agentleFS
Sign inStart free
rpraharajrpraharaj/ai-engineer/skills/handoff/SKILL.md

handoff

Skill1 starsChanged 16 days agoMITView on GitHub

Write a continuation brief so another person or session can pick up the work — what changed, what is left, how to verify, landmines. Use when stopping mid-task, switching agents, ending a session, or the user says handoff, wrap up, or continue later.

  • Reads credentials

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

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

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 3

    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:

    Leave a brief another session can trust.

    line 12
  2. Distinctive:

    Read AGENTS.md if present.

    line 14
  3. Distinctive:

    If you did not run a command, write unverified, not "probably passes."

    line 25
  4. Very specific:

    No secrets in the brief (tokens, .env values).

    line 72

“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

Leave a brief another session can trust. Do not implement more product code. Do not "just finish" a half-done feature unless the user asked to finish, not to hand off.

Read AGENTS.md if present.

Gather from this session (do not invent)

  • Goal and acceptance checks (shape-work if it exists)
  • Files you actually changed (git status, git diff --stat)
  • Commands you ran and their last result
  • Open fails from ready-to-merge, review-change, or a pass
  • Decisions and leftover questions
  • Existing artifacts to point at (spec, ADR, PR) — do not restate them

If you did not run a command, write unverified, not "probably passes."

Write this document

Reply with the brief. Write a file only if the user asked, or if this repo already keeps handoff notes.

# Handoff

## Goal
<one or two sentences>

## State
in progress | blocked | ready for review | done pending merge

## Done
- <behavior or file that is actually finished>

## Not done
- <remaining work, ordered>

## Verify
- Commands: `<exact>` — last result: pass | fail | not run
- Manual: <steps or none>

## Tree
- Branch:
- Uncommitted: yes | no
- Files: <paths>

## Landmines
- Do not touch: <generated paths, fragile areas>
- Secrets / env needed:
- Failed approaches (do not retry blindly):

## Artifacts
- <path or URL> — <what it already holds>

## Next skills
- `<skill-name>` — <why>

Quality

  • Not done is honest. A half-written function is not done.
  • Verify lists the real Test / Lint commands from AGENTS.md when known.
  • Landmines includes anything that wasted time this session.
  • No secrets in the brief (tokens, .env values). Point at the variable name instead. Use <REDACTED> if a value leaked into notes.
  • Next skills are real skill names from this pack (debug, implement-change, ready-to-merge, …), not a host command.

Done

Show the brief. If the user wanted a file, give its path. Stop.

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.

Check your setup, free