fixme-investigate

Reproduce browser bugs and generate root-cause investigation reports.

Updated Feb 18, 2026
One-click install
npx skills add https://github.com/denis-pingin/fixme --skill fixme-investigate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fixme-investigate
Source: https://github.com/denis-pingin/fixme/tree/main/.claude/skills/fixme-investigate
Command: npx skills add https://github.com/denis-pingin/fixme --skill fixme-investigate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reproduce bugs in a real browser and investigate codebase to find root cause. Standalone pipeline phase - receives task description, outputs investigation report.

Core Features & Use Cases

  • Reproduce bugs in a real browser to observe behavior and collect evidence
  • Analyze codebase to map UI actions to underlying sources and identify failure points
  • Generate an investigation report with reproduction steps and root cause hypotheses

Quick Start

Describe the bug and provide the dev server URL to start an automated reproduction and investigation.

Frequently Asked Questions about fixme-investigate

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

FAQPage Schema
How do I automate browser bug reproduction and root cause investigation?

Automate browser bug reproduction by providing a task description and a dev server URL. The pipeline uses Playwright to reproduce the bug in a real browser, analyze the codebase, and output an investigation report with root cause hypotheses.

What do I need to configure before investigating web application bugs?

You need Playwright tooling installed and a configured .fixme/config.json file to investigate web application bugs. This configuration file locates the dev server and output directory required to execute the automated reproduction pipeline.

Can I use Playwright to map UI actions to underlying source code failures?

Playwright reproduces bugs in a real browser to observe behavior and collect evidence, which the pipeline then uses to map UI actions to underlying source code and identify failure points for root cause analysis.

Does the automated investigation pipeline work for standalone web applications?

The automated investigation pipeline works across fixme-session and standalone investigations for web applications. It requires a task description and a running dev server URL to begin the end-to-end browser reproduction process.

What is included in the investigation report after a bug is reproduced?

The investigation report includes detailed reproduction steps and root cause hypotheses. It maps the observed browser behavior to codebase failure points, providing a standalone output for downstream debugging.

Why do I need a dev server URL to investigate a browser bug?

A dev server URL is needed to investigate a browser bug because the pipeline uses Playwright to interact with the live application. It reproduces the issue in a real browser environment to collect evidence and analyze the codebase.