Steward Handoff

Organization

vibevm

steward-handoff

Prepare, receive, cancel, inspect, or recover an explicitly owner-requested same-machine formal central handoff while preserving the complete plan and acceptance boundary. Never use for ordinary timeout, crash, compaction, new-chat, or model-change continuation.

Overview

Publisher	vibevm
Repository	`vibevm`
Skill name	`steward-handoff`
Stars	285
Forks	83
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 vibevm on GitHub. Read the source before you install it.

Installation

Install the Steward 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/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-handoff
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/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-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/vibevm/vibevm.git /tmp/vibevm
mkdir -p .claude/skills
cp -r /tmp/vibevm/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-handoff .claude/skills/steward-handoff

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

Use it in TypingMind

Enable Steward 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 Steward 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 Steward 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.

Steward handoff {#root}

@fact:HANDOFF-CENTRAL-ONLY This skill transfers owner-facing central custody, not work to a subagent. It never delegates acceptance. @status:impl/done

@fact:HANDOFF-EXPLICIT-ONLY Invoke this skill only from explicit owner intent to prepare, receive, cancel, inspect or recover a formal central handoff. Ordinary continuation resolves binding, settings, complete plan and tree directly and creates no session, handoff, receipt or takeover document. @status:impl/done

@fact:HANDOFF-CONTEXT-COMMAND Recognise ACCEPT HANDOFF FROM <context-id> / ПРИМИ ХЭНДОФФ ИЗ <context-id>. Resolve exactly one unreceipted, uncancelled offered bundle in that context; if several exist, require an exact handoff id. Read the stored HANDOFF.md—never ask the owner to paste it. An explicit cancelled id reports HANDOFF_CANCELLED. @status:impl/done

Select the operation {#operation}

@fact:HANDOFF-PREPARE Prepare when the owner explicitly requests formal transfer from the current active central writer to another session/model/harness. Verify that no conflicting central writer is live; advisory holder/session metadata alone does not select the outgoing writer. @status:impl/done
@fact:HANDOFF-RECEIVE Receive when an unreceipted offer targets this session. @status:impl/done
@fact:HANDOFF-RECOVER Recover only when the holder is unavailable and the owner explicitly directs repair of an already-open formal handoff in the named context. Stale or mismatched custody outside such an offer is ordinary continuation, not takeover. @status:impl/done

Prepare {#prepare}

@fact:HANDOFF-PREPARE-PROCEDURE Follow spec://org.vibevm.world/multi-user-planning/flows/multi-user-planning/custody-and-handoff#offer: verify the tree; backscan mandate/plan/evidence/artifacts; write the immutable offer, comprehensive HANDOFF.md, and short receive-by-context pointer; refresh and hash handoff, plan and selected goal; set custody to offering; then become repository- and plan-read-only. A summary without the created file and fence is not a handoff. @status:impl/done

@fact:HANDOFF-PREPARE-OUTPUT After sealing, always print exactly: HANDOFF CREATED, context-id: …, handoff-id: …, and receive-command: ПРИМИ ХЭНДОФФ ИЗ …. Printing is allowed after the write fence; never make the owner search ~/.vibe or paste HANDOFF.md. @status:impl/done

Receive {#receive}

@fact:HANDOFF-RECEIVE-PROCEDURE Read all authorities and the complete bundle, verify hashes and repository state independently, enumerate discrepancies, write accepted, accepted-with-exceptions, or rejected receipt, and advance formal custody only for an accepted receipt. Preserve all dirty/worker work as candidate. After the accepted receipt ends the offering fence, refresh goal, print full GOAL.md, then print the exact GOAL-CLAUDE.txt /goal … line separately. Report restored state and wait for the owner before execution. @status:impl/done

Recover {#recover}

@fact:HANDOFF-RECOVER-PROCEDURE Preserve artifacts, verify holder unavailability and the valid open formal offer, record the owner's repair or cancellation direction and observed accepted boundary, then follow the formal protocol's epoch transition. Treat everything after durable project acceptance as candidate. Never delete first or use staleness alone as authority. If no explicit formal offer is open, stop this skill and use ordinary continuation without a takeover record. @status:impl/done

Frequently asked questions

What does the Steward Handoff AI skill do?

Why use Steward Handoff on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.world/multi-user-planning/v1.0.0/vibevm/vibespecs/skills/steward-handoff. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Steward 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 Steward Handoff?

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

Is the Steward Handoff AI skill free?

It is published on GitHub by vibevm. 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

Competitive Report Structure

affaan-m

CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Crosspost

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user…

Deep Research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Steward handoff {#root}

Select the operation {#operation}

Prepare {#prepare}

Receive {#receive}

Recover {#recover}

Frequently asked questions

Related AI Skills

Set up your own AI workspace now