Plan User Flows logo

Plan User Flows

Community
schudarin
plan-user-flows

Plan user flows and screen states for a Figma design before any designing starts. Use when asked to plan a user flow, map out screens for a feature, define screen states, plan a Figma file structure, or work out what needs to be designed before opening Figma. Produces a complete flow map with all screens, states, entry/exit points, and a suggested Figma page structure.

Overview

Publisherschudarin
Repositorychudarin-design-skills
Skill nameplan-user-flows
Stars
4
Forks
0
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Plan User Flows 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/schudarin/chudarin-design-skills/tree/main/skills/plan-user-flows
  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/schudarin/chudarin-design-skills.git /tmp/chudarin-design-skills
mkdir -p .claude/skills
cp -r /tmp/chudarin-design-skills/skills/plan-user-flows .claude/skills/plan-user-flows
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plan User Flows 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 Plan User Flows 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 Plan User Flows 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.

Figma Plan User Flows

Plans what needs to be designed before a pixel is touched — mapping all screens, states, entry points, and edge cases so designers do not discover missing states mid-build.

Required Inputs

  • Feature or task being designed
  • User type (who performs this flow?)
  • Platform (iOS / Android / Web / Multi-platform)
  • Starting point (where does the user begin?)
  • Known edge cases (optional)

Output Structure

1. Flow Overview

Feature, user, goal, entry points, success exit, failure exits.

A flow that puts the user into a mode — a queue walk, a wizard, a guided pass — also maps three paths: where each exit lands, by screen; what an outside event does mid-mode (a new message, opening another item) and what the user sees next; how the user gets back in, and whether progress is kept. Each is a row in the screen map, not a note.

2. Screen Map

#Screen nameTypeTriggered byNotes
1[Screen]New/Modal/Drawer/Toast[What triggers][Considerations]

Screen types to cover: entry, happy path, loading, success, error (network/validation/permission), empty, first-time/onboarding, edge cases.

3. State Matrix

[Screen name]

StateTriggerVisual changeAction available
DefaultPage load[Description][What user can do]
LoadingUser taps actionSkeleton/spinnerNone
ErrorAPI failureError messageRetry/Go back
EmptyNo dataEmpty state[CTA]

4. Decision Points

Decision: [Name]

  • If yes: [Screen N]
  • If no: [Screen X]

5. Suggested Figma File Structure

Feature name/
- Cover
- Flow Map
- Happy Path
- Error States
- Empty States
- Edge Cases
- Handoff

6. What Not to Design Yet

[Explicit out-of-scope items — prevents scope creep]

Quality Checks

  • Loading, error and empty are covered for what this feature adds; states that reused components already handle are listed by component name, not mapped as new screens; every state traces to a source or is marked as a question
  • All decision points mapped with both branches
  • Entry points include all realistic user paths
  • Out-of-scope section is explicit
  • Figma file structure matches screen map

Drawing the map in Figma

When the map goes on the canvas as blocks and arrows:

  • If the user gives an example board, read it through the API — sizes, colours, text styles, connector ends — not from a screenshot, and ask what each colour or mark means. Without an example, use the default style below; do not invent one.
  • Build inside the frame the user prepared for the map, not in new frames next to it.
  • Place blocks on one grid, left to right in the order of the path.
  • End every connector on a block, never on the frame that holds the scheme.
  • Before showing, walk the connector graph: every block except an entry has an incoming connector, every block except a final exit has an outgoing one. Fix or list the ones that fail.

Default style. Four colour roles; when the file has colour variables, map each role to the closest one, otherwise use the values given.

RoleDefaultUsed for
Accent#3a88f5text, other paths, key block fill, outlines
Tint#dfecfdblock fill
Grid#daf0ffcanvas grid lines
Main path#ff62b2the main path's connectors, marks
  • Font: the file's main sans family; Inter when the file has none. Only Bold and Medium are used — check both styles exist before the first text write.
  • Canvas: white frame with a 1 px grid in the Grid colour.
  • Step: 394 wide, Tint fill, radius 35, vertical auto-layout, padding 40, gap 24; title Bold 36 and description Medium 18 in Accent.
  • Entry or short block: horizontal, height 127, padding 40, width hugs the title; title only.
  • Key block (the finish): Accent fill, white text.
  • Mark on a block: pill 42 high, radius 999, padding 8/16, white Bold 20 on Main path.
  • Connectors: elbowed, 2 px, arrow at the end; the main path in Main path, every other path in Accent; a two-way transition has arrows at both ends. In a Design file connectors cannot be created, only cloned — see the connectors file of figma-plugin-api-rules.
  • A sub-scheme sits in an outline: 4 px Accent at 48 %, radius 144.
  • Header: Bold 144, subtitle Bold 46, in Accent.

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 Plan User Flows AI skill do?

Plan user flows and screen states for a Figma design before any designing starts. Use when asked to plan a user flow, map out screens for a feature, define screen states, plan a Figma file structure, or work out what needs to be designed before opening Figma. Produces a complete flow map with all screens, states, entry/exit points, and a suggested Figma page structure.

Why use Plan User Flows on TypingMind?

Because you install it once and use it with any model. Plan User Flows 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 Plan User Flows in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/schudarin/chudarin-design-skills/tree/main/skills/plan-user-flows. 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 Plan User Flows?

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 Plan User Flows?

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

Is the Plan User Flows AI skill free?

Yes. It is published on GitHub by schudarin 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 👇