS            │
│  • LinkedIn (daily)    │  • Peer recommendation      │
│  • Product Hunt        │  • Free trial experience    │
│  • Podcasts (commute)  │  • Integration with Jira    │
│  • Lenny's Newsletter  │  • Team plan pricing        │
│  • Twitter/X           │  • ROI calculator           │
└──────────────────────────────────────────────────────┘

Building a Persona Step-by-Step

Step 1: Research

Start with data, not assumptions.

# Market demographics
infsh app run tavily/search-assistant --input '{
  "query": "product manager salary demographics 2024 survey report"
}'

# Pain points and challenges
infsh app run exa/search --input '{
  "query": "biggest challenges facing product managers SaaS companies"
}'

# Tool usage patterns
infsh app run tavily/search-assistant --input '{
  "query": "most popular tools product managers use 2024 survey"
}'

# Content consumption habits
infsh app run exa/answer --input '{
  "question": "Where do product managers get their industry news and professional development?"
}'

Step 2: Demographics

Use ranges, not exact values. Personas represent a segment, not one person.

Field Format Example
Age range X-Y 30-38
Income range $X-$Y $120,000-$160,000
Education Common degrees BS Computer Science, MBA
Location Region/type Urban US, major tech hubs
Job title Role level Senior PM, Product Lead
Company size Range 50-500 employees
Industry Sector B2B SaaS

Step 3: Psychographics

What they think, value, and believe.

Category Questions to Answer
Values What matters most to them professionally?
Attitudes How do they feel about their industry's direction?
Motivations What drives them at work?
Personality Analytical vs intuitive? Leader vs collaborator?
Interests What do they read/watch/listen to professionally?
Lifestyle Work-life balance preference? Remote/hybrid/office?

Step 4: Goals

What they're trying to achieve (both professional and personal).

Professional:
- Ship features faster with fewer meetings
- Make data-driven decisions (not gut feelings)
- Get promoted to Director of Product within 2 years
- Build a more autonomous product team

Personal:
- Leave work by 6pm more often
- Be seen as a strategic leader, not a ticket manager
- Stay current with industry trends without information overload

Step 5: Pain Points

Quantify whenever possible. Vague pain = vague persona.

❌ "Has trouble with reporting"
✅ "Spends 15 hours per week creating manual reports for 4 different stakeholders"

❌ "Too many tools"
✅ "Uses 8 different tools daily (Jira, Slack, Notion, Figma, Analytics, Sheets, Docs, Email) with no unified view"

❌ "Meetings are a problem"
✅ "Averages 6 hours of meetings per day, leaving only 2 hours for deep work"

Step 6: Jobs-to-be-Done (JTBD)

Three types of jobs:

Job Type Description Example
Functional The task they need to accomplish "Prioritize the product backlog based on customer impact data"
Emotional How they want to feel "Feel confident presenting to the exec team"
Social How they want to be perceived "Be seen as the person who makes data-driven decisions"

Step 7: Buying Process

Stage Behavior
Awareness Reads blog posts, sees peer recommendations on LinkedIn
Consideration Compares 3-4 tools, reads G2/Capterra reviews, asks in Slack communities
Decision Requests demo, needs IT/security approval, evaluates team pricing
Influencers Engineering lead, VP of Product, CFO (for budget)
Objections "Will my team actually adopt it?", "Does it integrate with Jira?"
Trigger event New quarter with aggressive goals, new VP demanding better reporting

Step 8: Generate Avatar

# Match demographics: age, gender, ethnicity, professional context
infsh app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot photograph of a 34-year-old Asian American woman, product manager, warm confident smile, modern tech office background, natural lighting, wearing smart casual blouse, realistic portrait photography, sharp focus",
  "width": 1024,
  "height": 1024
}'

Avatar tips:

  • Match the age range, ethnicity representation, and professional context
  • Use "professional headshot photograph" for realistic results
  • Friendly, approachable expression (not stock-photo-stiff)
  • Background suggests their work environment
  • Business casual or industry-appropriate attire

The Anti-Persona

Equally important: who is NOT your customer.

ANTI-PERSONA: "Enterprise Earl"
- CTO at a 5,000+ person enterprise
- Needs SOC 2, HIPAA, on-premise deployment
- 18-month procurement cycles
- Wants white-glove onboarding and dedicated CSM
- WHY NOT: Our product is self-serve SaaS for SMB/mid-market.
  Enterprise needs would require 2+ years of product investment.

Anti-personas prevent wasted effort on customers you can't serve.

Multiple Personas

Most products have 2-4 personas. More than 4 = too many to serve well.

Priority Persona Role
Primary The main user and buyer Who you optimize for
Secondary Influences the buying decision Who you need to convince
Tertiary Uses the product occasionally Who you support, not target

Validation

Personas based on assumptions are fiction. Validate with:

Method What You Learn
Customer interviews (5-10) Real language, real pain points
Support ticket analysis Actual problems, not assumed ones
Analytics data Actual behavior, not reported behavior
Survey (50+ responses) Quantified patterns across segments
Sales call recordings Objections, buying triggers, language

Common Mistakes

Mistake Problem Fix
Based on assumptions Fiction, not research Start with data
Too many personas (6+) Can't serve everyone well Max 3-4
Vague pain points Not actionable Quantify everything
Demographics only Misses motivations and behavior Add psychographics, JTBD
Never updated Becomes outdated Review quarterly
No anti-persona Wasted effort on wrong customers Define who you're NOT for
Single persona for all Different users have different needs Primary/secondary/tertiary

Related Skills

npx skills add inference-sh/skills@web-search
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: infsh app list

Usage Guidance
This skill appears to do what it claims (research + avatar generation), but exercise caution before following its install instructions. Key points: - The SKILL.md recommends running a remote installer via 'curl | sh' from cli.inference.sh and downloading binaries from dist.inference.sh. 'curl | sh' runs code fetched from the network with no local preview — only proceed if you manually inspect the installer script and verify the checksums yourself. - The manifest lists no required credentials, but the instructions call 'infsh login' and invoke external services (search assistants, image models). Expect to create or provide service tokens; review the CLI's privacy/security docs to understand what data the service logs or retains. - Image generation prompts and market queries will be sent to external providers. Avoid sending sensitive or proprietary information in prompts. - If you want lower risk: install the CLI from a well-known package/release (or from a GitHub release you can verify), or run the recommended commands in an isolated environment (sandbox or container) so the downloaded binary cannot access your wider system or secrets. If you want me to: I can (1) fetch and show the installer script and checksums URL so you can inspect them, (2) point out what permissions 'infsh login' appears to request, or (3) suggest a safer workflow that uses only well-known, auditable tools. Confidence in this assessment is medium because the skill is instruction-only and the external CLI is the main unknown factor.
Capability Analysis
Type: OpenClaw Skill Name: customer-persona Version: 0.1.5 The skill bundle is designed for creating customer personas using the `inference.sh` CLI tool. The `SKILL.md` provides clear, step-by-step instructions for the AI agent, including commands for web search and AI image generation, all executed via `infsh`. The `allowed-tools` permission `Bash(infsh *)` is appropriately scoped for the skill's functionality. While the `curl -fsSL https://cli.inference.sh | sh` installation method is a common practice for CLI tools, it represents a supply chain risk if the remote server were compromised. However, this is an installation instruction for a dependency, not an act of malice by the skill itself, and the skill provides transparency notes about the script's function. There is no evidence of prompt injection, data exfiltration, persistence, or other malicious intent within the provided files.
Capability Assessment
Purpose & Capability
The name/description (customer persona creation + avatar generation) matches the runtime instructions: the SKILL.md consistently instructs use of the inference.sh CLI to run market-research apps and an image model. No unrelated services, binaries, or credentials are requested in the manifest.
Instruction Scope
Instructions stick to persona research steps (market queries, pain points, psychographics) and image avatar generation. However, the document tells the user/agent to run 'curl -fsSL https://cli.inference.sh | sh' and to run 'infsh login' — the latter implies creating/storing service credentials/tokens even though the skill manifest declares no required credentials. The SKILL.md does not instruct the agent to read local files or other unrelated system state.
Install Mechanism
No install spec in the manifest, but SKILL.md recommends piping a script from https://cli.inference.sh into sh. The text claims the installer downloads binaries from dist.inference.sh and verifies SHA-256 checksums via a checksums.txt URL. dist.inference.sh/cli is not a widely-known release host like GitHub Releases; 'curl | sh' is a high-risk pattern unless you verify checksums and inspect the script. The skill does attempt to document verification, but the installer and distribution are external and not automatically validated by the platform.
Credentials
The manifest declares no required env vars or credentials, which superficially limits risk. In practice the instructions require 'infsh login' and will call external services (search assistants, image models) that need accounts or API tokens; these credentials are not declared in the skill metadata. That mismatch means the agent will request or create tokens at runtime, and those tokens could allow the external CLI to access or transmit your prompts/data.
Persistence & Privilege
always is false and the skill is user-invocable only. The skill does not request permanent presence or ask to modify other skill/system configs. The primary risk here is remote execution and credential storage by the external CLI, not elevated platform privileges from the skill manifest.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install customer-persona
  3. After installation, invoke the skill by name or use /customer-persona
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.5
- Added comprehensive step-by-step guide to creating research-backed customer personas, including templates, research tips, and practical examples. - Expanded documentation to cover demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. - Included sample CLI commands for integrating market research and AI-generated avatar creation using inference.sh. - Clarified key use cases: marketing strategy, product development, UX research, sales enablement, and content strategy.
v0.1.0
Initial release of customer-persona skill for research-based persona creation: - Create detailed, data-backed customer personas using market research and avatar generation. - Covers demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. - Provides step-by-step guides and templates for persona development. - Integrates with inference.sh CLI for research tools and AI avatar creation. - Supports use cases in marketing, product development, UX research, sales, and content strategy.
Metadata
Slug customer-persona
Version 0.1.5
License
All-time Installs 7
Active Installs 7
Total Versions 2
Frequently Asked Questions

What is Customer Persona?

Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and... It is an AI Agent Skill for Claude Code / OpenClaw, with 942 downloads so far.

How do I install Customer Persona?

Run "/install customer-persona" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Customer Persona free?

Yes, Customer Persona is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Customer Persona support?

Customer Persona is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Customer Persona?

It is built and maintained by Ömer Karışman (@okaris); the current version is v0.1.5.

💬 Comments