# Handoff

> Create or update a durable project handoff for the next AI agent/session. Use when ending a coding/research session, switching agents, compressing context, or preparing another Claude/ChatGPT/Codex session to continue the work.

- **Type:** Skill
- **Install:** `agentstack add skill-dgilford-ai-science-toolkit-handoff`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [dgilford](https://agentstack.voostack.com/s/dgilford)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [dgilford](https://github.com/dgilford)
- **Source:** https://github.com/dgilford/ai-science-toolkit/tree/main/skills/handoff

## Install

```sh
agentstack add skill-dgilford-ai-science-toolkit-handoff
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

Create or update `.ai/HANDOFF.md` so the next agent can resume without rereading this conversation.

## Current repo state

```!
git status --short 2>/dev/null || echo "(not a git repo)"
```

```!
git log --oneline -12 2>/dev/null || echo "(no git log)"
```

```!
git diff --stat HEAD 2>/dev/null | head -30 || echo "(no diff)"
```

## Before writing

Read these if they exist: `.ai/HANDOFF.md`, `CLAUDE.md`, `AGENTS.md`. Scan recently modified files for TODO/FIXME markers. Do not invent results for commands that were not run.

Do not duplicate content already captured in durable artifacts (specs, plans, ADRs, issues, commits, diffs, CLAUDE.md). Reference them by path or URL and summarize only what the next agent needs to act. Redact anything sensitive — API keys, tokens, passwords, PII — even though `.ai/` is gitignored.

## Write `.ai/HANDOFF.md`

Create `.ai/` if missing. Append `.ai/` to `.gitignore` if not already present.

Use only the sections that have real content. Skip empty ones.

## Objective

## Next actions

## State

## Decisions

## Scientific context

## Pitfalls

## Open questions

Preserve useful prior content. Remove stale or superseded details. Distinguish facts, assumptions, and recommendations explicitly.

Ask me at most one question, only if it would materially improve the handoff.

## Ship a worklog entry

After `.ai/HANDOFF.md` is written, run the `worklog` skill to capture this session
to its three targets (local `.ai/` mirror, remote server cache, Notion weekly
page). Pass it the session summary and next actions you wrote above so it does not
re-derive them. `worklog` is best-effort by design — it must never block or fail
the handoff.

## Finally

Run the `evolve-claude-md` skill to promote any durable session knowledge into `CLAUDE.md`.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [dgilford](https://github.com/dgilford)
- **Source:** [dgilford/ai-science-toolkit](https://github.com/dgilford/ai-science-toolkit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-dgilford-ai-science-toolkit-handoff
- Seller: https://agentstack.voostack.com/s/dgilford
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.