acm-bug-hunter

Hunt bugs in ACM feature implementations using a 10-dimension investigation.

3|4|Updated Jul 25, 2025
One-click install
npx skills add https://github.com/stolostron/acm-ai-qe --skill acm-bug-hunter
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: acm-bug-hunter
Source: https://github.com/stolostron/acm-ai-qe/tree/main/.claude/skills/acm-bug-hunter
Command: npx skills add https://github.com/stolostron/acm-ai-qe --skill acm-bug-hunter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires acm-source, jira, neo4j-rhacm, polarion, acm-search, acm-kubectl, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Identifies bugs in ACM feature implementations that might be missed by test cases, through a systematic 10-dimension investigation process.

Core Features & Use Cases

  • Systematic Analysis: Uses a 10-dimension model to investigate ACM feature implementations.
  • Adversarial Architecture: Spawns focused subagents for each dimension to prevent self-bias.
  • Confidence-Aware Feedback Loops: Incorporates confidence-aware feedback for honesty and thoroughness.
  • Cross-Component Probing: Performs integration probing across component boundaries.

Quick Start

Run the 'acm-bug-hunter' skill with a Polarion test case ID or a local .md file.

Frequently Asked Questions about acm-bug-hunter

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

FAQPage Schema
How do I investigate ACM feature implementations for bugs missed by test cases?

Yes, you can hunt for bugs in ACM features without a live cluster. The investigation process works with or without a live cluster by analyzing test cases from Polarion or local .md files and probing across component boundaries using source code and dependency graphs.

Do I need JIRA and Polarion access to perform systematic bug hunting in ACM?

Adversarial architecture improves bug hunting by spawning focused subagents for each investigation dimension. This structure prevents self-bias and ensures thoroughness by using confidence-aware feedback loops to challenge findings across component boundaries.

What's the best way to start an ACM bug investigation using test cases?

The best way to start an ACM bug investigation is to provide a Polarion test case ID or a local .md file. The system uses this input to initiate a cross-component probing process across ten analysis dimensions to find hidden implementation defects.

Are there limitations when using automated analysis for ACM feature bugs?

A limitation of automated ACM bug analysis is its dependency on external integrations; the process requires simultaneous access to JIRA, Polarion, ACM Source, and Neo4j MCPs to function. It also relies heavily on the initial quality of the provided test cases.