Preparing Design Handoff

Organization

bitwarden

preparing-design-handoff

Prepare a Bitwarden design handoff — the Figma file in Ready-for-Dev state and the Jira state transitions that go with it. The end-of-In-Design gate / checklist.

Overview

Publisher	bitwarden
Repository	`ai-plugins`
Skill name	`preparing-design-handoff`
Stars	149
Forks	19
Bundled files	Instructions only
Links	Skill source Repository

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 bitwarden on GitHub. Read the source before you install it.

Installation

Install the Preparing Design Handoff AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-design-tools/skills/preparing-design-handoff

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-design-tools/skills/preparing-design-handoff .claude/skills/preparing-design-handoff

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Preparing 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 Preparing 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 Preparing 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.

Preparing a Design Handoff

This skill is the end-of-In-Design gate. Engineering relies on a consistent set of signals to know a design is ready to pick up. A handoff missing any of those signals creates downstream questions and slows the epic into development.

The handoff is two things, not one

A handoff is finished when both are in place:

The Figma file in Ready-for-Dev state. Final designs grouped on a single page, with sections named to match the engineering stories that will consume them. Sections marked "Ready for Dev" in Figma. User-visible strings (toasts, error messages, form verifications, email body copy) annotated on the frames. Annotated prototype available.
The Jira state aligned. Figma file linked in the Epic's "Design" field, sections marked Ready for Dev in Figma, and the EM transitions the Epic to Ready for Dev. The full choreography is in navigating-design-jira-process.

If either is missing, the handoff isn't done.

Prep checklist (before declaring handoff)

The product initiative or PRD page exists and is current.
The engineering Epic exists in Jira and the designer is or has been assigned to it.
Designs have been through critique at 30%, 60%, and 90% and the 90% review has been addressed.
Real-user testing has happened where applicable (this is what 90% is for).
The Figma file's final-designs page is curated — no scratch pages, no unused frames in the Ready-for-Dev surface.
All user-visible strings are annotated in Figma alongside the frames they apply to.

If any item is missing, surface that before declaring the handoff ready — handoff is not the moment to discover the 90% review never happened.

Figma readiness check

Before marking sections Ready for Dev, confirm:

Sections aligned to stories. Each named section maps to a single engineering story. Avoid sections that span stories or stories that span multiple sections.
Tokens are library-bound. No raw hex values where a design-system variable exists. Compose using-figma with get_variable_defs to verify.
Strings annotated. Every user-visible string — button labels, error messages, toasts, empty states, helper text — is present in the Figma frames or annotations.
Edge cases covered. Empty, error, partial-success, offline, and premium-gated states exist on the relevant frames (or are explicitly out of scope and noted).

Composing with other skills

using-figma. Use get_metadata to confirm the Ready-for-Dev sections exist with the expected names; use get_variable_defs to confirm tokens are library-bound rather than raw values; use search_design_system if a component in the design is suspiciously close to one that already exists.
navigating-design-jira-process. The Jira moves that go with handoff — link Figma to Epic "Design" field, mark Ready for Dev in Figma, EM transitions Epic — live there.
content-style-guide. Walk every annotated string through the style guide before declaring handoff. Toasts, errors, and form-verification text are the highest-leverage place to catch content-style issues before engineering localizes them.

Common omissions to catch

Figma file with no Ready-for-Dev marks. Engineering can't find what's final. This is the most-skipped step.
Sections not aligned to stories. Each story should map to a Figma section whose content is only that story. Mismatch creates ambiguity at review time.
Missing string annotations. Engineering will ask for strings the moment they pick the Epic up. Annotate them in Figma alongside the frames before declaring handoff — don't defer to engineering to invent copy.
Edge states absent. Empty, error, partial-success, offline, premium-gated. If they're out of scope, say so explicitly on the frames or in the dev-support comments.

Output format

When asked to help prep a handoff:

Prep checklist — what's in place, what's missing.
Figma readiness check — section-to-story alignment, token binding, string annotations, edge states.
Jira moves — the specific status transitions and Figma links to apply (link to Epic "Design" field, mark sections Ready for Dev, EM transitions Epic). Defer to navigating-design-jira-process for the canonical choreography.

Always end with the explicit go/no-go: is this handoff actually ready?

Frequently asked questions

What does the Preparing Design Handoff AI skill do?

Prepare a Bitwarden design handoff — the Figma file in Ready-for-Dev state and the Jira state transitions that go with it. The end-of-In-Design gate / checklist.

Why use Preparing Design Handoff on TypingMind?

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

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

Which AI models can use Preparing 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 Preparing Design Handoff?

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

Is the Preparing Design Handoff AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. 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

Autoplan

garrytan

CommunityPopular

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

Design Consultation

Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview...…

Design Html

Design finalization: generates production-quality Pretext-native HTML/CSS. (gstack)

Design Shotgun

Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Preparing a Design Handoff

The handoff is two things, not one

Prep checklist (before declaring handoff)

Figma readiness check

Composing with other skills

Common omissions to catch

Output format

Frequently asked questions

Related AI Skills

Set up your own AI workspace now