Index of every page on this site: llms.txt
All skills
mattpocock avatar

/handoff

@abeeaf9 official
by Matt Pocockmattpocock/skills329k stars
27,654
Run it yourself

Compact the current conversation into a handoff document for another agent to pick up.

Use this Skill: https://skilld.dev/gh/mattpocock/skills/handoff

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈24 tokens for metadata: the name and description. ≈182 when used: this file. ≈36 more on demand in 1 file.

How this Skill uses context

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

This Skill turns off automatic use in Claude Code. Its description stays out of the automatic Skill list by default.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS ($TMPDIR, else /tmp; %TEMP% on Windows) - not the current workspace.

Include a "suggested skills" section in the document, 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.

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

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill creates a summary of the current conversation for agent handoff and saves it to the system's temporary directory. It includes safety instructions to redact sensitive information like API keys. As with any skill that processes conversation history, there is a minor risk of indirect prompt injection from data within the conversation.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Signed by skilld at abeeaf9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 months ago
argument-hint
What will the next session be used for?
disable-model-invocation
true
  • Documentation
  • handoff
  • conversation
  • agent
  • context
  • workflow
  • continuation

README badge

README badge for mattpocock/skills/handoff

Compacts the current conversation into a handoff document for another AI agent, saving it to the OS temp directory and including suggested skills. Strips sensitive data like API keys and avoids duplicating content already in artifacts, referencing them instead.

Generated from the current SKILL.md.

Where does the handoff document get saved?
It saves to the temporary directory of the user's OS (e.g., /tmp on Linux/macOS, %TEMP% on Windows), not to the current workspace.
Does this skill redact sensitive information?
Yes. API keys, passwords, and personally identifiable information are redacted from the handoff document.
What happens if there are existing artifacts like PRDs or ADRs?
The skill references them by path or URL instead of duplicating their content in the handoff document.
Does the skill suggest which skills the next agent should use?
Yes. It includes a 'suggested skills' section in the handoff document recommending relevant skills for the continuation.

Generated from the current SKILL.md. These answers refresh after source changes.