smithery.ai

Agent Handoff

Prepare for the next agent or session by documenting work and leaving codebase in good state

First seen Mar 22, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,431 B
  • docs SUMMARY.md 113 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Agent Handoff

Prepare for the next agent or session by documenting your work and leaving the codebase in a good state.

When to Use

  • At the end of a work session
  • Before switching to a different task
  • When handing off to another developer or agent
  • When context window is getting full

Steps

  1. Commit completed work

- Stage and commit any finished changes - Write clear, descriptive commit messages - Don't leave partial work uncommitted unless necessary

  1. Document work in progress

- Add TODO comments for incomplete work - Update task lists or issue trackers - Note any decisions made and why

  1. Summarize the session

- What was accomplished? - What remains to be done? - Any blockers or issues encountered?

  1. Clean up

- Remove debugging code or console.logs - Delete temporary files - Ensure tests pass (or document why they don't)

  1. Leave notes for next session

- What should the next agent focus on? - Any context that would be helpful? - Links to relevant documentation or issues

Notes

  • Leave the codebase in a working state when possible
  • Don't leave uncommitted debugging code
  • Be explicit about what's done vs what's in progress
  • The next agent has no context - write notes accordingly