Skip to content
Agentmart
Submit a tool

systematic-debugging

Use to investigate unknown failures, business incident reports, or incomplete diagnoses after align, within active tasks, or on diagnosis-only requests; not…

Skill by cheng6563

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cheng6563-systematic-debugging

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use to investigate unknown failures, business incident reports, or incomplete diagnoses after align, within active tasks, or on diagnosis-only requests; not known-cause fixes.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/systematic-debugging

What's inside

Skill name
systematic-debugging
Description
Use to investigate unknown failures, business incident reports, or incomplete diagnoses after align, within active tasks, or on diagnosis-only requests; not known-cause fixes.
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# 系统化调试

先恢复原始诉求与已确认上下文,明确触发条件、应发生的业务行为、实际结果及受影响对象;调查期间用它们校准结论和修复方向。用户追问或提醒回看时,沿用原任务检查尚未闭合的因果链,继续已授权的调查。

## 取证与假设

1. 读取完整错误和相关上下文,复现问题;不能复现时先收集能区分假设的证据。
2. 沿调用链或数据流回溯,从症状追到最早偏离预期的位置。日志中的过滤、跳过或调用成功先作为实际执行事实,再核实该条件是否符合业务期望。例如接收人被权限过滤后,还需核实该权限实际控制的功能、目标角色的职责及相关调用方。
3. 用实际记录验证一个具体根因假设,一次只改变一个变量。源码疑点须核对本次输入、分支条件和运行记录是否命中;假设失败时撤销实验,再提出新假设。
4. 用户提供正常场景或其他对照时,比较两者从触发到最终业务效果的关键差异,核实对照是否达到预期。额外入口、重试或补偿可能掩盖共同缺陷;只查到调用成功仍需确认对象、结果及副作用。

查询或连接失败时,判断失败覆盖的证据范围,再尝试已有日志、其他查询入口、本地源码或配置等可用来源。连续三个假设失败时停止试改,重审证据、前提和架构,再选择能减少关键不确定性的调查路径。

## 根因与修复方向

根因结论须能解释本次故障及已提供的关键对照,并区分已证实的因果关系与待验证事项。存在会改变结论的证据缺口且仍有已授权、可执行的取证路径时,继续调查;有效路径均受阻时,报告已尝试路径、缺失证据及最小解除条件。

提出修复方向前,核对它能否恢复原诉求的业务效果,并沿本次已发现的相关入口推演其影响,例如遗漏、重复执行和状态变化。

本 Skill 在诊断期间不修改生产行为。只诊断任务交付根因、证据和必要修复方向。

从只读诊断转入首次修复时,转 `skill:align` 按其入口判断并承接实施,交接原诉求、根因证据、建议方向和待定事项。已有实施合同的任务则返回既定 Approach 继续修复、按 Evidence 验证业务结果及本次改动影响,不因定位完成而结束,也不重新询问测试方式或交付终点。

From cheng6563/litepowers, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 24, 2026 (5 days ago)
Last release
Oct 24, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from cheng6563

Cite this page

systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/cheng6563-systematic-debugging (last updated 2026-10-24)