agentleFS
jpc4729jpc4729/setup/skills/my-skills/handoff/SKILL.md

handoff

Skill0 starsChanged 5 days agoMITView on GitHub

Summarize the current conversation into a handoff document and a kickoff prompt when the user asks to transfer work to another session.

192 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

2 rules. 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use only when the user asks for a handoff.

    line 10
  2. Distinctive:

    If relevant skills or guides are known, list their names, locations, and purpose as optional resources.

    line 24

“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

Use only when the user asks for a handoff. Produce two artifacts in order. If the user gives a focus for the next session, tailor both artifacts to it.

The handoff must work with any model, harness, or tool set. Describe the work and required capabilities without prescribing a model, provider, tool API, or invocation syntax. Record task-specific tools and commands as context and evidence; do not assume the next session has them, shared files, conversation history, or persistent state.

1. Handoff document

Write it so a new session can continue the work. If file writing is available and permitted, save a Markdown file in the operating system's temporary directory and report its path. Never save it in the current workspace. Otherwise, print the full document in the response. If the next session cannot access a saved file, tell the user to attach or paste its contents.

  • First reach a safe point: finish the current step or undo it, so no file is left half-edited. Record what is still broken.
  • State the objective, scope, constraints, and definition of done. Record pending questions and approvals; the handoff does not grant new permissions.
  • State what is done, what remains, and what is blocked. Include the checks actually run and their results, with commands when applicable. Mark unverified claims and checks not run.
  • Record relevant working state, such as the repository, branch, changed files, and unfinished operations. Explain what must be checked again before work resumes.
  • Reference existing artifacts (requirements, plans, decisions, issues, commits, diffs) by path or URL. Avoid copying whole artifacts, but include the facts needed to continue when the destination cannot access them. Identify required material that must be transferred.
  • Record failed approaches ("tried X, failed because Y") and decisions with their reasons, so the next session does not repeat rejected approaches.
  • If relevant skills or guides are known, list their names, locations, and purpose as optional resources. State the required work directly so it does not depend on those resources or a skill system.
  • List remaining tasks in dependency order and size each by complexity: S, M, L, or XL. Do not assume delegation is available or authorized.
  • Redact sensitive information (API keys, passwords, personal data).

2. Kickoff prompt

Print a single fenced code block, ready to copy into the next session. Keep it short and avoid repeating details from the handoff document.

  • Open with the action: Read <handoff path>, then ... when the file will be accessible, or Read the attached or pasted handoff, then ... otherwise.
  • State the objective and its definition of done.
  • Include scope constraints and required confirmations only where they apply.
  • Direct the next session to verify the current state and available capabilities, then take the next unfinished step within the user's authorization. If required context or access is missing, ask for it instead of assuming it exists.

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.