agentleFS
MithunWijayasiriMithunWijayasiri/dotclaude/skills/handoff-session/SKILL.md

handoff-session

Skill4 starsChanged 18 days agoMITView on GitHub

Use when the user wants to hand off, continue in a new session, or pass the current work to another agent. Compacts the conversation into a handoff document.

3 other projects use a version of this.

Adopted by

Most recently taken up by

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 3 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:

    Keep the doc compact by excluding:

    line 11
  2. Distinctive:

    If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 3 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

Summarise this conversation for a fresh agent to continue. Save to ~/Downloads/ with a descriptive hyphenated filename prefixed by the project name in square brackets, like [Project]-handoff-TICKETID.md or [Project]-handoff-topic.md. Project = repo name from the origin remote URL, else the folder name; cut to 20 characters. If that name already exists, append a timestamp instead of overwriting. If the folder is missing or unwritable, ask for another destination. Report the saved path.

Link to existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) instead of copying their content.

Keep the doc compact by excluding:

  • Exploratory questions ("how does X work?", "explain this code")
  • Cancelled or abandoned work — branches, experiments, approaches that were started but dropped
  • Dead-end debugging — investigation paths that led nowhere
  • Failed attempts — exclude them unless they explain the current state, reveal a constraint, or prevent repeating the same path
  • Tool/command usage details — focus on results, not mechanics
  • Fully resolved issues — exclude them unless the resolution affects future work
  • Off-topic tangents — side discussions unrelated to the main work
  • Redundant iterations — multiple rounds of the same fix/tweak

Use this structure:

Handoff: [Topic]

Context

[1-2 sentences on what we were working on]

Current State

[What's working, what's broken, what's in progress]

  • Mark assumptions and unverified claims explicitly.
  • Record the latest validation status, including failures and checks not run.

Blockers

[Anything stopping progress]

Decisions Made

[Key choices — architectural, trade-offs accepted]

Next Steps

[Prioritized list of concrete actions, including dependencies or conditions when a step cannot start immediately]

Open Questions

[Unresolved decisions for the next agent]

Key Files

[Relevant file paths]

Redact any sensitive information, such as API keys, passwords, or personally identifiable information.

If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

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.