Ai Design Workflow logo

Ai Design Workflow

Community
flitzrrr
ai-design-workflow

AI tool integration into the design process, structured prompting for designers, creative AI usage with clear boundaries, and review workflows.

Overview

Publisherflitzrrr
Repositoryfrontend-design-skills
Skill nameai-design-workflow
Stars
9
Forks
2
Bundled files
Instructions only
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.

  • 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 Ai Design Workflow 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/ai-design-workflow
  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/ai-design-workflow .claude/skills/ai-design-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ai Design Workflow 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 Ai Design Workflow 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 Ai Design Workflow 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.

AI Design Workflow

AI is an assistant, not an autopilot. You retain control over direction, decisions, and quality. AI accelerates individual steps but replaces neither strategy nor judgment.

Scope

Use this skill when you:

  • Integrate AI tools purposefully into design phases
  • Structure prompts for design tasks
  • Evaluate and contextualize AI-generated content (text, images)
  • Use AI as a sparring partner during reviews
  • Inform clients about AI usage
  • Want to preserve your own design signature despite using AI

Principles

1. AI Is an Assistant, Not an Autopilot

You retain control. AI accelerates individual steps but replaces neither strategy nor judgment.

2. The Workflow Decides, Not the Tool

Define in advance which phases AI assists with and which it does not. Without a clear process, results are arbitrary.

3. Prompting Is Briefing

The same principles that apply to a good client briefing apply to AI: context, role, task, format, tone.

4. Combinatorial Strength, Conceptual Weakness

AI interpolates between known patterns (combinatorial creativity). The deliberate break with conventions comes from the human.

5. Transparency Toward Clients

Communicate openly where and how AI is used in the project. Concealed usage erodes trust.

6. Every AI Output Is a Draft

No AI output goes into production unchecked. Every result undergoes a human review.

Rules

DO: Deploy AI Purposefully per Design Phase

PhaseAI UsageHuman Decides
BriefingAnalyze gaps and contradictionsWhich questions are relevant
ResearchDescribe industry patterns, competitionWhich insights are relevant
PersonasSharpen assumptions, plausibility checksFinal persona definition
ConceptMoodboard variations, creative techniquesWhich direction to pursue
Visual DesignColor palettes, font pairings, microcopyComposition, consistency, final design
ReviewCritical assessment, accessibility reviewWhether feedback is implemented
HandoffDocumentation templates, style guide copyFactual accuracy

DO: Structure the Prompt Like a Briefing

An effective prompt contains 5 elements:

  1. Role: Who should the AI be? ("You are an experienced UX designer...")
  2. Context: Starting situation (project, industry, target audience)
  3. Task: What exactly should be done? (one task per prompt)
  4. Format: In what form? (list, table, prose)
  5. Constraints: What should NOT happen? (restrictions, style guidelines)

DO: Prompt Iteratively Instead of One-Shot

  • START with a rough prompt, evaluate, refine.
  • USE follow-up prompts: "Make it more formal," "Narrow it down to 3 variants," "Explain your choice."
  • A chain of prompts is better than one perfect prompt.

DO: Use AI as a Sparring Partner in Reviews

  • DESCRIBE a finished design in words and request a critical assessment.
  • ASK about misunderstandings, unclear elements, accessibility barriers.
  • The act of formulating the description alone often reveals weaknesses.

DO: Evaluate AI-Generated Images Based on Context

  • Suitable: Abstract backgrounds, generic illustrations, concept visualizations.
  • Unsuitable: Authentic corporate photography, portraits, brand-specific imagery.
  • Communicate clearly to the client what is a placeholder and what is final material.

DON'T: Use AI as a Last Resort When Out of Ideas

  • If all variations feel generic, the problem is a missing concept, not a better prompt.
  • Go back to the strategy phase.

DON'T: Adopt AI Output Without Contextual Review

  • AI has no knowledge of company history, market context, or customer sentiment.
  • Validate every result against the briefing, brand, and target audience.

DON'T: Recycle Prompts Across Projects

  • Using the same prompts across different projects leads to interchangeable results.
  • Always adapt prompts to the project context.

DON'T: Use AI as a Substitute for User Testing

  • AI generates hypotheses but does not simulate real reactions.
  • Usability tests with real people remain mandatory.

Patterns

Briefing Analysis Prompt

At project kickoff: "Here is a project briefing for [project type]. Identify open questions, unclear requirements, and points that need to be clarified before starting." Result: Structured list of questions. See references/prompt-patterns.md for details and prompt templates.

Moodboard Divergence

Early concept phase: 1. Generate 15–20 variations with image generators, 2. Curate down to 2–3 directions, 3. Present as a decision-making basis.

SCAMPER Prompt Chain

For evolving existing ideas: AI examines an idea through each SCAMPER lens (Substitute, Combine, Adapt, Modify, Put to other use, Eliminate, Reverse).

Copy Refinement Loop

For microcopy, button labels, error messages: 1. Describe context, tone, and function, 2. Generate 5 variations, 3. Select the best and refine.

AI Review Session

After visual design, before handoff: 1. Describe the design in detail using words, 2. Request a critical assessment regarding clarity, accessibility, and consistency, 3. Use the response as a checklist.

Documentation Accelerator

During the handoff phase: Describe design decisions and have a structured documentation template generated. Framework produced in minutes instead of hours.

Anti-Patterns

The AI Sameness Trap

All projects look alike because the same tools are used with similar prompts. Solution: Treat AI output as raw material, never as the final product. Your own design signature must remain recognizable.

The Prompt Perfectionist

Spending hours crafting the perfect prompt instead of working iteratively. Solution: Start with an 80% prompt, refine in 2–3 iterations.

AI as an Excuse for Lacking Expertise

"The AI did it that way" as a justification. Solution: Every decision must be defensible by the designer.

Hype-Driven Feature Adoption

Integrating every new AI feature immediately without evaluating its value. Solution: Evaluate in a test project before production use.

Checklist

  • AI usage explicitly planned per design phase (where YES, where NO)
  • Prompts contain role, context, task, format, and constraints
  • AI-generated content documented internally
  • Every AI output validated against briefing and brand values
  • AI-generated images labeled as concept material or final
  • Client informed about AI usage
  • AI review session conducted before handoff
  • Usability tests with real users planned (not replaced by AI)
  • Own design signature recognizable in the final result

Cross-References

  • design-process — The AI workflow is an extension, not a replacement for the design process
  • customer-journey — AI can accelerate persona development and touchpoint analysis
  • landing-pages — AI-generated text and images must meet landing page standards
  • website-audit — AI tools can support website analysis
  • branding-identity — AI output must align with brand identity

Frequently asked questions

What does the Ai Design Workflow AI skill do?

AI tool integration into the design process, structured prompting for designers, creative AI usage with clear boundaries, and review workflows.

Why use Ai Design Workflow on TypingMind?

Because you install it once and use it with any model. Ai Design Workflow 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 Ai Design Workflow in TypingMind?

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

Which AI models can use Ai Design Workflow?

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 Ai Design Workflow?

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

Is the Ai Design Workflow 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.

View all

Set up your own AI workspace now

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