Hunt

When your fix doesn't stick or you're stacking patches on symptoms, this skill forces you to stop and diagnose first. It won't let you touch code until you can state the root cause in one sentence with evidence. Includes bisect mode for regressions, screenshot reference mode for visual bugs, and scope blast to find every other place the same pattern is hiding. The hard rules are good: same symptom after a fix is a hard stop, three failed hypotheses means you surface what you've ruled out and ask how to proceed. Designed for errors, crashes, and "it used to work" problems, not code review or greenfield features.

skills.sh installs: 15.2K
GitHub stars: 7.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tw93/waza --skill hunt --agent claude-code

Installs into .claude/skills of the current project.

Files

Hunt: Diagnose Before You Fix

Prefix your first line with 🥷 inline, not as its own paragraph.

A patch applied to a symptom creates a new bug somewhere else.

Outcome Contract

Outcome: the root cause is identified before any fix is applied.
Done when: one sentence explains the cause, every observed symptom fits it, and the fix or handoff is verified against a reproducible check.
Evidence: source trace, repro command or UI path, logs or state, targeted test/build output, and runtime evidence for UI or native defects.
Output: root cause, fix or handoff, verification result, and any unswept sibling risks.
Authorization: "diagnose", "investigate", "why", "look into", "排查", "看看", or equivalent is report-only. Apply a fix only when the current request explicitly asks to fix, change, implement, or optimize, or when an authorization to do so is still in force for this same unfinished task with the action, scope, and goal unchanged; root-cause proof is still required first. A fix authorization never carries commit, push, publish, or any destructive action with it.

SKILL.md on GitHub