Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and execute complex work across multiple files and modules.
.claude/skills/swarm-orchestration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-20 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and execute complex work across multiple files and modules.
Start a new swarm with hierarchical topology (anti-drift)
bashnpx @claude-flow/cli swarm init --topology hierarchical --max-agents 8 --strategy specialized
Example:
bashnpx @claude-flow/cli swarm init --topology hierarchical --max-agents 6 --strategy specialized
Route a task to the appropriate agents based on task type
bashnpx @claude-flow/cli hooks route --task "[task description]"
Example:
bashnpx @claude-flow/cli hooks route --task "implement OAuth2 authentication flow"
Spawn a specific agent type
bashnpx @claude-flow/cli agent spawn --type [type] --name [name]
Example:
bashnpx @claude-flow/cli agent spawn --type coder --name impl-auth
Check the current swarm status
bashnpx @claude-flow/cli swarm status --verbose
Orchestrate a task across multiple agents
bashnpx @claude-flow/cli task orchestrate --task "[task]" --strategy adaptive
Example:
bashnpx @claude-flow/cli task orchestrate --task "refactor auth module" --strategy parallel --max-agents 4
List all active agents
bashnpx @claude-flow/cli agent list --filter active
| Script | Path | Description | |--------|------|-------------| | swarm-start | .agents/scripts/swarm-start.sh | Initialize swarm with default settings | | swarm-monitor | .agents/scripts/swarm-monitor.sh | Real-time swarm monitoring dashboard |
| Document | Path | Description | |----------|------|-------------| | Agent Types | docs/agents.md | Complete list of agent types and capabilities | | Topology Guide | docs/topology.md | Swarm topology configuration guide |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.