TypingMindTypingMindThe best frontend for AI
Customer Journey logo

Customer Journey

Community
flitzrrr
customer-journey

Personas, touchpoint mapping, phase models, onboarding, customer retention, and data-driven journey analysis for user-centered web design.

Overview

Publisherflitzrrr
Repositoryfrontend-design-skills
Skill namecustomer-journey
Stars
9
Forks
2
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Customer Journey 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/flitzrrr/frontend-design-skills/tree/main/skills-src/customer-journey
  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/flitzrrr/frontend-design-skills.git /tmp/frontend-design-skills
mkdir -p .claude/skills
cp -r /tmp/frontend-design-skills/skills-src/customer-journey .claude/skills/customer-journey
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Customer Journey 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 Customer Journey 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 Customer Journey 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

Every design decision begins with the user's needs, motivations, and questions — not with the company's internal organizational structure.

Scope

Use this skill when you:

  • Create or validate personas for a web project
  • Visualize a customer journey map
  • Identify and prioritize touchpoints
  • Design onboarding sequences
  • Assign content to a journey phase
  • Plan post-purchase customer retention measures

Principles

1. Customer Perspective Before Company Perspective

Every design decision begins with the user, not with the internal structure.

2. Touchpoints Are Experience Moments

Every point of contact generates emotions and influences the purchase decision. No touchpoint should be left to chance.

3. The Journey Is Not Linear

Users jump between phases, skip steps, and return. Designs must account for this non-linearity.

4. Data Before Assumptions

Personas and journey maps are based on research (analytics, interviews, surveys) — not on gut feeling.

5. The Journey Does Not End at Purchase

Customer retention, referral, and win-back are integral components.

6. One Goal per Touchpoint

Each point of contact pursues exactly one primary call to action.

Rules

DO: Create Data-Driven Personas

  • COMBINE web analytics, CRM data, support inquiries, and user interviews.
  • DEFINE per persona: demographic key data, goals, pain points, preferred channels, decision criteria.
  • VALIDATE personas regularly against real user data and update at least annually.

DO: Explicitly Map the 5+1 Phases

  1. Awareness — The user recognizes a need or problem.
  2. Interest — They actively search for information and solutions.
  3. Evaluation — They compare options, read reviews, consult their network.
  4. Purchase Decision — They select an offer and complete the transaction.
  5. Customer Experience — They use the product and form an opinion.
  6. Retention — The company builds a long-term relationship.

DO: Categorize Touchpoints Using EPOMS

  • Earned: Reviews, referrals, press coverage.
  • Paid: Ads, sponsored posts, banner advertising.
  • Owned: Website, blog, newsletter, physical store.
  • Managed: Social media channels, app store presence.
  • Shared: Forum posts, shared social media content.

DO: Use Emotional Journey Mapping

  • CAPTURE the user's emotional state at each touchpoint.
  • FLAG critical points where negative emotions lead to abandonment.
  • DEFINE measures to transform negative emotions into positive ones.

DO: Fully Leverage Internal Data Sources

  • Web analytics (user flow, bounce rates, conversion paths)
  • Social media monitoring (sentiment, questions, complaints)
  • Email marketing analytics (open rates, click-through rates)
  • Support inquiries and complaints
  • Sales statistics
  • Feedback from marketing, sales, and service teams

DON'T: Invent Personas Based on Assumptions

  • NEVER create personas without a data foundation. Fictional personas lead to design decisions that miss reality.

DON'T: View Touchpoints in Isolation

  • A touchpoint is always part of the overall journey. Never optimize a contact point without examining the impact on upstream and downstream points.

DON'T: Treat B2B and B2C as Identical

  • B2B journeys have longer decision cycles, more decision-makers, and more heavily rational criteria. Use separate journey maps.

DON'T: Create the Journey Only Once

  • Validate the map at least semi-annually against current analytics data and customer feedback.

Patterns

Customer Journey Map (Visualization)

At project kickoff and before every relaunch. Horizontal axis = phases, vertical axis = touchpoints, emotions, channels, pain points, opportunities. Result: Visual artifact for shared understanding. See references/journey-map-template.md for details.

Onboarding Sequence

After purchase decision or registration: 1. Welcome message with a clear next step, 2. Step-by-step introduction (max. 3 steps), 3. First success within 60 seconds, 4. Follow-up after 24 hours and 7 days.

Micro-Conversion Chain

When the primary conversion is too far from first contact: Define 3–5 intermediate goals (newsletter, whitepaper, webinar) that progressively guide the user closer to the primary conversion.

Re-Engagement Loop

For inactive existing customers: Trigger-based communication (e.g., 30 days of inactivity), personalized offer, easy re-entry, feedback request.

Persona Validation Loop

When personas are based on assumptions or are older than 6 months: 1. Translate hypotheses into an interview guide, 2. Conduct 5–8 interviews, 3. Cross-reference with analytics, 4. Update or discard the persona.

Touchpoint Audit

Before a relaunch or when conversions are declining: 1. Capture all touchpoints in a matrix, 2. Walk through and evaluate from the user's perspective, 3. Identify gaps, 4. Prioritize the top 3 optimizations.

Anti-Patterns

The Company Org-Chart Website

The website structure mirrors the departmental structure instead of the customer journey. Users must understand the company's internal logic. Solution: Structure along user needs and journey phases.

Touchpoint Overkill

Too many contact points at once, without priorities. Inconsistent brand experience. Solution: Better to have 5 excellent than 20 mediocre touchpoints.

The Forgotten Post-Purchase Phase

All energy flows into acquisition; the customer experience after purchase is neglected. Solution: Allocate at least 30% of journey design effort to phases 5 and 6.

Copy-Paste Personas

Generic personas from templates without project-specific data. Solution: Every persona needs at least 3 project-specific data points.

Checklist

  • At least 2 data-driven personas defined
  • All 5+1 journey phases documented
  • Touchpoints categorized using EPOMS
  • Emotional states captured per phase
  • Pain points and opportunities identified per touchpoint
  • Clear call to action defined per touchpoint
  • Onboarding sequence designed for new customers
  • Customer retention measures planned for post-purchase phase
  • Journey map created as a visual artifact
  • KPIs defined per phase
  • Journey validated against real analytics data

Cross-References

  • design-process — The customer journey informs the briefing and concept phase
  • landing-pages — Landing pages are central touchpoints in the journey
  • website-audit — Journey analysis is a core component of every relaunch audit
  • ux-design — UX design as the framework for user-centered journey design
  • ai-design-workflow — AI can accelerate persona development and touchpoint analysis

Frequently asked questions

What does the Customer Journey AI skill do?

Personas, touchpoint mapping, phase models, onboarding, customer retention, and data-driven journey analysis for user-centered web design.

Why use Customer Journey on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/customer-journey. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Customer Journey?

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 Customer Journey?

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

Is the Customer Journey AI skill free?

Yes. It is published on GitHub by flitzrrr 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.

Related AI Skills

View all
NousResearch logo

Serving Llms Vllm

NousResearch
OrganizationPopular

vLLM: high-throughput LLM serving, OpenAI API, quantization.

53.5K
250.4K
4 files
View
NousResearch logo

Huggingface Hub

NousResearch
OrganizationPopular

HuggingFace hf CLI: search/download/upload models, datasets.

53.5K
250.4K
Instructions
View
NousResearch logo

Pytorch Lightning

NousResearch
OrganizationPopular

Clean training loops with built-in distributed support.

53.5K
250.4K
3 files
View
microsoft logo

Troubleshoot

microsoft
OrganizationPopular

Investigate unexpected behavior in the current Copilot agent session by analyzing its event log. Use when the user asks why something happened, why a request was slow, why a tool was or was not used,…

42.7K
192.7K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇