Skip to content
Back to skills

Handoff

ASecurity

Compact the current conversation into a handoff document for another agent or future session.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 23, 2026
ai-agentsgobashapi

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Scanned October 4, 2026

npx -y skills add juanitourquiza/shipframe --skill handoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Handoff?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Handoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juanitourquiza-handoff/badge)](https://www.skillsdirectory.com/skills/juanitourquiza-handoff)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: handoff
description: Compact the current conversation into a handoff document for another agent or future session.
argument-hint: "What will the next session be used for?"
disable-model-invocation: false
allowed-tools: Read Write Bash mcp__engram__mem_session_summary
---

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 - not the current workspace.

If `.shipframe/memory/index.md` exists in the active repo, check local state with `project-memory-state.sh status <repo-root>`; if it is not `declined`, also use the memory-curator workflow to persist only verified durable task state in one project task note (goal, status, evidence, next steps, source paths). Do not copy the conversation/transcript. Project-memory opt-in permits local curation only, never publication. Keep the temporary handoff as the local fallback; Engram remains optional and is never synced.

If Engram's `mem_session_summary` tool is available, save the same concise handoff using its required Goal / Instructions / Discoveries / Accomplished / Next Steps / Relevant Files structure. Engram is optional: always preserve the local handoff as the fallback, and never install or configure memory tooling.

Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.

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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.