hunt
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code review or new features.
- installs 8w
- 2,873
- 30-day movement
- starts with the next reading
- Related entries
- 3
- Connections
- 0
Hunt is a SKILL.md an AI coding agent loads that enforces diagnosing root cause before applying any fix, with an outcome contract and hypothesis quality gates. It includes activation modes for regressions, bisection, screenshots, freezes, rendering, IME/Unicode bugs, and post-fix scope checking, plus reference files on logging and durable context.
You reach for it when a bug keeps recurring or a fix attempt risks being a guess, because it forces a verified hypothesis first.
Use it to
- Diagnose root cause before fixing a crash or failing test
- Bisect a regression back to a known good commit
- Compare against a good screenshot or version for visual regressions
- Find other instances of the same bug pattern after fixing one
- Debug freezes, rendering, or IME/Unicode issues with targeted logging
For Developers using AI agents who want disciplined debugging
- Host repository
- tw93/Waza
- Installs, lifetime
- 14k
- Installs, 8 weeks
- 2,873
- Host stars
- 7,069
- Host language
- Python