---
name: elianiva-swarm
description: "Fan out N parallel workers, drain them, and return one report. Use for /skill:swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration."
disable-model-invocation: true
metadata:
  decimalai-skill-id: "269c472d-d461-4bef-b124-8b451a3ce1a0"
  decimalai-version-id: "af4fd64c-9207-40d6-89c6-a061985e96dd"
  decimalai-version: "1"
  decimalai-body-sha256: "dd882ddc73f188f804525b241027a588be6c035551319ae75b3de698ac90ab4a"
  decimalai-name: "elianiva/swarm"
  decimalai-format: "1"
  decimalai-invocation: "user"
  decimalai-category: "agent-tooling"
  decimalai-source: "https://app.decimal.ai/s/elianiva-swarm@1/SKILL.md"
---
# Swarm

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.

## Start

Open a todolist with one entry per phase before launching anything.

1. Frame
2. Fan out
3. Aggregate
4. Report

## Phase A: Frame

1. State the done predicate and the artifact or report the swarm must return.
2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare `first pass`, `rank all`, or `best-of` before spawning.
3. Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit.
4. Pick the worker model from `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.
5. Give each worker its own writable output when it writes. Use a worktree, branch, or `/tmp/swarm-<slug>/worker-<n>/`.

## Phase B: Fan out

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.

## Phase C: Aggregate

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.

## Phase D: Report

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.