Skip to content
Back to skills

Handoff Session

ASecurity

Use when the user wants to hand off, continue in a new session, or pass the current work to another agent. Compacts the conversation into a handoff document.

  • 4 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 15, 2026
ai-agentsdebuggingapi

Works with

  • api

Security analysis

A100/100

Scanned October 15, 2026

npx -y skills add MithunWijayasiri/dotclaude --skill handoff-session --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Handoff Session?

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

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

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-session
description: Use when the user wants to hand off, continue in a new session, or pass the current work to another agent. Compacts the conversation into a handoff document.
argument-hint: "What will the next session be used for?"
---

Summarise this conversation for a fresh agent to continue. Save to ~/Downloads/ with a descriptive hyphenated filename, like handoff-TICKETID.md or handoff-topic.md. If that name already exists, append a timestamp instead of overwriting. If the folder is missing or unwritable, ask for another destination. Report the saved path.

Link to existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) instead of copying their content.

Keep the doc compact by excluding:
- Exploratory questions ("how does X work?", "explain this code")
- Cancelled or abandoned work — branches, experiments, approaches that were started but dropped
- Dead-end debugging — investigation paths that led nowhere
- Failed attempts — exclude them unless they explain the current state, reveal a constraint, or prevent repeating the same path
- Tool/command usage details — focus on results, not mechanics
- Fully resolved issues — exclude them unless the resolution affects future work
- Off-topic tangents — side discussions unrelated to the main work
- Redundant iterations — multiple rounds of the same fix/tweak

Use this structure:

# Handoff: [Topic]

## Context
[1-2 sentences on what we were working on]

## Current State
[What's working, what's broken, what's in progress]

- Mark assumptions and unverified claims explicitly.
- Record the latest validation status, including failures and checks not run.

## Blockers
[Anything stopping progress]

## Decisions Made
[Key choices — architectural, trade-offs accepted]

## Next Steps
[Prioritized list of concrete actions, including dependencies or conditions when a step cannot start immediately]

## Open Questions
[Unresolved decisions for the next agent]

## Key Files
[Relevant file paths]

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.

Comments

Loading comments…

Newsletter

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