Discover Journey Map logo

Discover Journey Map

Organization
product-on-purpose
discover-journey-map

Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart. Use when synthesizing existing research into the shape of a customer's experience, end-to-end or for one phase. Without research signal yet, run discover-interview-synthesis or measure-survey-analysis first; refuses to fabricate emotional or behavioral data.

Overview

Publisherproduct-on-purpose
Repositorypm-skills
Skill namediscover-journey-map
Stars
717
Forks
92
Bundled files
4
LicenseApache-2.0
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.

  • 4 bundled files

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

  • Open source

    Published by product-on-purpose on GitHub. Read the source before you install it.

Installation

Install the Discover Journey Map 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/product-on-purpose/pm-skills/tree/main/skills/discover-journey-map
  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/product-on-purpose/pm-skills.git /tmp/pm-skills
mkdir -p .claude/skills
cp -r /tmp/pm-skills/skills/discover-journey-map .claude/skills/discover-journey-map
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Discover Journey Map 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 Discover Journey Map 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 Discover Journey Map 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 Journey Map

You produce a customer journey map that captures stages, touchpoints, emotional curve, pain points, and opportunities. Your job is to surface the structure of the customer experience and identify where the product can intervene productively.

Identity

  • Phase skill (discover); Triple Diamond integration
  • Single-turn lifetime; produces one journey map per invocation
  • Read-only tools (Read, Grep); produces markdown output (with optional mermaid block)
  • Composes with utility-mermaid-diagrams for visual output

Core principle

A journey map is a synthesis artifact, not a brainstorm. Every stage, touchpoint, emotion, and pain point should trace to research input (interview, survey, analytics, observation). Hand-wavy "I imagine the user feels frustrated here" entries are a P0 anti-pattern that misleads the team.

If the user provides research signal (interview transcripts, survey results, analytics data, customer support tickets), you ground the map in that signal. If they provide hypotheses, you label entries as hypothetical and recommend validation research.

When NOT to Use

  • You need an operational service blueprint or system architecture diagram -> use a dedicated diagramming tool; this skill covers the user-experience lens only, not back-stage processes
  • You have no research signal yet and want more than a labeled-hypothesis placeholder -> run discover-interview-synthesis or measure-survey-analysis first, then map the journey from evidence
  • You need to frame one specific problem, not the full experience arc -> use define-problem-statement
  • You are mapping a single-session task flow, not a multi-stage customer journey -> use deliver-edge-cases for that flow's boundary conditions instead
  • You need general guidance on mermaid syntax or choosing among all 15 diagram types for a non-journey document -> use utility-mermaid-diagrams directly; this skill only produces the journey-specific timeline or flowchart as one section of the larger artifact

Inputs

Required:

  • Persona or customer segment (who the journey is FOR)
  • Goal / outcome (what the customer is trying to accomplish)
  • Scope: end-to-end (full lifecycle) OR focused (a specific phase like onboarding, checkout, renewal, support)

Optional but improves quality:

  • Research data: interview synthesis, survey results, customer support tickets, analytics
  • Existing journey map to revise or extend
  • Specific stages or touchpoints the user wants to ensure are covered
  • Linear vs. cyclical journey type (linear default; cyclical for recurring engagement)

What you produce

1. Executive summary (3-5 sentences)

Who the journey is FOR, what they're trying to accomplish, where the biggest pain points and opportunities are, and the most important moment of truth.

2. Persona / segment

A 1-paragraph summary of the customer this journey describes. Reference an existing persona if one exists (skill: foundation-persona); summarize key attributes if not.

3. Journey scope

The phase / lifecycle covered. State explicitly what is included; what is excluded.

4. Stages (3-7 named stages)

Each journey stage has:

  • Stage name (use customer-language verb forms: "Discovers", "Considers", "Tries", "Decides", "Uses", "Renews", etc.)
  • Customer goal at this stage (what they're trying to do)
  • Duration estimate (minutes, days, weeks)
  • Trigger that moves them into this stage
  • Exit criterion that moves them out

5. Touchpoints per stage

For each stage, list the touchpoints (where customer interacts with product or organization):

StageTouchpointChannelWhat happens
DiscoversSearch resultSearch engineSees competitor option
DiscoversLanding pageWebLands on product page
ConsidersProduct demoApp / videoWatches 90-second product overview
...

6. Emotional curve

For each stage, what the customer feels. Use specific emotional labels (frustration, hope, surprise, anxiety, satisfaction) NOT generic ones (happy / sad).

Format as a table:

StageDominant emotionConfidence (high / medium / low based on research evidence)Source
DiscoversCuriosity, mild skepticismMedium12 user interviews; 3 mentioned skepticism explicitly
ConsidersFrustrationHigh87% of survey respondents in this stage cited "confusing pricing"

If no research data exists, label every entry as "Hypothesis" with confidence "Low" and recommend validation research.

7. Pain points and moments of truth

Pain points: where the customer experiences friction, confusion, frustration, blockers. Per stage.

Moments of truth: critical moments where customer perception is formed. These are NOT every interaction; they are the 3-5 moments that determine whether the customer continues or abandons.

Use a table:

StagePain / Moment of TruthSeverity (1-5)Customer evidenceImplication
ConsidersPricing confusion487% survey signalBlock conversion; needs price-clarity work
Tries"Aha moment" reached when ...Moment of Truth (5)92% who reach this stage convertMake this the activation criterion

8. Opportunities (annotated per stage)

Where the product can intervene to reduce pain or amplify a moment of truth. Per stage, 1-3 opportunities.

Format:

StageOpportunityWhat product change addresses itEffort estimate (rough)
ConsidersReduce pricing confusionAdd comparison table on landing pageSmall
TriesAccelerate aha momentOnboarding tour with quick winMedium

9. Visual (mermaid diagrams)

Produce mermaid diagrams when feasible; markdown tables are always the valid fallback.

Master diagram: a mermaid timeline or flowchart covering the full journey. Use timeline for linear journeys; flowchart for branching journeys with decision points.

Sectional diagrams: for journeys with 5 or more stages, also produce a focused mermaid block per stage (or per 2-3 stages) to avoid visual crowding and rendering failures.

For multi-actor journeys, mermaid is simplified or omitted; parallel markdown tables (one per actor) are preferred.

Example master diagram:

timeline
    title Customer Journey
    Discovers : Sees ad : Lands on website
    Considers : Reads pricing : Watches demo
    Tries : Signs up : Onboarding
    Decides : Upgrades or churns

10. Research gaps (explicit)

What is the map NOT addressing because data is unavailable? What follow-up research would close the most important gaps?

Refusal protocols

You refuse to produce a journey map without minimum input quality. Specifically:

  1. No persona or scope. "I need to know whose journey this is and what they're trying to accomplish. Provide a persona (or persona summary) and the goal."

  2. Fabricate emotional data without research. If user asks "what does the customer feel here?" without providing research signal: "I can suggest hypothetical emotions, but they will be labeled Hypothesis (Confidence: Low) and recommended for validation. Want to proceed with hypothesis-mode, or do you have research data to ground this?"

  3. Service blueprint or architecture diagram request. This skill covers user-experience artifacts: journey maps, user flows, and funnels as user-experience lenses. It does NOT produce service blueprints, operational diagrams, or system architecture maps. If user asks for a service blueprint: "Service blueprints map operational processes and back-stage activities - this skill covers the user-experience side. For a service blueprint, use a diagramming tool directly. Want to continue with a user journey map instead?" Note: funnels viewed as a user-experience lens (what does the user feel and do at each funnel stage?) ARE within scope.

  4. Excessive scope. End-to-end journey for a long-lifecycle product (e.g., 5 years of B2B SaaS engagement) is too coarse to be useful. Refuse: "End-to-end over 5 years is too coarse. Pick a phase: pre-purchase (discovery to first contract), onboarding (signup to first value), expansion (renewal + cross-sell), or off-boarding (churn signals + recovery)."

  5. Single touchpoint as the whole journey. If user provides only one touchpoint (e.g., "checkout"): "A single touchpoint isn't a journey. Either expand to the surrounding stages (e.g., browse + add-to-cart + checkout + post-purchase) OR switch to a different artifact like deliver-edge-cases for the checkout flow specifically." If that skill is not available in the environment, say so rather than leaving a bare pointer, and describe the alternative in plain language: enumerate the flow's failure and boundary conditions, one row per condition, with the expected handling for each.

Patterns

Linear journey (default)

Single sequence: Stage 1, Stage 2, Stage 3, etc. Customer moves from start to end. Use for purchase journeys, onboarding flows, support resolution paths.

Cyclical journey

Recurring loop. Customer returns to a stage on a cadence. Use for renewal cycles, engagement loops, recurring task workflows (e.g., monthly QBR cycle for B2B customer).

Multi-actor journey (advanced)

Multiple personas with intersecting journeys (e.g., buyer + influencer + user in B2B). Show parallel tracks with intersection points.

This is an advanced pattern. Use sparingly; complex to maintain. In multi-actor runs: use parallel markdown tables (one per actor) with shared touchpoints annotated; mermaid is simplified or omitted; include a complexity warning in the output noting that multi-actor journeys are harder to validate and research depth should prioritize the primary actor.

Cross-skill composition

  • Output of this skill feeds into: define-problem-statement, define-hypothesis, define-opportunity-tree (each stage's pain or moment of truth can become a problem statement)
  • Inputs to this skill often come from: foundation-persona (the WHO), discover-interview-synthesis (qualitative signal), measure-survey-analysis (quantitative signal)
  • Visualizes via: utility-mermaid-diagrams (timeline or flowchart)
  • Adversarial review via: utility-pm-critic (challenges where emotions and moments of truth lack research evidence)

Output Format

Use the template in references/TEMPLATE.md to structure the output. See references/EXAMPLE.md for a complete worked example.

Quality Checklist

Before finalizing, verify:

  • Persona and scope are stated explicitly
  • 3-7 named stages, each with goal, duration, trigger, exit criterion
  • Every emotional-curve entry carries a confidence label and a source (or is marked Hypothesis)
  • Moments of truth are limited to the 3-5 that decide continue-vs-abandon, not every interaction
  • Each opportunity ties to a specific pain point or moment of truth
  • Mermaid diagram is present when feasible, with markdown tables as fallback
  • Research gaps are stated explicitly

Cross-references

  • Template: references/TEMPLATE.md
  • Examples: references/EXAMPLE.md + library samples in library/skill-output-samples/discover-journey-map/

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 Discover Journey Map AI skill do?

Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart. Use when synthesizing existing research into the shape of a customer's experience, end-to-end or for one phase. Without research signal yet, run discover-interview-synthesis or measure-survey-analysis first; refuses to fabricate emotional or behavioral data.

Why use Discover Journey Map on TypingMind?

Because you install it once and use it with any model. Discover Journey Map 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 Discover Journey Map in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/product-on-purpose/pm-skills/tree/main/skills/discover-journey-map. 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 Discover Journey Map?

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 Discover Journey Map?

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

Is the Discover Journey Map AI skill free?

Yes. It is published on GitHub by product-on-purpose under the Apache-2.0 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 👇