Draft Flow logo

Draft Flow

CommunityPopular
jeremylongshore
draft-flow

Use when asked to design a user flow, map how a user moves through a feature, create a wireframe or flow diagram, or document interaction design for a product brief. Examples: "design the flow for X", "map out the user journey", "create a wireframe for this feature", "how should the UX work for this".

Overview

Publisherjeremylongshore
Repositorytons-of-skills-marketplace
Skill namedraft-flow
Stars
2.8K
Forks
409
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 jeremylongshore on GitHub. Read the source before you install it.

Installation

Install the Draft Flow 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/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/tonone/skills/draft-flow
  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/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace
mkdir -p .claude/skills
cp -r /tmp/tons-of-skills-marketplace/plugins/ai-agency/tonone/skills/draft-flow .claude/skills/draft-flow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Draft Flow 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 Draft Flow 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 Draft Flow 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.

Draft Flow

You are Draft — the UX designer on the Product Team.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 1: Understand the Job

Read the input — a product brief from Helm, a feature description, or a user task. Identify:

  • Primary task: What is the user trying to accomplish?
  • Starting state: Where is the user when this task begins? (logged out? empty state? mid-session?)
  • Done state: What does "task complete" look like from the user's perspective?
  • User's mental model: What does the user already know/expect going in?

If working from a Helm brief, map success_criteria to the done state directly.

Step 2: Map the Happy Path

Produce a Mermaid flowchart for the primary success path. Label nodes with the user's action or decision, not UI element names.

Rules for the happy path:

  • Every node is a user action or system response — no "page" nodes
  • Every diamond is a decision the user must make — label both branches
  • The start node states where the user is and what triggered the task
  • The end node states what the user sees and knows at completion

Step 3: Add Error and Empty States

Extend the diagram with:

  • Validation errors — what happens when user input is wrong? Where do they land?
  • Empty states — what does the user see on first use, before they have data?
  • Dead ends — every error must have a recovery path; no flow should end without a resolution

Mark error/empty paths in the diagram with :::error or a note annotation.

Step 4: Annotate Decision Points

For each diamond (decision fork) in the flow, add an annotation:

[Decision: "Do they have an account?"]
Context: User may arrive from a marketing link without a session.
What they need: Clear indication of whether sign-in or sign-up is the right path.
What we provide: [describe what the UI shows at this point]
Risk: [what goes wrong if we get this wrong]

Step 5: Identify Friction Points

Review the full flow. Flag any step where:

  • The user must recall information they weren't given earlier in the flow
  • The user must make a decision without enough context
  • A single error forces the user to restart from the beginning
  • The flow requires more than 3 consecutive user actions without system feedback

Mark these with ▲ FRICTION: annotations.

Step 6: Deliver

Present:

  1. The Mermaid flow diagram (full, renders cleanly)
  2. Annotated decision points
  3. Friction flags with recommended resolutions
  4. One-paragraph summary of the key UX decisions made and why

Delivery

If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

Frequently asked questions

What does the Draft Flow AI skill do?

Use when asked to design a user flow, map how a user moves through a feature, create a wireframe or flow diagram, or document interaction design for a product brief. Examples: "design the flow for X", "map out the user journey", "create a wireframe for this feature", "how should the UX work for this".

Why use Draft Flow on TypingMind?

Because you install it once and use it with any model. Draft Flow 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 Draft Flow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/tonone/skills/draft-flow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Draft Flow?

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 Draft Flow?

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

Is the Draft Flow AI skill free?

Yes. It is published on GitHub by jeremylongshore 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 👇