agentleFS
lgbarnlgbarn/shipyard/skills/shipyard-handoff/SKILL.md

shipyard-handoff

Skill66 starsChanged 5 months agoMITView on GitHub

Captures session context into .shipyard/HANDOFF.md so the next session can resume without losing progress. Use when the user says "handoff", "save context", or "I'm done for now", or when a long session ends and its state should be recorded.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write .shipyard/HANDOFF.md with exactly these five sections in order:

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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
<!-- TOKEN BUDGET: 80 lines / ~240 tokens -->

Session Handoff

<activation>

When to Use

  • User says "handoff", "hand off", "transfer session", "save context", or "I'm done for now"
  • User is ending a session and wants context preserved for the next session
  • A long work session is wrapping up and state should be recorded

Natural Language Triggers

  • "handoff", "hand off", "transfer session", "save context", "I'm done for now"
</activation>

Overview

Capture the current session's progress into .shipyard/HANDOFF.md so the next session can resume immediately with full context. The orchestrator writes the file directly — this is never delegated to a sub-agent.

I'm using the handoff skill to capture session context.

<instructions>

The Process

Write .shipyard/HANDOFF.md with exactly these five sections in order:

1. Current Task

What was being worked on at handoff time. Be specific: which file, which feature, which plan task.

2. Approach

The strategy or design being followed. Include key decisions already made so the next session doesn't re-litigate them.

3. Tried

What has been attempted and the outcomes — both successes and failures. Include error messages or unexpected behaviors observed.

4. Remaining

Concrete next steps not yet done. List as actionable items, ordered by priority.

5. Open Questions

Unresolved decisions or blockers that need human input or further investigation.

File Format

## Current Task
[What was being worked on]

## Approach
[Strategy and key decisions]

## Tried
[What was attempted and results]

## Remaining
[Concrete next steps]

## Open Questions
[Unresolved decisions or blockers]
</instructions><rules>

Key Principles

  • Orchestrator writes the file — never delegate to a sub-agent; sub-agents frequently fail to write output files
  • File path is always .shipyard/HANDOFF.md relative to the project root
  • All five sections are required — do not omit any section, even if the content is "none"
  • Be concrete — vague handoffs are useless; include file paths, line numbers, error text where relevant
  • After writing, confirm to the user: "HANDOFF.md is ready. The next session will automatically pick it up when it starts."
</rules>

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.