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.
Enables squad agents on different machines to share work via git-based task queuing
metadata
{"author":"cwoodruff"}
Skill: Cross-Machine Coordination Pattern
Skill ID:cross-machine-coordination Owner: Ralph (Work Monitor) Squad Integration: All agents Status: Specification (ready for implementation)
Overview
Enables squad agents running on different machines (laptop, DevBox, Azure VM) to securely share work, coordinate execution, and pass results without manual intervention.
Write result to .squad/cross-machine/results/gpu-voice-clone-001.yaml
Commit & push the result
For Task Executors (DevBox, Azure VMs)
Ralph automatically watches .squad/cross-machine/tasks/ for work targeted at this machine.
On each cycle (5-10 min):
# Pseudo-code (Ralph implementation)1. git pull origin main
2. Load all .yaml files in .squad/cross-machine/tasks/
3. Filter for status=pending AND target_machine=HOSTNAME
4. For each task:
a. Validate schema (must have: id, source_machine, target_machine, payload)
b. Validate command against whitelist
c. Execute task (with timeout)
d. Write result to .squad/cross-machine/results/{id}.yaml
e. Commit & push result
For Urgent/Ad-Hoc Tasks
Use GitHub Issues with squad:machine-{name} label:
id: {task-id} # Links back to tasktarget_machine:devbox# Executed oncompleted_at:2026-03-14T15:45:00Z# When it finishedstatus:completed|failed|timeout# Outcomeexit_code:0# Shell exit codestdout:"..."# Captured outputstderr:"..."# Captured errorsduration_seconds:900# How long it tookartifacts:-path:"/path/to/artifacts/..."# Location of resultstype:audio|text|model|...size_mb:2.5
# .squad/cross-machine/results/gpu-voice-clone-001.yamlid:gpu-voice-clone-001target_machine:devboxcompleted_at:2026-03-14T15:45:00Zstatus:completedexit_code:0stdout:"Voice cloning completed. Output written to /tmp/cloned.wav"stderr:""duration_seconds:900artifacts:-path:"/path/to/artifacts/voice-clone-001/output.wav"type:audiosize_mb:2.5
Example 2: Urgent Debug Request (Human → DevBox via Issue)
Create issue:
gh issue create \
--title "DevBox: Debug voice model failure" \
--body "Error: Model failed to load on last run. Please check /tmp/model.log and report findings." \
--label "squad:machine-devbox" \
--label "urgent"
Ralph automatically includes this pattern in its watch loop:
Ralph Watch Cycle (every 5-10 min):
1. Fetch GitHub issues with squad:machine-* labels
2. Poll .squad/cross-machine/tasks/
3. For each matching task:
- Validate
- Execute
- Write result
- Commit & push
4. Update status in issue (if applicable)
5. Sleep until next cycle
No manual Ralph configuration needed — just create task files or issues with the right labels.
Migration from Manual Handoff
Before (today):
Laptop → user manually copies file to Teams chat
user pastes into target terminal
user copies output back
user pastes result manually
After (with this pattern):
Laptop Ralph writes task file → git push
DevBox Ralph auto-executes → git push result
Laptop Ralph auto-reads result
0 human intervention needed
Future Enhancements
Potential expansions (Phase 2+):
Task Priorities: Execution order based on priority field
Serial Pipelines: Machine A → B → C task chains
GPU Availability Polling: Query DevBox before submitting work
Cost Tracking: Log resource usage per task
Notification Webhooks: Alert on task completion
Web Dashboard: Real-time task status visualization
Questions?
Refer to research report: research/active/cross-machine-agents/README.md
Contact: Seven (Research & Docs) or Ralph (Work Monitor)
