with one click
ultrawork
// Parallel execution engine for high-throughput task completion. Runs multiple droids simultaneously for independent tasks.
// Parallel execution engine for high-throughput task completion. Runs multiple droids simultaneously for independent tasks.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | ultrawork |
| description | Parallel execution engine for high-throughput task completion. Runs multiple droids simultaneously for independent tasks. |
<Use_When>
<Do_Not_Use_When>
ralph instead (ralph includes ultrawork)autopilot insteadralph
</Do_Not_Use_When><What_You_MUST_Do>
<What_You_MUST_NOT_Do>
<Why_This_Exists> Sequential task execution wastes time when tasks are independent. Ultrawork enables firing multiple droids simultaneously, reducing total execution time. It is designed as a composable component that ralph and autopilot layer on top of. </Why_This_Exists>
<Execution_Policy>
<Parallel_Execution>
Factory Droid does NOT support native background execution (run_in_background: true). For TRUE parallel execution of independent tasks, use background-manager.py:
# Launch multiple droids in TRUE parallel (fire ALL before checking ANY)
python3 hooks/background-manager.py launch "Fix auth" "Fix auth module errors" executor-med "main"
python3 hooks/background-manager.py launch "Fix API" "Fix API route errors" executor-med "main"
python3 hooks/background-manager.py launch "Fix UI" "Fix frontend type errors" executor-med "main"
# Monitor all running tasks
python3 hooks/background-manager.py list
# Check specific task output when done
python3 hooks/background-manager.py output <task_id>
CRITICAL: Launch ALL independent tasks BEFORE checking any results. Do NOT launch-wait-launch sequentially. </Parallel_Execution>
1. **Classify tasks by independence**: Identify which can run in parallel vs which have dependencies 2. **Route to correct droids**: - Simple changes: executor-low - Standard implementation: executor-med (DEFAULT) - Complex work: executor-high or hephaestus 3. **Fire independent tasks simultaneously**: Launch all parallel-safe tasks at once via Task tool 4. **Run dependent tasks sequentially**: Wait for prerequisites before launching dependent work 5. **Verify when all tasks complete** (lightweight): - Build passes - Affected tests pass - No new errors introduced Three independent tasks fired simultaneously: ``` Task(subagent_type="executor-low", prompt="Add missing type export for Config interface") Task(subagent_type="executor-med", prompt="Implement the /api/users endpoint with validation") Task(subagent_type="executor-med", prompt="Add integration tests for the auth middleware") ``` Why good: Independent tasks at appropriate tiers, all fired at once. Sequential execution of independent work: ``` result1 = Task(executor-low, "Add type export") # wait... result2 = Task(executor-med, "Implement endpoint") # wait... result3 = Task(executor-med, "Add tests") # wait... ``` Why bad: Independent tasks serialized, wasting time. Wrong tier selection: ``` Task(subagent_type="hephaestus", prompt="Add a missing semicolon") ``` Why bad: Overkill for a trivial fix. Use executor-low instead.<Escalation_And_Stop_Conditions>
ralph<Final_Checklist>
ralph (persistence wrapper)
└── includes: ultrawork (this skill)
└── provides: parallel execution only
autopilot (autonomous execution)
└── includes: ralph
└── includes: ultrawork (this skill)
ecomode (modifier)
└── modifies: ultrawork's droid selection to prefer cheaper tiers
Ultrawork is the parallelism layer. Ralph adds persistence and verification. Autopilot adds the full lifecycle pipeline. Ecomode adjusts droid routing.