agentleFS
lutzleonhardtlutzleonhardt/casefile/skills/handoff/SKILL.md

handoff

Skill4 starsChanged 59 days agoMITView on GitHub

Extract relevant context from the current

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

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 7

    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:

    No history, no conversation recap — just the objective.

    line 20
  2. Distinctive:

    Only include files that are NECESSARY for the remaining work.

    line 49
  3. Distinctive:

    If the task requires understanding non-obvious relationships between components, include a brief sketch.

    line 53
  4. Distinctive:

    Only include this if it saves the next session from having to rediscover the architecture.

    line 63
  5. Distinctive:

    Maximum signal density: Every line in handoff.md should save the next session from doing redundant work.

    line 78
  6. Distinctive:

    If a line doesn't directly help with implementation, cut it.

    line 80
  7. Distinctive:

    Do NOT commit handoff.md — it is temporary.

    line 88

“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

Session Handoff

The user's context window is filling up (typically 40-50%). The current task is NOT finished — analysis is done but implementation remains. Create a handoff document that enables a fresh session to continue without re-exploration.

Create handoff.md in the project root.

Document structure:

Background

2-3 sentences: What is the task? What is the goal? No history, no conversation recap — just the objective.

Already Done

What was already implemented in THIS session or earlier. Include concrete code references (file, method, pattern). This serves as a few-shot example for the remaining work — the next session will use it to understand the expected solution style.

TODO

For each remaining fix/change:

  1. Title — one-line description
  2. File and method — exact location with line numbers
  3. Current code — the actual snippet that needs changing
  4. Problem — why it's wrong (one sentence)
  5. Proposed fix — concrete code or pseudocode
  6. Complexity — Very low / Low / Medium / High
  7. Risk — None / Performance / Breaking change / etc.

Be specific. Vague TODOs waste context in the next session.

Key Files to Read

Table format:

FileWhy
Each entry: file path + one sentence explaining what
the next session needs from this file.

Only include files that are NECESSARY for the remaining work. Not everything that was read — only what matters.

Architecture Context

If the task requires understanding non-obvious relationships between components, include a brief sketch. Example:

MultiAnalyzer ├── delegates: Map<Language, IAnalyzer> └── templateAnalyzers: Collection<ITemplateAnalyzer>

Only include this if it saves the next session from having to rediscover the architecture.

Complexity Summary

Table format:

FixComplexityRisk

What NOT to include:

  • Conversation history
  • Rejected approaches or dead ends
  • Files that were read but aren't needed for the fix
  • Broad project context that's already in CLAUDE.md

Guiding principle:

Maximum signal density. Every line in handoff.md should save the next session from doing redundant work. If a line doesn't directly help with implementation, cut it.

After creating handoff.md:

  1. Tell the user: "handoff.md is ready. In the new session: /clear → then say 'Read handoff.md and follow the instructions.'"
  2. Do NOT commit handoff.md — it is temporary.
  3. Remind the user to delete handoff.md after the task is completed successfully.

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.