Advai Handoff logo

Advai Handoff

Organization
advai-x
advai-handoff

Persists session handoff notes in `.advai/HANDOFF.md` and restores prior context from that file. Invoke when user wants to record current session progress or resume work in a new session.

Overview

Publisheradvai-x
Repositoryadvai-skills
Skill nameadvai-handoff
Stars
78
Forks
0
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 advai-x on GitHub. Read the source before you install it.

Installation

Install the Advai 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.
    https://github.com/advai-x/advai-skills/tree/main/skills/advai-handoff
  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/advai-x/advai-skills.git /tmp/advai-skills
mkdir -p .claude/skills
cp -r /tmp/advai-skills/skills/advai-handoff .claude/skills/advai-handoff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Advai 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 Advai 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 Advai 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.

Advai Handoff

Use this skill to persist a compact session handoff in the current project and restore that context later from .advai/HANDOFF.md.

When to Invoke

Invoke this skill when the user wants to:

  • Record what has been done in the current conversation for the next agent session
  • Save the current task goal, progress, changed files, validation status, and next step
  • Resume work in a new conversation by reading the previous handoff note first
  • Maintain a lightweight project-local state file instead of relying on long chat history

Do not use this skill for general documentation, changelogs, or long-form project notes.

Handoff File

  • Use exactly one file: .advai/HANDOFF.md
  • Treat the current project directory as the storage scope
  • Create the .advai/ directory if it does not already exist
  • Do not introduce extra handoff files, dated snapshots, or nested handoff directories unless the user explicitly asks for them

Operating Flow

In an active conversation

When the user asks to record or update handoff state:

  1. Read the current .advai/HANDOFF.md if it exists.
  2. Refresh the file with the latest state of the current task.
  3. Keep the note concise, factual, and easy for the next session to scan.

In a new conversation

When the user asks to resume from a previous handoff:

  1. Check whether .advai/HANDOFF.md exists in the current project.
  2. Read it before making assumptions about prior progress.
  3. Summarize the handoff back to the user and continue from the recorded next step.
  4. If the file is missing, say that no prior handoff note was found and continue with normal discovery.

Recommended Template

Use this structure unless the user requests a different format:

markdown
# Handoff

## Goal
- <current objective>

## Completed
- <finished work>

## Changed Files
- `<path>`: <what changed>

## Validation
- <tests run, checks performed, or not run yet>

## Open Issues
- <known gaps, blockers, or follow-ups>

## Next Step
- <the most useful next action>

Writing Guidelines

  • Prefer updating the existing handoff file in place instead of appending repeated session logs.
  • Keep entries specific enough that a new agent can continue without rereading the whole conversation.
  • Include concrete file paths when code or docs changed.
  • Be explicit about validation status, including when checks were not run.
  • Capture unresolved questions only when they materially affect the next step.
  • If the current task direction changed, overwrite stale goals so the file reflects the latest agreed intent.

Reading Guidelines

  • Treat the handoff as working context, not as guaranteed truth.
  • Cross-check the repository state when the handoff mentions changed files, tests, or pending work.
  • If the handoff conflicts with the current user request, follow the newest user instruction and then refresh the handoff file if appropriate.

Example Prompts

  • "Record a handoff for this session."
  • "Update the handoff before we stop."
  • "Read the previous handoff and continue."
  • "Resume from .advai/HANDOFF.md."

Frequently asked questions

What does the Advai Handoff AI skill do?

Persists session handoff notes in `.advai/HANDOFF.md` and restores prior context from that file. Invoke when user wants to record current session progress or resume work in a new session.

Why use Advai Handoff on TypingMind?

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

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

Which AI models can use Advai 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 Advai Handoff?

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

Is the Advai Handoff AI skill free?

Yes. It is published on GitHub by advai-x 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 👇