Gdd Handoff

Community

hegemonart

gdd-handoff

Handoff-first entry point that initializes a cycle from a Claude Design handoff bundle (URL, ZIP, HTML, PDF, or PPTX), skips the explore/plan stages, and routes straight to post-handoff verify. Thin wrapper over the Handoff Routing logic in the root pipeline router and the claude-design connection. Use when a Claude Design bundle was sent or dropped into the project and you want to implement and verify it without re-running discovery, or when arguments start with handoff or contain --from-handoff.

Overview

Publisher	hegemonart
Repository	`get-design-done`
Skill name	`gdd-handoff`
Stars	3
Forks	1
Bundled files	Instructions only
License	MIT
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 hegemonart on GitHub. Read the source before you install it.

Installation

Install the Gdd 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.
https://github.com/hegemonart/get-design-done/tree/main/scripts/skill-templates/handoff
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.

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/hegemonart/get-design-done.git /tmp/get-design-done
mkdir -p .claude/skills
cp -r /tmp/get-design-done/scripts/skill-templates/handoff .claude/skills/gdd-handoff

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

Use it in TypingMind

Enable Gdd 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 Gdd 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 Gdd 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.

gdd-handoff

Initialize a design cycle from a Claude Design handoff bundle, then route to verify in post-handoff mode. This skill is the named home for the inline Handoff Routing block in the root pipeline router (SKILL.md); invoking {{command_prefix}}handoff <path> runs the same sequence. See connections/claude-design.md for bundle formats and parsing rules.

Role

You do no design work yourself. You resolve a handoff bundle, seed .design/STATE.md for a handoff-sourced cycle, dispatch the synthesizer + discussant agents, and hand off to the verify skill. Stages scan/discover/plan are skipped by design - a handoff bundle replaces them.

Invocation Contract

Input: a bundle path or hosted URL as the argument, OR --from-handoff <path>, OR a previously-recorded handoff_path in .design/STATE.md.
Output: a handoff-sourced .design/STATE.md and a routed call to Skill("get-design-done:verify", "--post-handoff").

Procedure

1. Resolve the bundle path

{{command_prefix}}handoff <path> -> bundle path is the argument.
--from-handoff <path> -> bundle path is the value after the flag.
A https://api.anthropic.com/v1/design/h/<hash> URL in the arguments -> treat as the bundle.
None of the above -> read handoff_path from .design/STATE.md. Still absent -> error: "Provide a bundle path: {{command_prefix}}handoff ./path/to/bundle.html".
For a file path: verify the file exists; if not, error "Bundle not found at ".

2. Initialize STATE.md

If .design/STATE.md does not exist, copy reference/STATE-TEMPLATE.md to .design/STATE.md.
In <position> set: handoff_source (per the bundle format - see the claude-design connection table), handoff_path: <resolved path>, skipped_stages: scan, discover, plan, status: handoff-sourced, stage: verify.
In <connections> set claude_design: available; leave every other connection unchanged.

3. Spawn the synthesizer in handoff mode


Task("design-research-synthesizer", """
mode: handoff
handoff_path: <resolved bundle path>
state_path: .design/STATE.md
""")

Wait for ## SYNTHESIZE COMPLETE.

4. Spawn the discussant in from-handoff mode


Task("design-discussant", """
<mode>--from-handoff</mode>
<required_reading>.design/STATE.md</required_reading>
""")

Wait for ## DISCUSS COMPLETE. This step surfaces every (tentative) decision for user confirmation; do not skip it - implementing against unconfirmed inferred values is the primary handoff failure mode.

5. Route to verify


Skill("get-design-done:verify", "--post-handoff")

Verify relaxes the DESIGN-PLAN.md prerequisite for handoff flows and adds a Handoff Faithfulness section to DESIGN-VERIFICATION.md.

6. Optional write-back (post-verify)

After verify completes without FAIL-level gaps, check STATE.md <connections> for figma:. If figma: available, offer to write implementation status back to Figma (annotates frames + Code Connect mappings) via agents/design-figma-writer.md with mode: implementation-status. Skip silently when figma is not_configured or unavailable.

Do Not

Do not run scan, discover, or plan - the bundle replaces them.
Do not promote PDF/PPTX-sourced decisions to (locked) without explicit user confirmation.
Do not commit raw extracted bundle files - only persist decisions to STATE.md.

Cross-references

connections/claude-design.md - bundle formats, field catalogue, confidence tagging.
Root SKILL.md ## Handoff Routing - the inline routing this skill wraps.
get-design-done:verify (--post-handoff) - the stage this skill routes to.

Frequently asked questions

What does the Gdd Handoff AI skill do?

Why use Gdd Handoff on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hegemonart/get-design-done/tree/main/scripts/skill-templates/handoff. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gdd 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 Gdd Handoff?

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

Is the Gdd Handoff AI skill free?

Yes. It is published on GitHub by hegemonart 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

Subagent Driven Development

obra

CommunityPopular

Use when executing implementation plans with independent tasks in the current session

Unified Memory

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer…

Draw Your Font

Turn a handwriting photo into an installable TTF font.

Adversarial Ux Test

Roleplay a hostile user to find and triage UX pain points.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

gdd-handoff

Role

Invocation Contract

Procedure

1. Resolve the bundle path

2. Initialize STATE.md

3. Spawn the synthesizer in handoff mode

4. Spawn the discussant in from-handoff mode

5. Route to verify

6. Optional write-back (post-verify)

Do Not

Cross-references

Frequently asked questions

Related AI Skills

Set up your own AI workspace now