dispatching-parallel-agents
Governs when and how to fan work out to parallel subagents: independence tests, scoping rules, and result-integration discipline.
Anatomy
| Parent repo | obra/superpowers |
|---|---|
| Path | skills/dispatching-parallel-agents |
| Trigger conditions | "Use when facing 2+ independent tasks that can be worked on without shared state" |
| Instruction format | yaml-frontmatter-md |
| Required tools | subagents |
| Reusability | universal |
| Complexity | high |
| Ships scripts / examples / tests / boundaries | no / yes / no / yes |
Failure modes
The independence judgment is the hard part and stays with the operator; misjudged dependencies produce conflicting parallel edits.
Verdict
The fan-out pattern with guardrails. Its main value is the independence checklist, which prevents the classic failure of parallelizing coupled work.
Related skills
Blocks the agent from claiming work is complete, fixed, or passing until it has run verification commands and confirmed output. Evidence…
Forces root-cause investigation before any fix: reproduce, hypothesize one cause at a time, test the hypothesis, then patch. Bans…
Frequently asked questions
What does the dispatching-parallel-agents skill do?
Governs when and how to fan work out to parallel subagents: independence tests, scoping rules, and result-integration discipline.
When does dispatching-parallel-agents trigger?
Its stated trigger: "Use when facing 2+ independent tasks that can be worked on without shared state". Trigger precision is a scored reliability dimension.