agentleFS
Sign inStart free
sreejithramansreejithraman/SreeStack/skills/handoff/SKILL.md

handoff

Skill1 starsChanged 16 days agoMITView on GitHub

Transfer or resume unfinished work through a compact handoff document.

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

Create a free account to mount
Files
SKILL.md

Transfer operational state, not a transcript summary. If the user asks for a handoff, write a document in the OS temporary directory, outside the workspace. Tailor it to the next session the user describes.

For T3 work, consult the current thread's history through t3_thread_read or scoped t3_thread_search when needed to recover decisions and task receipts. Record relevant thread/task IDs, ownership, and any still-running work in the note. The portable note remains the handoff artifact; use app history as evidence rather than copying a transcript. A handoff does not launch a new conversation.

Record the goal and definition of done; branch, worktree, and relevant commit or PR; what is complete and verified; what is pending or blocked; decisions that still constrain the work; exact artifact paths; and the first useful action on resume. Distinguish work saved on disk from an uncommitted or unpushed state. Include a short suggested-skills section only for skills the next agent will need. Point to specs, plans, ADRs, issues, diffs, and evidence rather than copying them. Redact secrets and personal data.

If the user asks you to resume from a handoff, read its linked artifacts and reconstruct the current branch, worktree, and external state before acting. Compare completed work with pending work and name the resume point. Treat the handoff as orientation: verify inherited claims that affect the next action against current code, artifacts, or remote state. Continue the requested work without redoing completed steps whose evidence still applies.

Creating a handoff does not itself authorize a commit, push, PR, or pause. Before finishing, check that the next agent can act from the note and its linked artifacts without this conversation. Report the document path and any state that could not safely be captured.

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