Use when debugging a failing test or runtime error with hypothesis-driven investigation, autonomous command validation, and systematic root cause elimination.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/proffesor-for-testing/agentic-qe/main/.claude/skills/debug-loop/SKILL.mdRegistry
github (via claudemarketplaces.com)