Bug Judge — Data skill for Claude Code
You are judging the outcome of one bug-fix attempt for an automated pipeline.
How to install Bug Judge
Installs to ~/.claude/skills/victorcorcos-wisetree-bug_judge/SKILL.md
mkdir -p ~/.claude/skills/victorcorcos-wisetree-bug_judge && curl -fsSL https://raw.githubusercontent.com/Victorcorcos/wisetree/HEAD/prompts/bug_judge.md -o ~/.claude/skills/victorcorcos-wisetree-bug_judge/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Bug Judge does
You are judging the outcome of one bug-fix attempt for an automated pipeline.
Alternatives in Data
- Data Contract — This document defines which files belong to the system (auto-updatable) and which belong to the user (never to 32.5k ★
- User Segmentation — Segment users by behavior, JTBD, and needs from feedback data 7.8k ★
- 06 Ink React Terminal UI — Prompt 06: Verify and Fix the Ink/React Terminal UI Pipeline 2.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Bug Investigate
You are investigating ONE reported bug in the current working directory for an automated pipeline. Your ONLY j
Exfiltration Triage
Judge whether outbound content or an egress connection is a real data-exfiltration attempt.
Fixer Plan
You are triaging a single pull-request review comment for an automated pipeline. Your ONLY job is to decide wh
Self Eval
Self-improvement loop. After a pipeline run, reviews how faithfully it executed step-by-step (from the determi
Clinstagram
Use when user asks to post on Instagram, check DMs, view stories, manage followers, get analytics, search user
Tw House Ops
AI-powered house hunting pipeline for Taiwan, built on Claude Code. Inspired by @santifer/career-ops — same op
Related Agents
Reviewer Response
Use when the user provides reviewer comment files (one per reviewer) and wants point-by-point LaTeX response l
ChatGPT Plan Review
ChatGPT implementation-plan review targeting tasks/builds/{slug}/plan.md; manual / automated / parallel modes,
Skill Applied Judge
Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each