Install any skill in seconds. Free to start, no credit card required.
Get Started Free →elianiva/swarm
Fan out N parallel workers, drain them, and return one report.
Passed 9 of 19 test cases with the skill, and 5 of 19 without it.
and 7 more in the full report
7 fixed4 passed either way11 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to dispatch 4 parallel code review workers for the modules `/apps/web`, `/apps/mobile`, `/apps/admin`, and `/apps/api`. What specific agent and role parameters must be passed in the `subagent` call?
| Checked | Without skill | With skill |
|---|---|---|
| Sets agent to poteto-agent in the subagent call. | Missed | Passed |
| Spawns all 4 code review workers concurrently in one parallel subagent tool invocation. | Missed | Passed |
The instructions your model reads when the skill loads.
Fan out N parallel cloud workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.
Open a todolist with one entry per phase before launching anything.
first pass, rank all, or best-of before spawning.swarm workers in ~/.pi/agent/pstack/models.json when present. Otherwise use inherit-parent. For a model race, name each arm's model up front./tmp/swarm-<slug>/worker-<n>/.Spawn all N workers in one parallel subagent call using its tasks array. Use agent: "poteto-agent" unless a workflow names another agent, and set role: "swarm workers". Pi child processes run locally with isolated context, so give each task explicit file pointers and prevent concurrent writes to shared paths.
When a worker must start from a non-default pushed branch, pass cloud_base_branch.
Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence.
If a worker drops out, proceed with N-1 and note it.
Read the terminal results. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.
Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.
Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.
test cases passed, vs 5 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.