agentleFS
jellydnjellydn/my-ai-tools/skills/handoffs/SKILL.md

handoffs

Skill127 starsChanged 27 days agoMITView on GitHub

Create handoff plans for continuing work across sessions

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not continue before asking for the purpose as you will otherwise not understand the instructions and do not assume a purpose!

    line 23
  2. Distinctive:

    Create a detailed summary of the conversation so far, paying close attention to the user's explicit purpose for the next steps.

    line 27
  3. Very specific:

    Before providing the final handoff, produce a concise evidence-based summary for the user.

    line 32
  4. Distinctive:

    Verify important paths, branch/status, recent command results, and unresolved blockers.

    line 35
  5. Distinctive:

    Problem Solving: Document problems solved and any ongoing troubleshooting efforts.

    line 45
  6. Distinctive:

    After providing your analysis and summary:

    line 122
  7. Very specific:

    Ensure the .planning/handoffs/ directory exists (create it if needed)

    line 124
  8. Very specific:

    Write the handoff summary to a markdown file at .planning/handoffs/[timestamp]-[slug].md where [timestamp] is the current date in format …

    line 125
  9. Distinctive:

    Read the handoff file back and verify it contains the purpose, current state, verification, blockers, and next action.

    line 126

≈ “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

Session Handoff Plan

Creates a detailed handoff plan of the conversation for continuing the work in a new session.

The user specified purpose:

<purpose>$ARGUMENTS</purpose>

You are creating a summary specifically so that it can be continued by another agent. For this to work you MUST have a purpose. If no specified purpose was provided in the <purpose>...</purpose> tag you must STOP IMMEDIATELY and ask the user what the purpose is.

Do not continue before asking for the purpose as you will otherwise not understand the instructions and do not assume a purpose!

Goal

Create a detailed summary of the conversation so far, paying close attention to the user's explicit purpose for the next steps. This handoff plan should be thorough in capturing technical details, code patterns, and architectural decisions that will be essential for continuing development work without losing context.

Process

Before providing the final handoff, produce a concise evidence-based summary for the user. Do not expose private chain-of-thought or <analysis> tags. Include decisions, current state, blockers, and the exact next action instead of a chronological transcript or full code dumps.

  1. Identify the user's explicit purpose and the current work state.
  2. Verify important paths, branch/status, recent command results, and unresolved blockers.
  3. Capture only decision-relevant file names, symbols, short snippets, and links.
  4. Mark uncertain or stale information explicitly.

Your plan should include the following sections:

  1. Primary Request and Intent: Capture all of the user's explicit requests and intents in detail
  2. Key Technical Concepts: List all important technical concepts, technologies, and frameworks discussed.
  3. Files and Code Sections: Enumerate specific files and code sections examined, modified, or created. Pay special attention to the most recent messages and include full code snippets where applicable and include a summary of why this file read or edit is important.
  4. Problem Solving: Document problems solved and any ongoing troubleshooting efforts.
  5. Pending Tasks: Outline any pending tasks that you have explicitly been asked to work on.
  6. Current Work: Describe in detail precisely what was being worked on immediately before this handoff request, paying special attention to the most recent messages from both user and assistant. Include file names and code snippets where applicable.
  7. Next Step: List the next step that you will take that is related to the most recent work you were doing. IMPORTANT: ensure that this step is DIRECTLY in line with the user's explicit requests, and the task you were working on immediately before this handoff request. If your last task was concluded, then only list next steps if they are explicitly in line with the users request. Do not start on tangential requests without confirming with the user first. Include this section only if there is an actionable next step.

Additionally create a "slug" for this handoff. The "slug" is how we will refer to it later in a few places. Examples:

  • current-user-api-handler
  • implement-auth
  • fix-issue-42

Together with the slug create a "Readable Summary". Examples:

  • Implement Current User API Handler
  • Implement Authentication
  • Fix Issue #42

Output Structure

The handoff file should contain the structured summary below. Do not include private chain-of-thought or a chronological transcript.

# Session Handoff Plan

## 1. Primary Request and Intent

[Detailed description of all user requests and intents]

## 2. Key Technical Concepts

- [Concept 1]
- [Concept 2]
- [...]

## 3. Files and Code Sections

### [File Name 1]

- **Why important**: [Summary of why this file is important]
- **Changes made**: [Summary of the changes made to this file, if any]
- **Code snippet**:

\`\`\`language
[Important Code Snippet]
\`\`\`

### [File Name 2]

- **Code snippet**:

\`\`\`language
[Important Code Snippet]
\`\`\`

[...]

## 4. Problem Solving

[Description of solved problems and ongoing troubleshooting]

## 5. Pending Tasks

- [Task 1 that you have been explicitly asked to work on]
- [Task 2 that you have been explicitly asked to work on]
- [...]

## 6. Current Work

[Detailed description of what was being worked on immediately before this handoff, including file names and code snippets]

## 7. Next Step

[Next step to take, directly aligned with user's explicit handoff purpose. Only include if there is an actionable next step.]

Final Step

After providing your analysis and summary:

  1. Ensure the .planning/handoffs/ directory exists (create it if needed)
  2. Write the handoff summary to a markdown file at .planning/handoffs/[timestamp]-[slug].md where [timestamp] is the current date in format YYYY-MM-DD and the slug is what we defined before
  3. Read the handoff file back and verify it contains the purpose, current state, verification, blockers, and next action.
  4. Tell the user about this file and that they can use /pickup $1 to continue where $1 is the filename

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.