Stop guessing at fixes. A 4-phase root-cause discipline (reproduce → isolate → hypothesize → verify) that forces your coding agent to find the real cause before touching code. The most-copied debugging skill in the Agent Skills ecosystem.
/systematic-debugging My checkout API returns 500, but only when two users pay at the same time
你能得到
- A 4-phase root-cause protocol (reproduce, isolate, hypothesize, verify) your agent follows before writing any fix
- Rules that stop symptom fixes and speculative patches
- Techniques for flaky and intermittent failures
- Condition-based waiting patterns (with a TypeScript example)
适合场景
- Any bug, test failure, or unexpected behavior
- Flaky tests and intermittent production issues
- Bugs that already survived one "quick fix"
不适合
- Greenfield feature work (use test-driven-development)
- Performance profiling (use diagnosing-bugs)
- 仓库
- obra/superpowers
- Stars
- 0
- 分类
- 编程开发
- 包含 skills
- 1
独家内容
托管在 SkillStack 站内——购买后可查看完整 markdown。
--- name: systematic-debugging description: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes ---
Systematic Debugging
Overview
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
**Violating the…
下载与安装
更新内容: Initial SkillStack curated release: original MIT-licensed content repackaged as an install-ready ZIP with attribution.
登录用户免费下载。
1. 下载 ZIP
点击上方按钮下载打包好的 skill，内含 SKILL.md 及全部配套文件。
2. 解压到 agent 的 skills 目录
解压后确保 SKILL.md 直接位于以 skill 命名的文件夹内：
unzip systematic-debugging-v1.0.0.zip -d ~/.claude/skills/systematic-debugging/各 Agent 的 skills 目录
- Claude Code
- ~/.claude/skills
- Cursor
- ~/.cursor/skills
- Codex
- ~/.codex/skills
- GitHub Copilot
- ~/.copilot/skills
3. 重启你的 agent
下次启动时 agent 会自动识别新 skill，直接问它能做什么。
评价
相关技能
Diagnosing Bugs
mattpocock/skills
A battle-tested diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test. Includes a human-in-the-loop helper script. From a working engineer's daily setup.
Claude Code · Codex · Cursor
Test-Driven Development
obra/superpowers
RED-GREEN-REFACTOR with iron laws: write the test first, watch it fail, then write the minimal code to pass. Turns your agent into a disciplined TDD practitioner that never ships untested code.
Claude Code · Codex · Cursor · Copilot +1
Code Review & Quality
addyosmani/agent-skills
Multi-axis code review with severity gates (Critical/High/Medium/Low) across correctness, readability, architecture, security, and performance. By Addy Osmani (Google Chrome). Nothing merges without a verdict.
Claude Code · Codex · Cursor · Copilot
Tidy — AI Code Review
mblode/agent-skills
A diff/PR reviewer built specifically for agent-written code. Catches AI-slop patterns that line-by-line reviews miss, tiers findings as confirmed vs plausible, and can apply the fixes itself. The differentiator in your review stack.
Claude Code · Codex · Cursor