Skills for Real Engineers. Straight from my .agents directory.
hunt
Agent skill fromtw93/Waza
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
How to install hunt
npx skills add tw93/Waza# or add only this skill to Claude Code: copy the folder
skills/hunt/
# into
~/.claude/skills/hunt/ (all projects)
.claude/skills/hunt/ (one project)
1# Hunt: Diagnose Before You Fix23Prefix your first line with 🥷 inline, not as its own paragraph.45A patch applied to a symptom creates a new bug somewhere else.67## Outcome Contract89- Outcome: the root cause is identified before any fix is applied.10- Done when: one sentence explains the cause, every observed symptom fits it, and the fix or handoff is verified against a reproducible check.11- Evidence: source trace, repro command or UI path, logs or state, targeted test/build output, and runtime evidence for UI or native defects.12- Output: root cause, fix or handoff, verification result, and any unswept sibling risks.13- 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.1415**Do not touch code until you can state the root cause in one sentence:**16> "I believe the root cause is [X] because [evidence]."1718Name a specific file, function, line, or condition. "A state management issue" is not testable. "Stale cache in `useUser` at `src/hooks/user.ts:42` because the dependency array is missing `userId`" is testable. If you cannot be that specific, you do not have a hypothesis yet.19…
Excerpt shown under the repository's MIT license.
More skills in Waza
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
