agentleFS
jcurbelojcurbelo/agent-seed/.claude/skills/handoff/SKILL.md

handoff

Skill8 starsChanged 8 months agoMITView on GitHub

Compact the current conversation into a handoff document so a fresh agent can continue the work. Use when the conversation is approaching context limits or you want to hand off to a new session.

191 other projects use a version of this, 84 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-mapping, setup-ts-deep-modules and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 93 projects that use this

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 87 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 51 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 54 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a handoff document summarising the current conversation so a fresh agent can pick up the work.

    line 8
  2. Very specific:

    If multiple handoffs land on the same day, suffix with a number: 2026-05-20-auth-refactor-1.md, 2026-05-20-auth-refactor-2.md.

    line 16
  3. Distinctive:

    If git status shows uncommitted work, list those files in State so the next agent doesn't lose them.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 172 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/handoff - Conversation Handoff Document

Write a handoff document summarising the current conversation so a fresh agent can pick up the work.

Where to save

Always save inside the repo at handoffs/YYYY-MM-DD-<slug>.md. Never write to /tmp or any OS tempdir — handoffs are part of the repo's history and must be committed.

The slug is a short kebab-case description of what the next session will work on (e.g. auth-refactor, bug-investigation-payment).

If multiple handoffs land on the same day, suffix with a number: 2026-05-20-auth-refactor-1.md, 2026-05-20-auth-refactor-2.md.

Template

# Handoff: <one-line summary>

**Date:** YYYY-MM-DD
**Next session focus:** <from the user's argument, or "general continuation">

## What we were doing

<2-4 sentences. What problem, what was attempted, where we landed.>

## State

- **Branch:** <git branch if relevant>
- **Open files / draft locations:** <list of paths being edited>
- **External references:** <issue links, PR URLs, ticket IDs — as clickable markdown links>

## Key findings

<Bullet list of anything substantive learned this session that isn't already captured in artifacts. Reference artifacts by path/URL — don't duplicate.>

## What's blocking / what's next

<What the next agent should do first. Be concrete.>

## Suggested skills

<List of `/skill-name` invocations the next agent should consider. Examples:
- `/standup` to re-orient on priorities
- `/grill-me` if the next step needs alignment
- `/write-a-skill` if a recurring need surfaced
>

## Redacted notes

<Anything sensitive that was in conversation but shouldn't land in the repo. Mark as `[REDACTED]` with a pointer to where the original lives.>

Rules

  • Never duplicate content already in plans, ADRs, issues, commits, diffs. Reference by path/URL.
  • Redact API keys, passwords, tokens, customer PII, anything sensitive.
  • Always commit the handoff file before ending the session. A handoff that's not committed isn't a handoff.
  • If git status shows uncommitted work, list those files in State so the next agent doesn't lose them.

Commit message

chore: handoff <YYYY-MM-DD> <slug>

Adapted from mattpocock/skills/productivity/handoff. See memory/external-skill-sources.md for full attribution.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.