Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.
Create a handoff document that enables seamless session continuation.
Execution Steps
Given /handoff [topic]:
Step 1: Create Output Directory
mkdir -p .agents/handoff
Step 2: Identify Session Context
If topic provided: Use it as the handoff identifier.
If no topic: Derive from recent activity:
# Recent commits
git log --oneline -5 --format="%s" | head -1
# Check current issue
bd current 2>/dev/null | head -1
# Check ratchet state
ao ratchet status 2>/dev/null | head -3
Use the most descriptive source as the topic slug.
Topic slug format: 2-4 words, lowercase, hyphen-separated (e.g., auth-refactor, api-validation).
Fallback: If no good topic found, use session-$(date +%H%M) (e.g., session-1430).
Step 3: Gather Session Accomplishments
Review what was done this session:
# Recent commits this session (last 2 hours)
git log --oneline --since="2 hours ago" 2>/dev/null
# Recent file changes
git diff --stat HEAD~5 2>/dev/null | head -20
# Research producedls -lt .agents/research/*.md 2>/dev/null | head -3
# Plans createdls -lt .agents/plans/*.md 2>/dev/null | head -3
# Issues closed
bd list --status closed --since 2>/dev/null | -5
```
"2 hours ago"
head
Step 4: Identify Pause Point
Determine where we stopped:
What was the last thing done?
What was about to happen next?
Were we mid-task or between tasks?
Any blockers or decisions pending?
Check for in-progress work:
bd list --status in_progress 2>/dev/null | head -5
### Step 7: Write Continuation Prompt
**Write to:** `.agents/handoff/YYYY-MM-DD-<topic-slug>-prompt.md` (use `date +%Y-%m-%d`)
```markdown
# Continuation Prompt for New Session
Copy/paste this to start the next session:
---
## Context
<2-3 sentences describing the work and where we paused>
## Read First
1. The handoff doc: `.agents/handoff/YYYY-MM-DD-<topic-slug>.md`
2. <Other critical files>
## What I Need Help With
<Clear statement of what the next session should accomplish>
## Key Files
Open Questions
<Question 1>
<Question 2>
<Suggested skill to invoke, e.g., "Use /implement to continue">
### Step 8: Extract Learnings (Optional)
If significant learnings occurred this session, also run post-mortem:
```bash
# Check if post-mortem skill should be invoked
# (if >3 commits or major decisions made)
git log --oneline --since="2 hours ago" 2>/dev/null | wc -l
If ≥3 commits: Suggest running /post-mortem --quick to extract learnings.
If <3 commits: Handoff alone is sufficient; learnings are likely minimal.
Step 9: Report to User
Tell the user:
Handoff document location
Continuation prompt location
Summary of what was captured
Suggestion: Copy the continuation prompt for next session
If learnings detected, suggest /post-mortem --quick
Output completion marker:
<promise>DONE</promise>
If no context to capture (no commits, no changes):
<promise>EMPTY</promise>
Reason: No session activity found to hand off
Example Output
Handoff created:
.agents/handoff/20260131T143000Z-auth-refactor.md
.agents/handoff/20260131T143000Z-auth-refactor-prompt.md
Session captured:
- 5 commits, 12 files changed
- Paused: mid-implementation of OAuth flow
- Next: Complete token refresh logic
To continue: Copy the prompt from auth-refactor-prompt.md
<promise>DONE</promise>
Key Rules
Capture state, not just summary - next session needs to pick up exactly where we left off
Identify blockers clearly - don't leave the next session guessing
List files explicitly - paths, not descriptions
Write the continuation prompt - make resumption effortless
Cite everything - file:line for all references
Integration with /post-mortem
Handoff captures state for continuation.
Post-mortem captures learnings for the flywheel (full knowledge lifecycle).
For a clean session end:
/handoff # Capture state for continuation
/post-mortem --quick # Extract learnings for future
Both should be run when ending a productive session.
Without ao CLI
If ao CLI not available:
Skip the ao ratchet status check in Step 2
Step 8 retro suggestion still works (uses git commit count)
All handoff documents are still written to .agents/handoff/
Knowledge is captured for future sessions via handoff, just not indexed
Examples
Paused Mid-Implementation
User says:/handoff (after working on OAuth flow for 2 hours, need to stop)
What happens:
Agent detects recent commits (5 commits in last 2 hours, auth-related)
Agent checks in-progress work with bd list (issue #42 still open)
Agent identifies pause point: "Completed token generation, about to start refresh logic"
Agent lists key files: auth.go, token.go, research doc, plan doc
Agent writes handoff document with accomplishments and pause state
Agent writes continuation prompt with clear next action
Agent checks commits (5) and suggests running /post-mortem --quick to extract learnings