agentleFS
joris887joris887/exosuit/.claude/skills/handoff/SKILL.md

handoff

Skill9 starsChanged 3 months agoMITView on GitHub

Generate a structured handoff document for ending a development session. Saves to docs/sessions/ for the continue skill to read.

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

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 10

    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 conflicting session file for today's date

    line 27
  2. Distinctive:

    If the directory is missing, create it silently and proceed.

    line 29
  3. Distinctive:

    If work was done this session, ensure it's captured:

    line 43
  4. Distinctive:

    After generating the session file, dispatch a fresh sub-agent to test it from a reader's perspective:

    line 149
  5. Distinctive:

    Input: ONLY the generated session file — no conversation history

    line 152
  6. Distinctive:

    If uncommitted changes: suggest commit message and push

    line 159
  7. Distinctive:

    If sprint complete but no PR: suggest creating PR

    line 160
  8. Distinctive:

    If PR approved but not merged: suggest merging

    line 161
  9. Distinctive:

    If the user declines, skip without further prompting.

    line 175
  10. Distinctive:

    Ensure these are current:

    line 180

“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

Skill metrics: Emit a start event to the activity log:

echo "{\"type\":\"skill\",\"event\":\"start\",\"skill\":\"handoff\",\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" >> docs/sessions/.activity-log.jsonl

Generate a comprehensive handoff for ending a development session:

Phase 0: Validate Prerequisites

Before starting, verify:

  • docs/sessions/ directory exists (create if missing)
  • No conflicting session file for today's date

If the directory is missing, create it silently and proceed.

1. Capture Current State

Analyze:

  • Current branch: git branch --show-current
  • Git status (uncommitted changes?)
  • Open PRs: gh pr list --author @me --state open
  • Current sprint spec (if exists: docs/sprints/sprint-*.md) — extract sprint goal, capacity used, and any decisions logged this session
  • Last entries in @docs/progress.md

2. Document Progress

If work was done this session, ensure it's captured:

  • Sprint spec updated with progress
  • Any decisions documented
  • Blockers noted

3. Generate Session File

Save a structured session file to docs/sessions/session-YYYY-MM-DD.md.

The file MUST start with YAML frontmatter for /resume searchability:

---
date: YYYY-MM-DD
sprint: [current sprint number]
sprint_goal: "[sprint goal — one sentence from sprint spec]"
sprint_capacity: "[sessions used/total — e.g., 5/8]"
branch: [branch-name]
stories: [comma-separated story IDs worked on]
status: [completed | in-progress | blocked]
---

# Session Handoff — [YYYY-MM-DD]

## Git State
- **Branch:** [branch-name]
- **Uncommitted changes:** [yes/no — list if yes]
- **PR Status:** [Open #123 / Merged / Not created]

## Work Completed
- [x] [Task/story completed]
- [ ] [Task in progress — what's done, what remains]

## Key Decisions
- [Decision]: [Rationale]

## Blockers / Issues
- [Issue]: [Status]

## Files Accessed This Session

### Modified
- [path/to/file]: [what changed and why]

### Read (context-relevant)
- [path/to/file]: [why this file was important to understand]

### Investigated (can skip on resume)
- [path/to/file]: [explored but not relevant to current work]

## Test Status
- Passing: [count]
- Failing: [count]
- Coverage: [percentage if available]

## Next Steps (Minimal First Action)
1. [The single next thing to do — be very specific]
2. [Second priority]
3. [Third priority]

## Files to Load on Resume
- @[path] — [why this file is needed]

## Activity Summary

<!-- Populated from activity log if available -->

## Warnings / Gotchas
- [Any issues the next session should be aware of]
<IF condition="docs/sessions/.activity-log.jsonl exists"> **Activity summary:** Parse the activity log to populate the "Activity Summary" section with: total edits, total commands run, most-edited files (top 5), and edit-to-bash ratio. </IF>

4. Create Next Session Prompt

Generate a ready-to-use prompt for the next session:

## Next Session Start Prompt

Continue development.

### Context
- Last session: [date]
- Current story: [ID] - [title]
- Branch: [branch-name]
- PR Status: [Open #123 awaiting review / Not created / Merged]
- Status: [in progress / between sprints]

### Immediate Next Steps
1. [First thing to do]
2. [Second thing]
3. [Third thing]

### Files to Review
- @[path] - [why]

### Warnings/Gotchas
- [Any issues discovered]

4.5. Document Quality Check

After generating the session file, dispatch a fresh sub-agent to test it from a reader's perspective:

  • Agent type: Explore (read-only, forked context)
  • Input: ONLY the generated session file — no conversation history
  • Instructions: "You are a developer starting a new session tomorrow with only this handoff file. (1) Can you understand what was done? (2) Are next steps specific enough to act on immediately? (3) Is any critical context missing? (4) Would you need to re-explore anything that could have been captured here?"

Review findings. Fix genuine gaps before finalizing.

5. Commit and PR Reminder

  • If uncommitted changes: suggest commit message and push
  • If sprint complete but no PR: suggest creating PR
  • If PR approved but not merged: suggest merging

5.5. PR Session Summary

<IF condition="An open PR exists for the current branch (from step 1 gh pr list)"> Offer to add a session summary as a PR comment. This helps teammates (and future-you) understand the reasoning behind the code — the minimum viable knowledge transfer (see `docs/reference/TEAM_WORKFLOW.md` → Session Summaries):
gh pr comment --body "### Session Summary ($(date +%Y-%m-%d))
- **Decisions made:** [what was decided and why]
- **Alternatives rejected:** [approaches considered but not taken]
- **AI limitations encountered:** [what the AI struggled with or got wrong]"

If the user declines, skip without further prompting. </IF>

6. Update Persistent Files

Ensure these are current:

  • @docs/progress.md: recent sprints updated
  • @CLAUDE.md "Current Focus" is accurate

Skill metrics: Emit a completion event:

echo "{\"type\":\"skill\",\"event\":\"end\",\"skill\":\"handoff\",\"outcome\":\"success\",\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" >> docs/sessions/.activity-log.jsonl

Output the session summary and next session prompt.

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.