CtrlK
BlogDocsLog inGet started
Tessl Logo

parallel-agent-spawner

Spawn and coordinate parallel agents for faster completion. Use when running parallel tasks, spawning subagents, coordinating concurrent work, or optimizing throughput.

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/parallel-agent-spawner/SKILL.md
SKILL.md
Quality
Evals
Security

Parallel Agent Spawner

Spawns and coordinates parallel agents for faster feature completion.

Quick Start

Spawn Parallel Agents

from scripts.parallel_spawner import ParallelSpawner

spawner = ParallelSpawner(project_dir)
results = await spawner.spawn_parallel(
    tasks=["feature-1", "feature-2", "feature-3"],
    agent_type="coding"
)

Coordinate Results

await spawner.wait_all()
summary = spawner.get_results_summary()

Parallel Execution Model

┌─────────────────────────────────────────────────────────────┐
│                   PARALLEL EXECUTION                        │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  MAIN ORCHESTRATOR                                          │
│  ├─ Analyzes feature dependencies                          │
│  ├─ Identifies parallelizable work                         │
│  ├─ Spawns worker agents                                   │
│  └─ Coordinates results                                    │
│                                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐                 │
│  │ Agent 1  │  │ Agent 2  │  │ Agent 3  │                 │
│  │          │  │          │  │          │                 │
│  │ feature-1│  │ feature-2│  │ feature-3│                 │
│  └────┬─────┘  └────┬─────┘  └────┬─────┘                 │
│       │             │             │                        │
│       ▼             ▼             ▼                        │
│  ┌─────────────────────────────────────────┐              │
│  │           RESULT AGGREGATOR              │              │
│  │  ├─ Collects all results                │              │
│  │  ├─ Resolves conflicts                  │              │
│  │  ├─ Merges code changes                 │              │
│  │  └─ Updates feature list                │              │
│  └─────────────────────────────────────────┘              │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Agent Types

TypePurposeParallelizable
codingImplement featuresYes, if independent
testingRun E2E testsYes
reviewCode reviewYes
researchExplore codebaseYes

Spawn Configuration

@dataclass
class SpawnConfig:
    max_parallel: int = 3
    timeout_per_agent: int = 1800  # 30 min
    retry_failed: bool = True
    merge_strategy: str = "sequential"  # or "git-merge"

Integration Points

  • autonomous-loop: Provides work to parallelize
  • coding-agent: Worker agents for features
  • checkpoint-manager: Create checkpoints before spawn
  • error-recoverer: Handle agent failures

References

  • references/PARALLELIZATION-STRATEGY.md - Strategy guide
  • references/CONFLICT-RESOLUTION.md - Merge conflicts

Scripts

  • scripts/parallel_spawner.py - Core spawner
  • scripts/agent_pool.py - Agent pool management
  • scripts/result_aggregator.py - Aggregate results
  • scripts/dependency_analyzer.py - Find parallelizable work
Repository
fernandezbaptiste/Skrillz
Path

skills/parallel-agent-spawner/SKILL.md

Commit

93ed392

Last updated
First committed

Also appears in

fernandezbaptiste/Skrillz
In sync

since Sep 12, 2026

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

Claim skill