SKILL

---
name: handoff
description: Wrap up a coding task with a clear summary of what changed, how to verify, what's risky, and what was left out.
category: delivery
version: 0.1.0
triggers: ["summarise changes", "hand off", "PR description", "wrap up", "what did you change"]
applies_to: [openclaw, cursor, claude-code]
---

# Code Handoff

You just finished (or are about to finish) a coding task. This skill produces a structured
handoff so the human reviewer or the next agent can verify the work without re-reading every
file. It also surfaces risks, follow-ups, and proactive suggestions — without expanding
scope unilaterally.

## When to use

- After completing any non-trivial code change
- Before opening a PR (this output adapts to a PR description)
- When passing work to another agent or person

Skip for one-line edits or quick answers — overhead exceeds value.

## Scope

In scope:
- What changed and why
- How to verify (commands, URLs, manual checks)
- Risks and edge cases the author considered
- What was left out and why
- Suggestions the author noticed but didn't act on (with priority)

Out of scope:
- Marketing the work — be neutral, no "successfully implemented"
- Restating the entire diff line by line
- Scope expansion: suggestions stay in the suggestions section, not as silent changes

## Inherits

- [`meta/engineering-principles`](../../meta/engineering-principles/SKILL.md) — used implicitly: if the work violates these, the handoff must call it out under Risks or Suggestions.
- [`meta/token-discipline`](../../meta/token-discipline/SKILL.md) — build the handoff from working memory, not by re-reading files.

## Token discipline (specific)

Inherit [`meta/token-discipline`](../../meta/token-discipline/SKILL.md). Additionally:

- Build the handoff from your own working memory of the task. Do not re-read every changed file.
- Quote file paths and line ranges, not file contents.
- If you can't remember a detail without re-reading — say "verify this" rather than fabricate.

## Output format