Skip to content
AI & Agents
Skill

/handoff-spec

Hand a spec that is mid-implementation to another machine or another agent.

BOOST
From plugin
dzhng-skills
1.3k30 skills
Install
$ npx -y skills add dzhng/skills --skill handoff-spec --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/handoff-spec

Context preview

The summary Claude sees to decide when to auto-load this skill.

Hand a spec that is mid-implementation to another machine or another agent.

SKILL.md

handoff-spec.SKILL.md
name: handoff-spec
description: Hand a spec that is mid-implementation to another machine or another agent.
disable-model-invocation: true

Handoff Spec

I'm moving this spec's work to another machine or another agent. The next session starts **cold**: it has the repository and nothing else. It has none of this conversation, none of this machine's files and none of your memory. Leave the spec so that session can carry on as if it had been here.

Collect what this session knows and the spec doesn't yet say, from the discussion and from the work itself, and put it in the spec:

  • what is done, what is half-done and exactly where it stopped, and what is

next;

  • what I decided or corrected along the way, and how I want the work done;
  • calls you made where I was silent, and anything still waiting on me;
  • what is known to be broken or unverified, with what you already found out

about it;

  • anything that lives only on this machine and the next session needs:

unpushed branches, uncommitted work, scratch results worth keeping.

Write it into the spec's own handoff, in place: the spec stays one current account, not a transcript with a new note on top. Then push, so everything the spec points at exists on the remote.

Done when a fresh agent, given only the repository, would pick the same next step you would, and would not repeat a question I've already answered.

Ships withdzhng-skills

AI skills for building software factories. My personal library of domain-agnostic agent skills, reused across every project.

Get the whole plugin
Stats
1,337
Stars
81
Forks
Active
Maintenance
HTML
Language
MIT
License
13h ago
Last commit
3mo ago
Created
5h ago
Added

Repo: dzhng/skills

Other skills on dzhng-skills.