Catalog
mattpocock/handoff

mattpocock

handoff

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

NewUpdated Oct 7, 2026

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.

Files2
2 files · 1.2 KB

Select a file to preview

Overall Score

78/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

88

Quality

72

Clarity

82

Completeness

68

Summary

A compact skill that instructs an agent to summarize the current conversation into a handoff document for another agent to continue. The skill writes to OS temporary directories, includes sensitive data redaction guidance, and directs agents to reference external artifacts and suggest follow-up skills. It is designed to bridge agent-to-agent transitions with minimal state loss.

Detected Capabilities

file writetemporary file creationdata summarizationsensitive data redactioncross-agent communication

Trigger Keywords

Phrases that agents use to match this skill to user intent.

agent handoffconversation summarysession continuationhand off to agentnext agent context

Risk Signals

INFO

Write to OS temporary directory ($TMPDIR, /tmp, %TEMP%)

SKILL.md body
INFO

Redaction of sensitive information (API keys, passwords, PII)

SKILL.md body
INFO

Cross-agent handoff with skill references

SKILL.md body

Use Cases

  • Hand off long-running conversations between agents
  • Summarize progress for a fresh agent session
  • Maintain context across multiple agent invocations
  • Reduce redundant re-work in multi-step projects
  • Document suggested skills for continuation

Quality Notes

  • Skill is tightly scoped to a single, well-defined purpose: conversation handoff
  • Clear security guidance on redacting sensitive information before handoff
  • Good practice of referencing external artifacts rather than duplicating content
  • Instructs agent to suggest follow-up skills, enabling continuity
  • Uses standard OS temp directories appropriately to avoid polluting workspace
  • Minimal scope and clear boundaries make this low-risk
  • No supporting examples or templates provided — agents must infer handoff document format
  • No guidance on what constitutes 'sensitive information' beyond API keys, passwords, and PII
  • No error handling specified (e.g., what if temp directory is unavailable)
  • Argument handling is flexible but could benefit from examples
Model: claude-haiku-4-5-20251001Analyzed: Oct 7, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v1.2

    Content updated

    ✦ AIClarifies temporary directory paths: adds explicit environment variable and fallback references ($TMPDIR on Unix, %TEMP% on Windows).

    2026-10-07

    LATEST
  2. v1.1

    Content updated

    ✦ AIClarifies suggested skills section to name which skills the next agent should call, and adds OpenAI config artifact.

    2026-09-09

    View This Version
  3. v1.0

    2026-06-30

    View This VersionInitial version

Use mattpocock/handoff in your dev environment

Command Palette

Search for a command to run...