Skills › Skills For Real Engineers › claude-handoff

claude-handoff

skill · 18 lines · MIT · skills/in-progress/claude-handoff/SKILL.md

The facts

Its description

Hand the current conversation off to a fresh background agent that picks up the work immediately.

The description the agent reads to decide when to use it.

From its settingsline 3

When it starts

This skill is not picked from conversation: it sets disable-model-invocation, so the agent never selects it from its name and description alone — the user starts it directly as a command, optionally passing an argument describing what the next session will focus on.

A model's summary of when it is used.

A model's reading

Who can start it

Only you

Only you can start it. The agent never picks it on its own.

From its settingsline 5

What it takes when started

What will the next session be used for?

What to type after its name when you start it.

From its settingsline 4

Licence

MIT, from LICENSE

The terms its author shares it under, which let it be shown here.

From the repositorylicence text

Other files in this skill (1) Close

agents/openai.yaml

The text

Open on GitHub

1---

2name: claude-handoff

3description: Hand the current conversation off to a fresh background agent that picks up the work immediately.

4argument-hint: "What will the next session be used for?"

5disable-model-invocation: true

6---

8Write 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`.

10Always 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.

12Include a "suggested skills" section in the summary, naming which skills the next agent should call the Skill tool for.

14Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.

16Redact any sensitive information, such as API keys, passwords, or personally identifiable information, since the summary becomes the agent's prompt.

18If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.

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.

Raw lines 1 to 18

From mattpocock/skills at 4ae2317, 2026-10-31. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.