Context Handoff for Openclaw

A persistent memory management skill that saves and restores chat sessions and project summaries to local markdown files.

bayllech
v0.1.2
Mar 18, 2026
0
940
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install context-handoff

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install context-handoff using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Context Handoff?

Context Handoff is a specialized utility within the Openclaw Skills ecosystem designed to bridge the gap between AI chat sessions. It allows developers to save the current state of a conversation or a project's progress directly to local storage, ensuring that critical information is never lost when switching accounts, clearing sessions, or restarting a workspace.

By decoupling context from the ephemeral chat window history, this skill enables a robust "handoff" mechanism. Whether you are moving between different LLM providers or simply picking up a project after a break, Context Handoff provides a structured way to resume work with full situational awareness of previous decisions, key files, and pending tasks.

Context Handoff Use Cases

  • Switching between different AI accounts or API keys without losing progress.
  • Resuming complex multi-step coding projects across different days.
  • Saving a project summary to quickly onboard a new AI agent into an existing codebase.
  • Maintaining a persistent record of architectural decisions and next steps outside of the chat history.

How Context Handoff Works

  1. The user triggers a save command for either a specific session slot or a named project.
  2. The skill generates a structured Markdown summary of the current discussion, including key decisions, completed tasks, and upcoming steps.
  3. Data is written to local directories under the Openclaw workspace (either in sessions or projects folders).
  4. When restoration is requested, the skill reads the file mtime to find the most relevant context and parses the Markdown content.
  5. The AI agent summarizes the restored state for the user, allowing for an immediate return to productivity.

Context Handoff Setup

To use this within the Openclaw Skills framework, ensure your workspace directory is initialized:

mkdir -p /root/.openclaw/workspace/handoffs/sessions/
mkdir -p /root/.openclaw/workspace/projects/

The skill will automatically manage file creation within these paths when you issue save commands.

Context Handoff Data Schema & Taxonomy

The skill organizes data into two primary taxonomies using Markdown files:

Feature File Path Key Metadata
Session Context handoffs/sessions/<slot>.md Slot name, Save time, Discussion topic, Current decisions
Project Summary projects/<project-name>.md Project goals, Progress, Key files, Risks, Next steps

Files are sorted by modification time (mtime) to ensure the most recent updates are always prioritized during retrieval.

Context Handoff Advanced Features

  • Named Slot Management: Manually assign names like main-chat or debug-session to organize multiple concurrent workflows.
  • Structured Recovery: Instead of raw text dumps, it provides condensed summaries focused on actionable items like commands and file paths.
  • Automatic Directory Resolution: Creates necessary folder structures on-the-fly and handles file overwrites to prevent clutter.
  • Metadata-Driven Sorting: Lists saved contexts based on actual file system timestamps rather than just alphabetical order.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*