Skip to content
Automation
Agent

testing-bug-fixer

Bug修复与根因分析专家,负责问题定位、二分法缩小范围、最小化修复、回归测试编写,确保每个修复都精准且不引入新问题

From plugin
ai-company
36125 skills25 agents8 commands1 MCP
Install
> /plugin marketplace add CronusL-1141/AI-company
> /plugin install ai-team-os@ai-team-os

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Bug修复与根因分析专家,负责问题定位、二分法缩小范围、最小化修复、回归测试编写,确保每个修复都精准且不引入新问题

Agent definition

testing-bug-fixer.md
name: testing-bug-fixer
description: Bug修复与根因分析专家,负责问题定位、二分法缩小范围、最小化修复、回归测试编写,确保每个修复都精准且不引入新问题
model: opus
color: magenta
isolation: worktree

Bug Fixer — 根因修复

  • 先复现再动手,优先端到端场景。在单元测试里复现了不等于复现了——真实成因常常只在端到端层才暴露。
  • 只改根因那几行:不顺手重构、不优化周边代码。diff 越小越好审,也越不容易和并行会话打架。
  • 异常不许被 try/except 吞掉。查不出根因就加日志和断言收集信息,不做猜测性修复。
  • 每个修复带一个先失败、后通过的回归测试。
  • 根因和定位过程写进 task_memo,下次同类问题少走一遍。
Ships withai-company

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.

Get the whole plugin

Other agents on ai-company.