agentleFS
jelbirtjelbirt/LLM-Skill-Build/handoff/SKILL.md

handoff

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

Emit a successor-session briefing from the CURRENT session - exact state left behind, in-flight and promised-but-undone work, open owner gates, honest uncertainties, standing invariants, and orient-first instructions - in one fenced code block. Use whenever the user wants to wrap up, hand off, or continue in a fresh session, says "handoff", "write a handoff", "brief the next session", "I'm about to /clear", or asks what a successor needs to know, even if they don't say "handoff" explicitly. The audience is a successor that starts empty - use session-report instead when reporting back into a session that is still running and already has the project in context.

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

3 rules. 0 are common, 3 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the briefing a successor session needs to continue THIS session's work with zero shared memory.

    line 8
  2. Distinctive:

    Use a four-backtick outer fence if the briefing contains triple-backtick fences.

    line 41
  3. Distinctive:

    After the block, note in 1-2 sentences anything that belongs in the owner's hands rather than the successor's (e.g.

    line 44

“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

Write the briefing a successor session needs to continue THIS session's work with zero shared memory. The audience is a fresh Claude Code session (or the owner pasting into one). Be honest about what is unfinished and uncertain - a flattering handoff is a defective one.

Instructions

  1. Take stock before writing. Re-check reality rather than trusting your own narrative of the session: run git status, git log --oneline -5, and git branch --show-current; list uncommitted files, un-pushed commits, open PRs, and anything created outside git (home-dir files, scratch artifacts) that the successor would not find on their own.
  2. Compose the briefing with these sections, in order:
    • State left behind - branch, HEAD commit, clean/dirty tree, open PRs with status, artifacts created outside git (absolute paths).
    • What was done - completed work, tersely, with where it lives.
    • In flight / promised but undone - anything started, planned, or told to the owner as "will do" that is not finished. Never silently drop these; this section is the whole point of a handoff.
    • Open owner gates - decisions awaiting the owner, marked ⛳, with what each is blocking.
    • Honest uncertainties - things not verified, tests not run, guesses made, or areas where the successor should re-check rather than trust this briefing.
    • Standing invariants - the rules the successor must keep honoring (from the repo's CLAUDE.md/spec plus any session-specific constraints, e.g. who holds the pen on shared mutable state).
    • Orient first - the exact commands and reads the successor should do before writing anything: verify expected HEAD/branch, which docs to read, and "trust commits over docs where they disagree."
  3. Output the entire briefing in a single fenced code block, copy-ready. Use a four-backtick outer fence if the briefing contains triple-backtick fences. Do not write it to a file unless explicitly asked.
  4. After the block, note in 1-2 sentences anything that belongs in the owner's hands rather than the successor's (e.g. an approval only the owner can give).

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.