field-test

Coordinate field tests across repositories using isolated worktrees and structured feedback reports.

2|1|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/TeamSPWK/nova --skill field-test-teamspwk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: field-test
Source: https://github.com/TeamSPWK/nova/tree/main/.claude/skills/field-test
Command: npx skills add https://github.com/TeamSPWK/nova --skill field-test-teamspwk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Field-Test Nova in real projects to identify improvement points, validate methodology, and surface friction points by observing Nova in action within isolated worktrees.

Core Features & Use Cases

  • Orchestrated, real-world validation across multiple repositories using isolated worktrees.
  • Structured feedback capture with mandatory reporting format to drive actionable improvements.
  • End-to-end phase execution (Phase 1-6) to surface issues early and guide next actions.

Quick Start

Describe a real project and run Field Test to deploy Nova sub-agents across each repository, observe feedback, and summarize results.

Frequently Asked Questions about field-test

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

FAQPage Schema
How do I validate AI sub-agents across multiple repositories using isolated worktrees?

To validate sub-agents across multiple repositories, you run a coordinated field test that sets up isolated worktrees, deploys agents in parallel, and executes end-to-end phases to collect structured feedback reports for actionable improvements.

What is a structured field test for real-world software engineering projects?

A structured field test observes your methodology in action within isolated worktrees to identify improvement points, validate processes, and surface friction points by deploying sub-agents and capturing mandatory feedback across multiple repositories.

How do I collect actionable feedback from automated testing in real projects?

You collect actionable feedback by enforcing a mandatory reporting format during end-to-end phase execution, ensuring all structured feedback reports from deployed sub-agents are captured to drive methodology improvements.

Does field testing with parallel sub-agents require interactive prompts?

Yes, field testing with parallel sub-agents requires interactive prompts and mandatory feedback formats to coordinate end-to-end phase execution across multiple repositories and uncover actionable improvements.

Can I run an end-to-end validation phase across multiple repositories simultaneously?

Yes, you can run end-to-end validation phases across multiple repositories simultaneously by deploying sub-agents in parallel within isolated worktrees, capturing structured feedback to surface issues early and guide next actions.

What are the limitations of using worktrees for parallel sub-agent field tests?

Limitations include relying on interactive prompts and mandatory feedback formats, meaning field tests require active coordination across multiple repositories and end-to-end phase execution rather than fully autonomous background runs.