persona-docs

Create persona documentation for a product or codebase. Use when asked to create persona docs, document target users, define user journeys, document onboarding flows, or when starting a new product and needing to define its audience. Persona docs should be the first documentation created for any product.

7 stars

Best use case

persona-docs is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Create persona documentation for a product or codebase. Use when asked to create persona docs, document target users, define user journeys, document onboarding flows, or when starting a new product and needing to define its audience. Persona docs should be the first documentation created for any product.

Teams using persona-docs should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/persona-docs/SKILL.md --create-dirs "https://raw.githubusercontent.com/wpank/ai/main/skills/writing/persona-docs/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/persona-docs/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How persona-docs Compares

Feature / Agentpersona-docsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create persona documentation for a product or codebase. Use when asked to create persona docs, document target users, define user journeys, document onboarding flows, or when starting a new product and needing to define its audience. Persona docs should be the first documentation created for any product.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Persona Docs

Create user-centered documentation that defines who a product is for and how they interact with it. Persona docs establish the foundation for product-driven development — every feature decision, design choice, and prioritization call flows from understanding your users.


## Installation

### OpenClaw / Moltbot / Clawbot

```bash
npx clawhub@latest install persona-docs
```


## When to Create

Persona docs should be the first thing fleshed out for any product. Even minimal documentation about who uses the product helps direct development and design decisions.

- **Project inception** — before writing code, define who you're building for
- **Pivoting to a new audience** — document the shift so the team aligns
- **Team lacks clarity on target users** — when people disagree on "who is this for?"
- **Before major feature planning** — validate that planned features serve actual users
- **New team member onboarding** — give them context on who they're building for

## Process

1. **Analyze the codebase** — look for existing documentation, README, landing pages, or marketing copy that hints at the target audience
2. **Ask clarifying questions** if the target user isn't clear:
   - "Who is the primary user of this product?"
   - "What problem does this solve for them?"
   - "How would they discover this product?"
   - "What's the first thing they'd do after finding it?"
3. **Start minimal** — a few sentences per section is better than nothing
4. **Read the template** — see `references/template.md` for the full structure
5. **Iterate** — revisit and expand as you learn more about actual users

## Core Components

### 1. Target User Profile

Who they are, their background, their context. Be specific enough to be useful.

**Good:** "Backend engineers at mid-size SaaS companies who debug production issues under time pressure, typically 3-8 years of experience, comfortable with command-line tools."

**Too vague:** "Developers."

Include:
- Role, job title, or archetype
- Technical level and relevant skills
- Industry or domain context
- When and where they'd use this product
- Team size and organizational context

### 2. User Needs and Pain Points

The problems this product solves. What frustrations or gaps exist in their current workflow?

Structure as:
- **Primary pain point** — the single biggest problem you solve
- **Secondary pain points** — additional problems you address
- **Current workarounds** — what they do today without your product
- **Why existing solutions fail** — what alternatives exist and why they're insufficient

### 3. Discovery Path

How they find the product. This informs marketing, positioning, and first-impression design.

- **Search** — what queries lead them here?
- **Referral** — word of mouth, colleague recommendation?
- **Content** — blog posts, tutorials, conference talks?
- **Marketplace** — app store, plugin directory, package registry?
- **The hook** — what makes them click "sign up" or "download"?

### 4. Onboarding Flow

The simplest possible path from "I found this" to "I'm getting value."

Define:
- **First encounter** — landing page, app store listing, GitHub README
- **Registration/Login** — minimum viable auth (email-only? OAuth? no account?)
- **Time to value** — how quickly can they experience the core benefit?
- **First success moment** — the specific action that makes them think "this is useful"
- **Friction points** — where do users drop off, and how do you minimize that?

Example flow:
> User lands on homepage → clicks "Try it" → pastes their data → sees result in <30 seconds → decides to create account

### 5. User Journey Map

Key touchpoints and interactions across the user lifecycle.

**New User (Day 1):**
- Discovers product via [channel]
- Takes [first action]
- Achieves [first success]

**Returning User (Week 1):**
- Key repeated action they perform
- Features they explore
- Integrations or customizations they set up

**Power User (Month 1+):**
- Advanced features they rely on
- Workflows they've established
- How they'd describe the product to others

### 6. Feature Touchpoints

Map where users encounter key features in their journey:

| Feature | When Encountered | User Need at That Moment |
|---------|------------------|--------------------------|
| [Feature 1] | [Journey stage] | [What they're trying to do] |
| [Feature 2] | [Journey stage] | [What they're trying to do] |

## Multi-Persona Products

If your product serves multiple distinct user types:

1. **Identify the primary persona first** — who must you serve to survive?
2. **Document secondary personas separately** — one file per persona
3. **Note conflicts** — where persona needs clash, document the tradeoff
4. **Prioritize ruthlessly** — you can't optimize for everyone simultaneously

## Output Location

Place persona docs at:
- `docs/PERSONA.md` — single file for simple products
- `docs/personas/` — directory for multiple personas

Keep it in the repo so it evolves with the product.

## Quality Criteria

A good persona doc should:

- Be **specific** enough that two team members would build the same feature from it
- Include **evidence** — data, quotes, or observations, not just assumptions
- Be **actionable** — reading it should change how you build
- Be **maintained** — outdated personas are worse than none
- Be **honest** — don't describe aspirational users; describe actual users

## NEVER Do

1. **NEVER skip personas for a new product** — building without knowing your user is guessing, and guessing is expensive
2. **NEVER describe users as demographics alone** — "25-34 male" tells you nothing about what they need; describe behaviors and goals
3. **NEVER create personas in isolation** — involve the team; one person's assumptions become the whole product's blind spots
4. **NEVER treat personas as permanent** — users change, markets shift; review personas quarterly
5. **NEVER create more than 3 personas initially** — if you try to serve everyone, you serve no one; start with your primary user
6. **NEVER write aspirational personas** — document who actually uses your product, not who you wish did

Related Skills

schema-markup

7
from wpank/ai

Add, fix, or optimize schema markup and structured data. Use when the user mentions schema markup, structured data, JSON-LD, rich snippets, schema.org, FAQ schema, product schema, review schema, or breadcrumb schema.

prompt-engineering

7
from wpank/ai

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

professional-communication

7
from wpank/ai

Write effective professional messages for software teams. Use when drafting emails, Slack/Teams messages, meeting agendas, status updates, or translating technical concepts for non-technical audiences. Triggers on email, slack, teams, message, meeting agenda, status update, stakeholder communication, escalation, jargon translation.

mermaid-diagrams

7
from wpank/ai

Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, and other diagram types. Triggers include requests to diagram, visualize, model, map out, or show the flow of a system.

game-changing-features

7
from wpank/ai

Find 10x product opportunities and high-leverage improvements. Use when the user wants strategic product thinking, mentions 10x, wants to find high-impact features, or asks what would make a product dramatically more valuable.

clear-writing

7
from wpank/ai

Write clear, concise prose for humans — documentation, READMEs, API docs, commit messages, error messages, UI text, reports, and explanations. Combines Strunk's rules for clearer prose with technical documentation patterns, structure templates, and review checklists.

brainstorming

7
from wpank/ai

Explore ideas before implementation through collaborative dialogue. Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Turns ideas into fully formed designs and specs through structured conversation.

Article Illustrator

7
from wpank/ai

When the user wants to add illustrations to an article or blog post. Triggers on: "illustrate article", "add images to article", "generate illustrations", "article images", or requests to visually enhance written content. Analyzes article structure, identifies positions for visual aids, and generates illustrations using a Type x Style two-dimension approach.

subagent-driven-development

7
from wpank/ai

Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code quality). Use when you have an implementation plan with mostly independent tasks and want high-quality, fast iteration within a single session.

skill-judge

7
from wpank/ai

Evaluate Agent Skill quality against official specifications. Use when reviewing SKILL.md files, auditing skill packages, improving skill design, or checking if a skill follows best practices. Provides 8-dimension scoring (120 points) with actionable improvements. Triggers on review skill, evaluate skill, audit skill, improve skill, skill quality, SKILL.md review.

skill-creator

7
from wpank/ai

WHAT: Guide for creating effective AI agent skills - modular packages that extend Claude's capabilities with specialized knowledge, workflows, and tools. WHEN: User wants to create, write, author, or update a skill. User asks about skill structure, SKILL.md format, or how to package domain knowledge for AI agents. KEYWORDS: "create a skill", "make a skill", "new skill", "skill template", "SKILL.md", "agent skill", "write a skill", "skill structure", "package a skill"

session-handoff

7
from wpank/ai

WHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves long-running agent context exhaustion problem. WHEN: (1) User requests handoff/memory/context save, (2) Context window approaches capacity, (3) Major task milestone completed, (4) Work session ending, (5) Resuming work with existing handoff. KEYWORDS: "save state", "create handoff", "context is full", "I need to pause", "resume from", "continue where we left off", "load handoff", "save progress", "session transfer", "hand off"