agentleFS
jalbarrangjalbarrang/skills/handoff/SKILL.md

handoff

Skill2 starsChanged 3 months agoMITView on GitHub

Distill the current conversation into a self-contained handoff prompt for a fresh chat. Use when a thread has grown long or is about to be compacted, when switching to a new focused task, or when the user says "hand off", "start a new thread", "carry this over", or "summarize this for a new chat".

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

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:

    If they don't, ask one short question: "What's the next task for the new chat?"

    line 23
  2. Distinctive:

    Offer to edit: After producing the block, let the user tweak the goal or scope before they start the new chat.

    line 63

“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

Compaction is lossy — it shrinks history without knowing what the next task needs. A handoff is the opposite: it extracts exactly what the next task needs and packages it as a prompt you can paste into a fresh chat that has zero prior context.

When to use

  • The current thread is long, slow, or near its context limit.
  • You're pivoting to a related but distinct task ("now do this for teams too", "execute phase one", "check the other call sites").
  • You want a clean chat that still knows the decisions already made.

Input

The user states the goal for the new thread — what they want to do next. If they don't, ask one short question: "What's the next task for the new chat?"

Process

  1. Review the conversation so far: what was built or decided, which files were read or modified, what approach was chosen and what was rejected.
  2. Produce a self-contained prompt for the new thread. It must stand alone — the new chat cannot see this conversation.
  3. Output it in a fenced code block so the user can copy it verbatim. Do not add preamble like "Here's the prompt" — the block is the deliverable.

Output format

## Context
We've been working on <X>. Key decisions:
- <decision 1>
- <decision 2>

Files involved:
- path/to/file1.ts — <what it is / what changed>
- path/to/file2.ts — <what it is / what changed>

Relevant constraints / gotchas:
- <constraint or gotcha discovered along the way>

## Task
<Clear, specific description of what to do next, based on the user's goal.>

Rules

  • Self-contained. Include every decision, file path, and constraint the new thread needs. Assume it knows nothing.
  • Concise but complete. Summarize; don't transcribe. Drop dead ends unless they explain why an approach was rejected.
  • Real paths. List actual file paths that were touched or discussed, with a one-line note on each.
  • Lead with the task. The ## Task section is the point — make it concrete and actionable, not a vague theme.
  • Offer to edit. After producing the block, let the user tweak the goal or scope before they start the new chat.

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.