agentleFS
mojopolymojopoly/three-loops/skills/handoff/SKILL.md

handoff

Skill0 starsChanged 3 months agoMITView on GitHub

Compact the current session into a handoff document a fresh session (or another person) can resume from cold. Use at the end of a long session with unfinished work, or when handing work to someone else.

191 other projects use a version of this.

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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write for a reader with zero shared context.

    line 53

“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

A fresh session knows nothing you didn't write down. The handoff's job is to transfer state and judgment, not narrative — what is true, what is believed, what is left, and where the traps are.

The one distinction that matters

Separate verified from believed everywhere. "The worker claims the row atomically (verified: drove the race, both orderings)" and "the email path should work (believed: not exercised)" are different classes of fact, and conflating them is how the next session ships the second one.

Structure

# Handoff: <work name> — YYYY-MM-DD

## Goal
One sentence. Plus the one-line status: on track / blocked on X / redirected.

## State
- DONE + VERIFIED: <each item, with how it was verified>
- DONE, NOT VERIFIED: <each item, with what verification is missing>
- IN PROGRESS: <the exact stopping point — file, function, half-written what>
- NOT STARTED: <remaining tickets/steps, in intended order>

## Decisions made (and why)
- <decision>: <the reason, and what was rejected>
Only decisions a resumer might otherwise re-litigate or accidentally reverse.

## Landmines
The expensive discoveries: the API quirk, the config gotcha, the test that
flakes if X. Each one here saves the next session an hour of rediscovery.

## Next actions
Ordered, concrete, first one small enough to start cold:
1. <action — file/command level>
2. ...

## Map
Files touched (with one-line roles), branch name, PR link, relevant
spec/tickets, launch command.

Rules

  • Write for a reader with zero shared context; expand every "it" and "the fix".
  • Landmines and decisions are the highest-value sections — spend the effort there, compress the rest.
  • Durable facts (new domain terms, invariants, volatile external facts) belong in CONTEXT.md or tripwires, not only in the handoff — the handoff is read once; the docs are read every session.
  • Save to docs/handoffs/YYYY-MM-DD-<name>.md, or paste directly into the next session's opening message.

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.