Design Handoff logo

Design Handoff

OrganizationPopular
anthropics
design-handoff

Generate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interaction states, responsive breakpoints, edge cases, and animation details.

Overview

Publisheranthropics
Repositoryknowledge-work-plugins
Skill namedesign-handoff
Stars
24.9K
Forks
3K
Bundled files
Instructions only
LicenseApache-2.0
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 anthropics on GitHub. Read the source before you install it.

Installation

Install the Design Handoff 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.
  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/anthropics/knowledge-work-plugins.git /tmp/knowledge-work-plugins
mkdir -p .claude/skills
cp -r /tmp/knowledge-work-plugins/design/skills/design-handoff .claude/skills/design-handoff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Handoff 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 Design Handoff 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 Design Handoff 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.

/design-handoff

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Generate comprehensive developer handoff documentation from a design.

Usage

/design-handoff $ARGUMENTS

Generate handoff specs for: @$1

If a Figma URL is provided, pull the design from Figma. Otherwise, work from the provided description or screenshot.

What to Include

Visual Specifications

  • Exact measurements (padding, margins, widths)
  • Design token references (colors, typography, spacing)
  • Responsive breakpoints and behavior
  • Component variants and states

Interaction Specifications

  • Click/tap behavior
  • Hover states
  • Transitions and animations (duration, easing)
  • Gesture support (swipe, pinch, long-press)

Content Specifications

  • Character limits
  • Truncation behavior
  • Empty states
  • Loading states
  • Error states

Edge Cases

  • Minimum/maximum content
  • International text (longer strings)
  • Slow connections
  • Missing data

Accessibility

  • Focus order
  • ARIA labels and roles
  • Keyboard interactions
  • Screen reader announcements

Principles

  1. Don't assume — If it's not specified, the developer will guess. Specify everything.
  2. Use tokens, not values — Reference spacing-md not 16px.
  3. Show all states — Default, hover, active, disabled, loading, error, empty.
  4. Describe the why — "This collapses on mobile because users primarily use one-handed" helps developers make good judgment calls.

Output

markdown
## Handoff Spec: [Feature/Screen Name]

### Overview
[What this screen/feature does, user context]

### Layout
[Grid system, breakpoints, responsive behavior]

### Design Tokens Used
| Token | Value | Usage |
|-------|-------|-------|
| `color-primary` | #[hex] | CTA buttons, links |
| `spacing-md` | [X]px | Between sections |
| `font-heading-lg` | [size/weight/family] | Page title |

### Components
| Component | Variant | Props | Notes |
|-----------|---------|-------|-------|
| [Component] | [Variant] | [Props] | [Special behavior] |

### States and Interactions
| Element | State | Behavior |
|---------|-------|----------|
| [CTA Button] | Hover | [Background darken 10%] |
| [CTA Button] | Loading | [Spinner, disabled] |
| [Form] | Error | [Red border, error message below] |

### Responsive Behavior
| Breakpoint | Changes |
|------------|---------|
| Desktop (>1024px) | [Default layout] |
| Tablet (768-1024px) | [What changes] |
| Mobile (<768px) | [What changes] |

### Edge Cases
- **Empty state**: [What to show when no data]
- **Long text**: [Truncation rules]
- **Loading**: [Skeleton or spinner]
- **Error**: [Error state appearance]

### Animation / Motion
| Element | Trigger | Animation | Duration | Easing |
|---------|---------|-----------|----------|--------|
| [Element] | [Trigger] | [Description] | [ms] | [easing] |

### Accessibility Notes
- [Focus order]
- [ARIA labels needed]
- [Keyboard interactions]

If Connectors Available

If ~~design tool is connected:

  • Pull exact measurements, tokens, and component specs from Figma
  • Export assets and generate a complete spec sheet

If ~~project tracker is connected:

  • Link the handoff to the implementation ticket
  • Create sub-tasks for each section of the spec

Tips

  1. Share the Figma link — I can pull exact measurements, tokens, and component info.
  2. Mention edge cases — "What happens with 100 items?" helps me spec boundary conditions.
  3. Specify the tech stack — "We use React + Tailwind" helps me give relevant implementation notes.

Frequently asked questions

What does the Design Handoff AI skill do?

Generate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interaction states, responsive breakpoints, edge cases, and animation details.

Why use Design Handoff on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/knowledge-work-plugins/tree/main/design/skills/design-handoff. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Design Handoff?

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 Design Handoff?

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

Is the Design Handoff AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 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 👇