handoff

An agent skill by mattpocock, from mattpocock/skills. Tags: documentation, handoff, multi-agent, workflow.

What it does

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

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add mattpocock/skills --skill handoff

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/productivity/handoff ~/.claude/skills/handoff

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill only asks the agent to summarize an existing conversation into a handoff document and save it in the OS temp directory, not the workspace. The main exposure is limited file writing in a predictable temp location; it does not itself run commands, access networks, or request privileged changes.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	The skill only says to write a handoff document; there are no shell commands, code evaluation, or native scripts in `SKILL.md` or `agents/openai.yaml`.
Network access	0 (none)	No downloading, remote calls, or data exfiltration are specified; it only references existing artifacts by path or URL and writes locally.
Filesystem reach	1 (low)	It writes a file to the OS temp directory (`$TMPDIR`/`/tmp`/`%TEMP%`) instead of the current workspace, so the write is bounded but still outside the project tree.
Secrets & credentials	0 (none)	The skill asks to redact sensitive information and does not request access to keychains, `.env` files, or other secret stores.
Privilege & persistence	0 (none)	There is no sudo use, system configuration, global installation, or service registration in the skill files.
Instruction hijack surface	0 (none)	The instructions do not tell the agent to ignore higher-level rules, follow remote instructions, hide behavior, or adopt a deceptive persona.
Irreversible actions	0 (none)	It does not perform external actions like posting, deploying, merging, paying, or deleting; it only prepares a document for later use.
Transparency	0 (none)	The reviewed files are plain text Markdown/YAML with no binaries, base64 blobs, or runtime-decoded content.

Before installing

Confirm you are comfortable with the agent writing one file into the OS temp directory.
Read `SKILL.md` to verify it only summarizes and redacts, and does not add extra actions.
If your workflow depends on workspace-only changes, note that this skill intentionally writes outside the repo.

Rated 2026-10-16 by an automated review of 2 files from the skill's repository.

Source

Repository: mattpocock/skills (all skills from this repository)
Path: skills/productivity/handoff/SKILL.md
Branch: main
Updated: 2026-10-05

continual-learning — Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
claude-handoff — Hand the current conversation off to a fresh background agent that picks up the work immediately.
automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
orchestrate — Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task.
principle-guard-the-context-window — Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
ralph-loop — Start a Ralph Loop for iterative self-referential development.