Score
9.1
/ 10
Installs
372K
Repo Stars
284.8K
Last Updated
1d ago
Quality Ratio
88%
Description
Verified
Language
Shell
First Published
Jul 2026
Summary
The Claude Handoff agent skill likely facilitates the seamless transfer of context, tasks, or conversational state to or from an AI agent utilizing the Claude model. This agent skill is particularly beneficial for developers building multi-agent systems, complex conversational UIs, or workflows that require session persistence or task delegation involving Claude-powered agents. It is a skill with 10K installs, indicating significant adoption within the o-mega.ai ecosystem. Due to the unavailability of the SKILL.md content, specific patterns, commands, or underlying mechanisms for this handoff are not detailed. However, based on its name, it can be inferred to provide instructions or an interface for an agent to cleanly conclude a task and pass relevant information for subsequent processing by another agent or system leveraging Claude's capabilities, or vice versa. Further details regarding its configuration and exact usage are limited without the skill's documentation.
Skill Definition
Write a handoff summary of the current conversation so a fresh agent can continue the work. Save it to the temporary directory of the user's OS, then launch a background agent seeded with it as its prompt: claude --bg --name "<descriptive name>" -- "$(cat <summary file>)". Passing the file keeps the shell from running backticks or expanding $ in the summary. It starts in the current working directory and returns immediately; the user manages it with claude agents.
Always pass -n/--name with a descriptive name (e.g. --name "Fix login bug"); it sets the display name shown in the job list, session picker, and terminal title.
Include a "suggested skills" section in the summary, naming which skills the next agent should call the Skill tool for.
Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information, since the summary becomes the agent's prompt.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.