agentleFS
freskhufreskhu/genesis/.claude/skills/handoff/SKILL.md

handoff

Skill5 starsChanged 6 months agoApache-2.0View on GitHub

Package shaped context -- plans, decisions, project state -- into a structured handoff document for another AI agent, your future self, or a coworker. Use when user mentions 'handoff', needs to transfer context between sessions, or wants to package project state for someone else.

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 47 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 59 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 105 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 101 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 62 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 4

    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:

    Do NOT display what you gathered.

    line 26
  2. Distinctive:

    Check for active tasks, plans, or project state.

    line 32
  3. Distinctive:

    Use the appropriate template based on audience.

    line 41
  4. Distinctive:

    View: Read full handoff, present conversational summary

    line 78

“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

Package shaped context into a structured document for handoff to another agent, future self, or coworker.

Input

Mode: Parse first argument:

  • "list" -- Show all existing handoffs
  • "update [slug]" -- Append to existing handoff
  • "view [slug]" -- Read and summarize existing handoff
  • Anything else / empty -- Create new handoff

Before Starting (Auto-Gather)

Silently gather context:

  1. MemPalace -- python3 scripts/palace.py search "active projects current state" --limit 5
  2. Task state -- SELECT id, title, status, description FROM tasks WHERE status IN ('in_progress', 'pending') ORDER BY updated_at DESC LIMIT 10;
  3. Git state (if in a repo) -- git log --oneline -20, git status, git diff --stat
  4. Directory structure -- ls at repo root

Do NOT display what you gathered. Hold as context.

Mode: Create (Default)

Step 1: Determine context source

Check for active tasks, plans, or project state. If found, use as basis. If not, ask the user to describe the project state.

Step 2: Ask focused questions

  1. "Who is this handoff for?" -- AI agent, myself later, or a coworker
  2. "Anything to add beyond what's in the context?" -- gotchas, failed approaches, constraints

Step 3: Generate the handoff

Use the appropriate template based on audience. Save to MemPalace and optionally to a file.

See examples/ for complete handoff examples.

Templates

AI Agent Template

Optimize for an agent to pick up and work immediately with zero additional context.

Sections: Summary, Project Context, The Plan, Key Files (table), Current State (Done/In Progress/Not Started), Decisions Made (with reasoning), Important Context (gotchas), Next Steps (priority-ordered with acceptance criteria), Constraints.

Self/Later Template

Optimize for fast context recovery -- "where was I and what was I thinking?"

Sections: Where I Left Off, The Plan, What's Working, What's Not Working Yet, My Current Thinking, Decisions I've Made, Things I Tried That Didn't Work, Next Time I Pick This Up, Open Questions.

Coworker Template

Optimize for readability -- assume no context on this work.

Sections: TL;DR, Background, The Plan, What's Done, What's Left, Key Decisions, Things to Watch Out For, Where to Get Help.

Storage

Save handoffs to MemPalace for retrieval across sessions:

python3 scripts/palace.py add --wing ai_team --room protocols --hall hall_advice --content "[handoff content]"

Also save the handoff as a file in the right outbox/ subfolder, named <date>-<slug>-handoff.md. The file on disk is the resume artefact (see .claude/protocols/checkpoint.md). Do not write checkpoint JSON into tasks.description: resuming never went through it.

Mode: List / Update / View

  • List: Query MemPalace for handoff entries, display as table
  • Update: Find existing handoff, append new context section
  • View: Read full handoff, present conversational summary

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.