User Story Mapping logo

User Story Mapping

Organization
getcrew44
user-story-mapping

Create a user story map that lays out activities, steps, tasks, and release slices. Use when planning a workflow, backlog, or MVP around the user journey.

Overview

Publishergetcrew44
Repositorycrew44
Skill nameuser-story-mapping
Stars
358
Forks
12
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by getcrew44 on GitHub. Read the source before you install it.

Installation

Install the User Story Mapping 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.
    https://github.com/getcrew44/crew44/tree/main/daemon/internal/presets/defaultcrew/skills/product/user-story-mapping
  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/getcrew44/crew44.git /tmp/crew44
mkdir -p .claude/skills
cp -r /tmp/crew44/daemon/internal/presets/defaultcrew/skills/product/user-story-mapping .claude/skills/user-story-mapping
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable User Story Mapping 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 User Story Mapping 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 User Story Mapping 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.

Purpose

Visualize the user journey by creating a hierarchical map that breaks down high-level activities into steps and tasks, organized left-to-right as a narrative flow. Use this to build shared understanding across product, design, and engineering, prioritize features based on user workflows, and identify gaps or opportunities in the user experience.

This is not a backlog—it's a strategic artifact that shows how users accomplish their goals, which then informs what to build.

Key Concepts

The Jeff Patton Story Mapping Framework

Invented by Jeff Patton, story mapping organizes work into a 2D structure:

Horizontal axis (left-to-right): User journey over time

  • Backbone: High-level activities the user performs
  • Steps: Specific actions within each activity
  • Tasks: Detailed work required to complete each step

Vertical axis (top-to-bottom): Priority and releases

  • Top rows: Essential tasks (MVP / Release 1)
  • Lower rows: Nice-to-have tasks (Future releases)

Story Map Structure

Segment → Persona → Narrative (User's goal)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[Activity 1] → [Activity 2] → [Activity 3] → [Activity 4] → [Activity 5]
     ↓              ↓              ↓              ↓              ↓
  [Step 1.1]     [Step 2.1]     [Step 3.1]     [Step 4.1]     [Step 5.1]
  [Step 1.2]     [Step 2.2]     [Step 3.2]     [Step 4.2]     [Step 5.2]
  [Step 1.3]     [Step 2.3]     [Step 3.3]     [Step 4.3]     [Step 5.3]
     ↓              ↓              ↓              ↓              ↓
  [Task 1.1.1]   [Task 2.1.1]   [Task 3.1.1]   [Task 4.1.1]   [Task 5.1.1]
  [Task 1.1.2]   [Task 2.1.2]   [Task 3.1.2]   [Task 4.1.2]   [Task 5.1.2]
  [Task 1.1.3]   [Task 2.1.3]   [Task 3.1.3]   [Task 4.1.3]   [Task 5.1.3]
  ...            ...            ...            ...            ...

Why This Works

  • User-centric: Organizes work around user goals, not engineering modules
  • Shared understanding: Product, design, engineering all see the same journey
  • Prioritization clarity: Top tasks = MVP, lower tasks = future iterations
  • Gap identification: Missing steps or tasks become obvious
  • Release planning: Draw horizontal "release lines" to define scope

Anti-Patterns (What This Is NOT)

  • Not a Gantt chart: This isn't project management—it's user journey visualization
  • Not a feature list: Activities aren't features—they're user behaviors
  • Not static: Story maps evolve as you learn more about users

When to Use This

  • Kicking off a new product or major feature
  • Aligning stakeholders on user workflow
  • Prioritizing backlog based on user needs
  • Identifying MVP vs. future releases
  • Onboarding new team members to the product vision

When NOT to Use This

  • For trivial features (don't map what you already understand)
  • When user workflows are constantly changing (map stabilizes workflows)
  • As a replacement for user stories (the map informs stories, doesn't replace them)

Application

Step 1: Define the Context

Use template.md for the full fill-in structure.

Segment

Who are you building for?

markdown
### Segment:
- [Specify the target segment, e.g., "Small business owners using DIY accounting software"]

Quality checks:

  • Specific: Not "users" but "enterprise IT admins" or "freelance designers"

Persona

Provide details about the persona within this segment (reference skills/proto-persona/SKILL.md).

markdown
### Persona:
- [Describe the persona: demographics, behaviors, pains, goals]

Example:

  • "Sarah, 35-year-old freelance graphic designer, manages 5-10 client projects at once, struggles with invoicing and payment tracking, wants to spend less time on admin and more time designing"

Step 2: Define the Narrative

What is the user trying to accomplish? Frame this as a Jobs-to-be-Done statement (reference skills/jobs-to-be-done/SKILL.md).

markdown
### Narrative:
- [Concise narrative of the persona's objective, e.g., "Complete a client project from kickoff to final payment"]

Quality checks:

  • Outcome-focused: Not "use the product" but "deliver a client project on time and get paid"
  • One sentence: If it takes more than one sentence, the scope may be too broad

Step 3: Identify Activities (Backbone)

List 3-5 high-level activities the persona engages in to fulfill the narrative. These form the backbone of your map.

markdown
### Activities:
1. [Activity 1, e.g., "Negotiate project scope and pricing"]
2. [Activity 2, e.g., "Execute design work"]
3. [Activity 3, e.g., "Deliver final assets to client"]
4. [Activity 4, e.g., "Send invoice and receive payment"]
5. [Activity 5, optional]

Quality checks:

  • Sequential: Activities happen in order (left-to-right)
  • User actions: Describe what the user does, not what the product provides
  • 3-5 activities: Too few = oversimplified, too many = overwhelming

Step 4: Break Activities into Steps

For each activity, list 3-5 steps that detail how the activity is carried out.

markdown
### Steps:

**For Activity 1: [Activity Name]**
- Step 1: [Detail step 1, e.g., "Review client brief"]
- Step 2: [Detail step 2, e.g., "Draft project proposal"]
- Step 3: [Detail step 3, e.g., "Negotiate timeline and budget"]
- Step 4: [Optional step 4]
- Step 5: [Optional step 5]

**For Activity 2: [Activity Name]**
- Step 1: [Detail step 1]
- Step 2: [Detail step 2]
...

Quality checks:

  • Actionable: Each step is something the user does
  • Observable: You could watch someone perform this step
  • Logical sequence: Steps follow a natural order

Step 5: Break Steps into Tasks

For each step, list 5-7 tasks that must be completed.

markdown
### Tasks:

**For Activity 1, Step 1: [Step Name]**
- Task 1: [Detail task 1, e.g., "Read client brief document"]
- Task 2: [Detail task 2, e.g., "Identify key deliverables"]
- Task 3: [Detail task 3, e.g., "Note budget constraints"]
- Task 4: [Detail task 4, e.g., "Clarify timeline expectations"]
- Task 5: [Detail task 5, e.g., "List open questions for client"]
- Task 6: [Optional task 6]
- Task 7: [Optional task 7]

**For Activity 1, Step 2: [Step Name]**
- Task 1: [Detail task 1]
...

Quality checks:

  • Granular: Tasks are small, specific actions
  • User-facing or behind-the-scenes: Include both (e.g., "Send email" and "Receive confirmation")
  • Prioritizable: You'll prioritize tasks vertically (top = essential, bottom = nice-to-have)

Step 6: Prioritize Vertically

Arrange tasks top-to-bottom by priority:

  • Top rows: MVP / Release 1 (must-have)
  • Middle rows: Release 2 (important but not critical)
  • Bottom rows: Future / Nice-to-have

Draw horizontal "release lines" to demarcate scope.


Step 7: Identify Gaps and Opportunities

Review the map and ask:

  • Are there missing steps or tasks?
  • Are there pain points we're not addressing?
  • Are there opportunities to delight users?
  • Do all activities flow logically?

Examples

See examples/sample.md for a full story map example.


Common Pitfalls

Pitfall 1: Activities Are Features, Not User Behaviors

Symptom: "Activity 1: Use the dashboard. Activity 2: Generate reports."

Consequence: You've mapped the product, not the user journey.

Fix: Reframe as user actions: "Activity 1: Monitor project progress. Activity 2: Summarize work for stakeholders."


Pitfall 2: Too Many Activities

Symptom: 10+ activities across the backbone

Consequence: Map becomes overwhelming and loses focus.

Fix: Consolidate. If you have 10 activities, you're likely mixing activities with steps. Aim for 3-5 high-level activities.


Pitfall 3: Tasks Are Too Vague

Symptom: "Task 1: Do the thing"

Consequence: Can't prioritize or estimate vague tasks.

Fix: Be specific: "Task 1: Enter client email address in the 'Bill To' field."


Pitfall 4: Ignoring Vertical Prioritization

Symptom: All tasks at the same level—no MVP vs. future releases defined

Consequence: No clarity on what to build first.

Fix: Explicitly prioritize. Draw release lines. Force hard choices about what's MVP.


Pitfall 5: Mapping in Isolation

Symptom: PM creates the map alone, then presents it to the team

Consequence: No shared ownership or understanding.

Fix: Map collaboratively. Run a story mapping workshop with product, design, and engineering.


References

Related Skills

  • skills/proto-persona/SKILL.md — Defines the persona for the story map
  • skills/jobs-to-be-done/SKILL.md — Informs the narrative and activities
  • skills/user-story/SKILL.md — Tasks from the map become user stories
  • skills/problem-statement/SKILL.md — Problem statement frames the narrative

External Frameworks

  • Jeff Patton, User Story Mapping (2014) — Origin of the story mapping technique
  • Teresa Torres, Continuous Discovery Habits (2021) — Opportunity solution trees (complementary to story maps)

Dean's Work

  • User Story Mapping Prompt (adapted from Jeff Patton's methodology)

Provenance

  • Adapted from prompts/user-story-mapping.md in the https://github.com/deanpeters/product-manager-prompts repo.

Skill type: Component Suggested filename: user-story-mapping.md Suggested placement: /skills/components/ Dependencies: References skills/proto-persona/SKILL.md, skills/jobs-to-be-done/SKILL.md, skills/user-story/SKILL.md, skills/problem-statement/SKILL.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the User Story Mapping AI skill do?

Create a user story map that lays out activities, steps, tasks, and release slices. Use when planning a workflow, backlog, or MVP around the user journey.

Why use User Story Mapping on TypingMind?

Because you install it once and use it with any model. User Story Mapping 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 User Story Mapping in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/getcrew44/crew44/tree/main/daemon/internal/presets/defaultcrew/skills/product/user-story-mapping. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use User Story Mapping?

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 User Story Mapping?

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

Is the User Story Mapping AI skill free?

Yes. It is published on GitHub by getcrew44 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 👇