agentleFS
huntiehuntie/skills/handoff/SKILL.md

handoff

Skill0 starsChanged 21 days agoMITView on GitHub

Write a handoff of the current session to vault/handoffs/ so it can be resumed on another machine, under a slug the skill picks. Use only when the user invokes /handoff.

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, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run git -C vault pull --rebase --autostash.

    line 14
  2. Distinctive:

    Write the file with these sections, leaving out any that would be empty:

    line 18
  3. Distinctive:

    Keep it to what the session learned.

    line 28
  4. Very specific:

    Do not add the file to vault/index.md.

    line 29

“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 handoff is for a fresh session on another machine with no chat history. That session gets the vault and the pushed state of each checkout, and nothing else. Write the file so a reader seeing it cold can continue the work without asking what came before.

Takes an optional argument: a slug, or a hint about what to stress.

  1. Run git -C vault pull --rebase --autostash. If vault/handoffs/README.md is missing, copy this skill's templates/README.md there.
  2. Pick the slug: two to five kebab-case words naming the work, not the session (metro-stale-graph-fix, not debugging-session). The file is vault/handoffs/<YYYY-MM-DD>-<slug>.md, dated today. If that path exists from an earlier handoff of the same work, update it in place.
  3. Collect live state for each checkout the session touched: the branch, git status --short, and commits not on the remote (git log @{u}.. or, with no upstream, the branch has never been pushed). In a Sapling checkout, also sl log -r 'draft()' from inside it. None of that travels. List it under Not pushed, then tell the user before writing. Do not commit or push it for them.
    • When commit cloud is set up (.commit-cloud/.git exists at the root) and a touched Sapling checkout has draft stacks, ask the user whether to back them up now with scripts/commit-cloud backup <checkout>, per the commit-cloud skill, so the other machine restores them on its next pull. Run it only on a yes. Note under Not pushed which stacks are backed up and which are not.
  4. Write the file with these sections, leaving out any that would be empty:
    • Goal. One or two sentences on what the work is for, plus a link to the plan or the PR if there is one.
    • State. Where things stand: what is done and verified, and what is in progress. Cite branches, PR numbers, SHAs, and file paths.
    • Checkouts. One line per checkout: projects/<name>, its branch, and the scripts/checkout <owner/repo>@<branch> command that lands on it.
    • Not pushed. From step 3.
    • Decisions. What was chosen in this session and why, including the user's preferences and corrections that apply to this work.
    • Dead ends. What was tried and failed, and why, so the next session does not repeat it.
    • Open questions. Anything waiting on the user or still unknown.
    • Next step. The single most useful concrete action.
    • Resume prompt. One fenced block to paste into the new session. It points to this file and states the next step. Keep it to what the session learned. Anything the code, a plan, or git log already shows gets a link, not a repeat. Leave out secrets and tokens.
  5. Do not add the file to vault/index.md. Commit it on its own as handoffs: Add <slug> (or handoffs: Update <slug>), with the README in the same commit the first time, then push per vault/COMMITTING_POLICY.md.

End with the file path, the resume prompt, and anything listed under Not pushed.

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.