claude-code-handoff

Parse Claude Code JSONL session logs to generate HANDOFF.md documents.

248|30|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/cafe3310/public-agent-skills --skill claude-code-handoff-cafe3310
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-code-handoff
Source: https://github.com/cafe3310/public-agent-skills/tree/main/skills/claude-code-handoff
Command: npx skills add https://github.com/cafe3310/public-agent-skills --skill claude-code-handoff-cafe3310

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill solves the problem of losing development context when a Claude Code session is interrupted, by reconstructing session history and creating actionable handoff information for another Agent.

Core Features & Use Cases

  • Session Analysis: Parses Claude Code JSONL session records to identify conversation history, execution state, errors, and recent work.
  • Context Recovery: Extracts existing HANDOFF.md files or synthesizes new handoff documents containing progress, interruption reasons, and next steps.
  • Use Case: When Claude Code stops because of rate limits or context limits, use this Skill to analyze the previous session and prepare another Agent to continue the unfinished task.

Quick Start

Ask the AI to analyze the specified Claude Code session ID or session JSONL file and generate a HANDOFF.md file for continuing the task.

Frequently Asked Questions about claude-code-handoff

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

FAQPage Schema
How do I recover an interrupted Claude Code session?

To recover an interrupted Claude Code session, this Skill parses your session JSONL logs to extract conversation history and errors, then generates a HANDOFF.md document to resume the task.

What is context transfer for AI agent workflows?

Context transfer for AI agent workflows is the process of extracting development state from previous sessions and synthesizing actionable handoff documents for another Agent to continue the unfinished task.

How do I generate a handoff document from JSONL parsing?

You can generate a handoff document by asking the AI to analyze your specified Claude Code session ID or JSONL file, which extracts progress and interruption reasons to output a HANDOFF.md file.

Can I continue a coding task after hitting context limits?

Yes, you can continue a coding task after hitting context limits by analyzing the previous session logs to diagnose the interruption and preparing another Agent with the recovered workspace metadata.

Do I need Python to extract Claude Code conversation history?

Yes, you need a Python environment to execute the JSONL parsing scripts that extract conversation history, attachments, and workspace metadata from Claude Code session records.

What is the best way to transfer API interrupted tasks to another agent?

The best way to transfer API interrupted tasks is to automate session recovery by analyzing JSONL session records to identify execution state and synthesize actionable handoff information.