Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →josstei/execution
Phase execution methodology for orchestration workflows with error handling and completion protocols
Passed 10 of 15 test cases with the skill, and 9 of 15 without it.
and 3 more in the full report
5 fixed9 passed either way4 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Begin Phase 3 execution. Environment settings have MAESTRO_EXECUTION_MODE set to parallel.
| Checked | Without skill | With skill |
|---|---|---|
| Updates session state with execution_mode set to parallel. | Missed | Passed |
| Skips asking the user for execution mode choice. | Passed | Passed |
The instructions your model reads when the skill loads.
Activate this skill during Phase 3 (Execution) of Maestro orchestration. This skill defines how Maestro executes implementation phases through native subagent delegation.
If workflow_mode is express in the current session, STOP HERE. Do not proceed
to the execution mode gate. Do not prompt the user. Do not resolve execution mode.
Express always dispatches sequentially. Return to the Express Workflow and continue
from the delegation step.
Read MAESTRO_EXECUTION_MODE (default: ask).
parallel: call update_session with { execution_mode: 'parallel', execution_backend: 'native' } to record in session state. Skip to delegation.sequential: call update_session with { execution_mode: 'sequential', execution_backend: 'native' } to record in session state. Skip to delegation.ask: proceed to Step 2.Before prompting the user, analyze the approved plan to generate a recommendation:
Count total phases in the plan
Count phases marked parallel: true (parallelizable phases)
Count distinct parallel batches (groups of parallelizable phases at the same dependency depth)
Count sequential-only phases (phases with blocked_by dependencies that prevent parallelization)
Cross-check file ownership across all phases. If any two phases share a file in their files arrays, those phases CANNOT be parallel-eligible — subtract them from the parallelizable count. Report each overlap as an Overlapping-file Warning in the prompt.
If validate_plan was called during planning and returned a parallelization_profile, use its parallel_eligible and effective_batches counts as the authoritative source for items 1-5 above. These are computed from actual dependency depths and override any manual flag-based counts. If parallelization_profile is not available, use the counts from items 1-5 as-is.
Record these counts — they feed into the prompt.
test cases passed, vs 9 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.