py-test-swarm

Coordinate hierarchical BioETL test swarms across L1/L2/L3 agents.

1|Updated Dec 1, 2025
One-click install
npx skills add https://github.com/SatoryKono/BioactivityDataAcquisition --skill py-test-swarm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: py-test-swarm
Source: https://github.com/SatoryKono/BioactivityDataAcquisition/tree/main/docs/skills/local/py-test-swarm
Command: npx skills add https://github.com/SatoryKono/BioactivityDataAcquisition --skill py-test-swarm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Orchestrates hierarchical BioETL test swarms (L1/L2/L3) to enable full-audit, structured failure triage, coverage expansion, and final reporting across multiple providers.

Core Features & Use Cases

  • Decomposes work into L2/L3 agents, enforces constraints, aggregates evidence, and produces final artifacts.
  • Reads L1 startup inputs and task contracts to coordinate deterministic test campaigns.
  • Provides artifact contracts and telemetry aggregation for scalable quality assurance across pipelines.

Quick Start

Launch the L1 orchestrator with a task-id and mode to begin a swarm and generate reports under reports/test-swarm/<task-id>.

Frequently Asked Questions about py-test-swarm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate hierarchical pytest campaigns for large-scale test suites?

You orchestrate test campaigns by launching the L1 orchestrator with a task-id and mode. This decomposes work into L2/L3 agents to enforce deterministic execution, aggregate telemetry, and generate final reports under reports/test-swarm/<task-id>/.

What is the best way to triage test failures at scale across multiple providers?

Triage test failures at scale using the fix-failures mode in a hierarchical test swarm. The L1 orchestrator coordinates L2/L3 agents to execute deterministic campaigns, aggregate telemetry, and output structured failure diagnostics under reports/test-swarm/<task-id>/FINAL-REPORT.md.

How can I expand test coverage and diagnose flakiness in automated BioETL pipelines?

Expand coverage and diagnose flakiness by configuring coverage-boost and stability modes in the test swarm. You define flakiness-runs and a baseline-report in the input contract to execute stability diagnostics and aggregate telemetry for final reporting.

What inputs do I need to start a deterministic test swarm for quality assurance?

Starting a deterministic test swarm requires an input contract defining a task-id, mode, scope, baseline-report, and flakiness-runs. These inputs coordinate L1 startup and constrain L2/L3 agents to produce mandated output artifacts.

Does this test orchestration approach work without external dependencies?

Yes, this test orchestration approach works without external dependencies. The L1 orchestrator reads task contracts and coordinates L2/L3 agents internally to enforce deterministic execution and aggregate telemetry for final reporting.