Menu
处理缺陷、回归、崩溃、错误输出或性能下降时使用。复现→定位→修复→验证。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | fix-bug |
| description | 处理缺陷、回归、崩溃、错误输出或性能下降时使用。复现→定位→修复→验证。 |
| argument-hint | [缺陷描述或 issue 链接] |
!git branch --show-current 2>/dev/null && git log --oneline -5 2>/dev/null
!git status --short 2>/dev/null | head -20
superpowers:systematic-debugging：先明确复现条件、复现命令、复现证据superpowers:test-driven-development：至少补 1 条覆盖根因的测试superpowers:verification-before-completion：回归测试必须覆盖根因场景| 场景 | Agent | 执行方式 |
|---|---|---|
| 多条定位线索 | researcher(日志) + researcher(代码路径) | 并行 |
| 根因涉及多模块交互 | researcher(数据流追踪) | 串行 |
| # | 标准 | 验证方式 |
|---|---|---|
| 1 | 根因已定位并有证据 | 含复现步骤 + 修复后验证结果 |
| 2 | 修复范围最小化 | diff 中无无关改动 |
Personalized writing assistant with style transfer, error memory, grammar checking, and long-term writing preferences. Use when users ask for writing polishing, style mimicry, iterative correction, bilingual grammar checks, or persistent writing preferences by domain.
Academic paper AI content detection and rewriting assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions. Supports .docx files, outputs reports and rewritten documents. Bilingual: Chinese & English.
解释代码、回答技术问题或概念问答时使用。直接给出答案，不启动开发流程。
评估系统架构、平台设计或高层结构时使用。输出风险检查清单。
Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.