handover-manager

Capture ephemeral conversation context for AI session handovers.

Updated Nov 8, 2025
One-click install
npx skills add https://github.com/berad217/human-training --skill handover-manager
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: handover-manager
Source: https://github.com/berad217/human-training/tree/main/skills/handover-manager
Command: npx skills add https://github.com/berad217/human-training --skill handover-manager

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

When collaborating with AI agents on software projects, ephemeral conversation context like active debates, failed approaches, and in-flight issues is lost when the AI's context window fills up or you pause work, forcing new AI sessions to rehash old discussions or miss critical context that was never saved to permanent project files.

Core Features & Use Cases

  • Ephemeral Delta Capture: Records only conversation context not already stored in permanent project files like SPEC.md, DEVLOG.md, and code, avoiding redundant duplication of documented information.
  • Universal AI Compatibility: Works with any AI agent (Claude, GPT, Gemini, etc.) with no tool or platform lock-in.
  • Context Hygiene Enforcement: Includes guardrails to keep handovers lean (under 200 tokens), prune obsolete context, and avoid common anti-patterns like duplicating permanent documentation or leaving stale "zombie" context.
  • Use Case: Midway through a sprint building a new feature, you hit your AI's context limit. Use this skill to generate a handover so the next AI session picks up exactly where you left off, with full context of what was tried, what's still being debated, and what the next immediate steps are.

Quick Start

Ask your AI assistant to use the handover-manager skill to create a context handover when you need to pause work, reset the AI context, or get a fresh perspective on your project.

Frequently Asked Questions about handover-manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transfer AI conversation context when resetting an AI session?

To transfer AI conversation context during a context reset, you can capture ephemeral discussion state like active debates and failed approaches into a lean handover format, allowing the new AI session to resume work without rehashing old conversations.

What is the best way to save unrecorded AI discussion state during software development?

The best way to save unrecorded AI discussion state is to capture only the ephemeral context delta, actively avoiding the duplication of information already stored in permanent project files like SPEC.md, DEVLOG.md, and source code.

Does this AI context handover format work with any AI agent?

Yes, this AI context handover format works universally with any AI agent like Claude, GPT, or Gemini, ensuring there is no tool or platform lock-in when transferring in-flight discussion state to a new session.

How do I prevent bloated AI handovers and avoid duplicating permanent documentation?

To prevent bloated AI handovers and avoid duplicating permanent documentation, apply context hygiene guardrails that prune obsolete context, avoid anti-patterns, and keep the handover format lean under 200 tokens with specific next steps.

When do I need to create a context handover during collaborative software development?

You need to create a context handover when your AI's context window fills up, at natural pause points like sprint ends, or when you need a fresh perspective and must transfer in-flight discussion state to a new AI session.

Why does my new AI session miss critical context from previous conversations?

Your new AI session misses critical context because ephemeral conversation state like active debates and failed approaches is lost when the context window fills up or work pauses, requiring a standardized handover to minimize redundant work.