test

Validate uncommitted changes with lint, tests, and agent reviews.

Updated Aug 27, 2026

Search Tags:#automation #agents #lint #code-review #tests #dev-workflow

Ready to run

npx skills add https://github.com/oobagi/jflow --skill test-oobagi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: test
Source: https://github.com/oobagi/jflow/tree/main/skills/test
Command: npx skills add https://github.com/oobagi/jflow --skill test-oobagi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Validate uncommitted changes by running lint, tests, and review agents to surface issues early and help teams ship reliable code.

Core Features & Use Cases

Light mode: runs a single Code Reviewer to quickly surface quality issues during development.
Full mode: launches Code Reviewer, Reality Checker, and Security Engineer in parallel for deeper analysis, with optional focus areas.
Use Case: When preparing a PR, run the test skill to automatically lint, test, and collect agent reviews before review.

Quick Start

Run the test skill to validate uncommitted changes by linting, tests, and agent reviews.

Frequently Asked Questions about test

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

FAQPage Schema

How do I automate code review for uncommitted changes before a PR?▼

Automate code change reviews by running lint, tests, and agent-based reviews on uncommitted changes. This surfaces issues early before preparing a pull request, using either light or full review modes.

What is the difference between light and full agent-based code review modes?▼

Light agent-based code review runs a single Code Reviewer for quick quality checks. Full review mode launches Code Reviewer, Reality Checker, and Security Engineer in parallel for deeper analysis, with optional focus areas like security or performance.

How do I run lint and tests alongside agent reviews during development?▼

Run the test skill to validate uncommitted changes by orchestrating lint, tests, and agent reviews together. It presents a unified summary of findings, helping you catch issues during active development rather than waiting for PR review.

Can I focus automated code reviews on specific areas like security or performance?▼

Yes, automated code reviews can weight a specified focus area like security or performance. In full mode, the Code Reviewer, Reality Checker, and Security Engineer agents adjust their analysis based on your specified focus.

What agents are involved in a full automated code change review?▼

A full automated code change review involves a Code Reviewer, Reality Checker, and Security Engineer. These agents run in parallel to analyze changes, with optional additional agents available depending on your review needs.

When should I use a single Code Reviewer instead of multiple review agents?▼

Use a single Code Reviewer during active development for quick quality issue surfacing. Switch to multiple review agents in full mode when preparing a PR and needing deeper parallel analysis from security, reality checking, and code review perspectives.