Skip to content

borghei/Claude-Skills / workflow/handoff

handoff

Unverified

Package in-progress work into a self-contained context doc or a background agent's prompt. Use when handing work off, switching off a task, or delegating to a fresh or background agent.

assets/handoff_template.md

View on GitHub
# Handoff: <short title of the work>

**From:** <name/agent>  **To:** <receiver>  **Date:** <YYYY-MM-DD>
**Assumptions (if drafted without full input):** <none | list>

## Goal & done-state
<2-3 sentences: where this is headed and how we'll know it's finished.>

## Current state
- [x] Done: <…>
- [~] In progress: <…> — <where it stands right now>
- [ ] Untouched: <…>

## Next steps (in order)
1. <verb + file/location + expected outcome>
2. <…>
3. <…>

**Start here →** <the single first action the receiver should take.>

## Decisions already made (don't relitigate)
- <decision> — <one-line why>

## Abandoned paths (tried, ruled out)
- <approach> — <why it failed / was rejected>

## Open questions / risks
- <question or risk> — <owner, if known>

## Key locations
- Branch / PR: <…>
- Files: <…>
- Tickets / docs / dashboards: <…>
- People to ask: <…>

<!-- The three sections below are required in background-agent mode, optional otherwise. -->

## Stop and report when
- <condition that means the agent should stop instead of improvising, e.g. a migration is needed, a test outside scope fails, the spec looks wrong>

## Report back
- <where the result goes: a PR, a file path, a comment on the ticket> — <what it must contain>

## Suggested skills
- <skill name> — <the step it covers>
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall