Generates a clipboard-ready prompt you can paste into a fresh Claude session when you want another agent to pick up a task. Strips out filesystem paths and replaces them with portable anchors like repo URLs, branch names, issue links, and exact error text so the handoff works regardless of where the receiving agent starts. The prompts explicitly ask the new agent to review independently first, decide if the task is still valid, and report findings before making changes. Useful when you're handing off mid-investigation, delegating a bug fix, or want a second agent to validate an approach without inheriting your assumptions. Keeps you from accidentally leaking workspace-specific details or writing command-only work orders that skip the thinking step.
npx -y skills add openclaw/agent-skills --skill handoff --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot