MCP HubMCP Hub
Вернуться к навыкам

discover-journey-map

product-on-purpose
Обновлено Yesterday
8 просмотров
238
33
238
Посмотреть на GitHub
Дизайнaidesigndata

О программе

Этот навык Claude создает структурированные карты клиентского пути в формате markdown, визуализируя этапы, точки взаимодействия и эмоциональные кривые. Он поддерживает как линейные, так и циклические модели путешествия и может включать визуализации в виде диаграмм Mermaid. Разработчикам следует использовать его на этапе исследования для анализа пользовательского опыта, учитывая, что навык требует реальных исследовательских данных и не будет создавать вымышленные поведенческие данные.

Быстрая установка

Claude Code

Рекомендуется
Основной
npx skills add product-on-purpose/pm-skills -a claude-code
Команда плагинаАльтернативный
/plugin add https://github.com/product-on-purpose/pm-skills
Git клонированиеАльтернативный
git clone https://github.com/product-on-purpose/pm-skills.git ~/.claude/skills/discover-journey-map

Скопируйте и вставьте эту команду в Claude Code для установки этого навыка

Документация

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

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.

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."

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: /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

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

GitHub репозиторий

product-on-purpose/pm-skills
Путь: skills/discover-journey-map
0
agent-skillsai-skillsclaude-codeclaude-desktopdesign-sprintfoundation-sprint

Похожие навыки

executing-plans

Дизайн

Используйте навык executing-plans, когда у вас есть полный план реализации для выполнения контролируемыми партиями с контрольными точками проверки. Он загружает и критически анализирует план, затем выполняет задачи небольшими партиями (по умолчанию 3 задачи), сообщая о прогрессе между каждой партией для проверки архитектором. Это обеспечивает систематическую реализацию со встроенными контрольными точками проверки качества.

Просмотреть навык

requesting-code-review

Дизайн

Этот навык запускает суб-агента для ревью кода, который анализирует изменения в коде на соответствие требованиям перед дальнейшими действиями. Его следует использовать после завершения задач, реализации крупных функций или перед слиянием с основной веткой. Ревью помогает выявить проблемы на ранней стадии, сравнивая текущую реализацию с исходным планом.

Просмотреть навык

connect-mcp-server

Дизайн

Этот навык предоставляет разработчикам подробное руководство по подключению серверов MCP к Claude Code с использованием транспортов HTTP, stdio или SSE. Он охватывает установку, конфигурацию, аутентификацию и безопасность для интеграции внешних сервисов, таких как GitHub, Notion и пользовательские API. Используйте его при настройке интеграций MCP, конфигурации внешних инструментов или работе с Model Context Protocol от Claude.

Просмотреть навык

web-cli-teleport

Дизайн

Этот навык помогает разработчикам выбирать между веб-интерфейсом Claude Code и CLI на основе анализа задачи, а также обеспечивает бесшовное перемещение сессий между этими средами. Он оптимизирует рабочий процесс, управляя состоянием и контекстом сессии при переключении между веб-интерфейсом, CLI или мобильным приложением. Используйте его для сложных проектов, требующих различных инструментов на разных этапах работы.

Просмотреть навык