systematic-debugging SKILL.md skillA

systematic-debugging from jimyag/dotfiles is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jimyag/dotfiles/systematic-debugging@git:20261015.f79eac0

Pins git:20261015.f79eac0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jimyag/dotfiles
Path
skills/systematic-debugging/SKILL.md
Versions recorded
7
Latest version
git:20261015.f79eac0, committed Oct 15, 2026
First version recorded
Sep 5, 2026
Size
8,342 bytes
Repository stars
11
License
MIT

在缺陷、测试或构建失败、异常行为和反复修错时使用;先建立可区分假设的反馈环和根因证据,再按用户授权决定是否修复。普通代码审查、明确的小修改或只执行已有测试不触发。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 系统化排查问题

目标是找到能解释现象的根因,并用同一个反馈环证明修复有效。诊断请求默认只定位和报告;用户要求修复时才修改代码。

## 核心循环

1. **固定现象**:记录错误、环境、输入、期望、实际结果和最近已知正常状态。
2. **建立反馈环**:优先使用最小测试、复现命令、页面路径、日志条件或可观察状态,使问题能失败、复跑并在修复后变绿。这一步最值得投入:有了能在这个缺陷上变红的命令,后面的二分、假设和观测都只是在消费它。构造方法、收紧和提高复现率见 [references/advanced-modes.md](references/advanced-modes.md)。
3. **收集独立证据**:日志、堆栈、配置差异、近期变更、相关源码、网络和环境状态可以并行读取,但结论必须汇入同一证据链。
4. **排序假设**:先列出 3-5 个按可能性排序的假设再开始验证,只列一个容易锚定在第一个想法上。每个假设写出它的预测:“如果原因是 X,改动 Y 会让问题消失”;说不出预测的不算假设。用户在场时把排序给用户看一眼,他们常有能立刻重排的领域信息;不等待回复,用户不在时按自己的排序继续。维护轻量矩阵:

   `假设 | 支持证据 | 反证 | 置信度 | 下一步最小检查`

5. **验证一个假设**:用最小观测或可逆改动获取能证实或证伪的结果,不同时改变多个变量。环境支持时优先用调试器或 REPL 查看,一个断点胜过十条日志;加日志时给每条临时日志加唯一前缀(如 `[DEBUG-a4f2]`),结束时按前缀搜索并全部删除。
6. **更新模型**:记录被排除方向;同一症状未消失时停止叠补丁,回到矩阵重新排序。
7. **修复与回归**:根因明确且用户授权修复后,做最小修改;先用原反馈环证明问题消失,再按风险扩大验证。修复授权不包含提交、推送、发布或破坏性操作。
8. **同型排查**:宣布修复前,提炼触发缺陷的函数、调用形状、选择器、锁或校验缺口,在仓库内搜索同类位置,逐项标注;方法见 [references/advanced-modes.md](references/advanced-modes.md)。
9. **事后追问**:修复完成后问一句“什么能预防这个缺陷?”。答案涉及架构(没有合适的测试接缝、调用方纠缠、隐式耦合)时,把具体情况作为建议提出,不在本次修复中扩大范围。正确的假设写进提交信息或 PR 说明。

在改代码前,应能用一句话表达当前假设:`我认为根因是 X,因为证据 Y;结果 Z 会证伪它。`X 要具体到文件、函数、行或触发条件;“状态管理问题”这类说法无法证伪,还不算假设。假设必须解释全部已观察症状,包括报告人认为无关的症状;只解释首个症状的是表层猜测。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jimyag/dotfiles/systematic-debugging@sha256:ac891a2747d10c39

The line at the top of this page pins the label git:20261015.f79eac0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cx2tlo56uay2zjz2.svg)](https://markdownregistry.com/a/art_cx2tlo56uay2zjz2)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 7 versions of this file, between Sep 5, 2026 and Oct 15, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261015.f79eac0 latest2026-10-15 f79eac0 8,342 BA view · diff
git:20261015.2c8093f2026-10-15 2c8093f 6,941 BA view · diff
git:20260929.603248c2026-09-29 603248c 4,451 BA view · diff
git:20260919.7add2782026-09-19 7add278 4,098 BA view · diff
git:20260919.361331b2026-09-19 361331b 8,677 BA view · diff
git:20260905.64eb1872026-09-05 64eb187 7,698 BA view · diff
git:20260905.751659e2026-09-05 751659e 7,581 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8342 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jimyag/dotfiles · 11 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cx2tlo56uay2zjz2
GET https://markdownregistry.com/api/v1/resolve?ref=jimyag/dotfiles/systematic-debugging
GET https://markdownregistry.com/api/v1/blob/ac891a2747d10c396163f070a453660f01e39077491fa8fc3dac23e72e8eaf9b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jimyag/dotfiles

absorb-skill SKILL.md skill
jimyag/dotfiles · skills/absorb-skill/SKILL.md · 用户想从外部技能生态寻找、比较可复用的 Agent Skill,或要求把外部 Skill、项目资料或历史经验中的可复用内容吸收到已有 Skill 时使用;对照来源与目标后修改目标…
git:20261019.0e15234 · audit B · 11 stars
agent-health SKILL.md skill
jimyag/dotfiles · skills/agent-health/SKILL.md · 在审计 AGENTS/CLAUDE 指令、MCP、hooks、工具权限、验证入口、跨工作流配置漂移,或技能库的规范、可移植性、触发重叠、上下文加载、脚本和评测时使用;不用于创建技能,不因普通任务涉及配置就触发。
git:20261019.0e15234 · audit B · 11 stars
architecture-decision-record SKILL.md skill
jimyag/dotfiles · skills/architecture-decision-record/SKILL.md · 已有具体技术决策,需要判断是否记录 ADR,或创建、更新、替代 ADR 时使用。
git:20260905.751659e · audit A · 11 stars
brainstorming SKILL.md skill
jimyag/dotfiles · skills/brainstorming/SKILL.md · 在目标、范围或成功标准不清,存在接近的实现方案,或高成本假设可能导致返工时使用;用户要求拷问、追问或 grill 方案时也使用。适用于实现前澄清需求、挑战隐含前提并收敛到一个推荐方案;不用于已经明确的小改动。
git:20261015.bb74506 · audit A · 11 stars
codecov-coverage SKILL.md skill
jimyag/dotfiles · skills/codecov-coverage/SKILL.md · 在需要查询 Codecov 仓库、PR、提交、patch 或文件覆盖率,比较覆盖率变化,或诊断 codecov/project、codecov/patch 等覆盖率检查失败时使用。
git:20260905.751659e · audit A · 11 stars
frontend-design-review SKILL.md skill
jimyag/dotfiles · skills/frontend-design-review/SKILL.md · 在确定或审查前端页面、落地页、作品集和重新设计的视觉方向时使用;区分只读审查、方向建议和已授权实现,并用真实截图或渲染验证视觉结论。不用于纯业务逻辑、状态管理或已经有明确设计稿的机械实现。
git:20261015.b377f6b · audit A · 11 stars
gh-stack SKILL.md skill
jimyag/dotfiles · skills/gh-stack/SKILL.md · 使用 gh-stack GitHub CLI 扩展管理堆叠分支和拉取请求。适用于创建、推送、变基、同步、切换、查看、重组或合并相互依赖的 PR 链及堆叠差异。
v0.0.9 · audit A · 11 stars
linux-performance-analysis SKILL.md skill
jimyag/dotfiles · skills/linux-performance-analysis/SKILL.md · 诊断 Linux 主机或容器的缓慢、高负载、资源压力及网络性能异常,定位瓶颈与触发进程;不用于普通命令语法查询。
git:20260905.751659e · audit A · 11 stars
loop-on-ci SKILL.md skill
jimyag/dotfiles · skills/loop-on-ci/SKILL.md · 在已有 GitHub PR 需要持续观察 Actions 检查、读取失败作业日志、修复问题、重新运行并跟到全部检查变绿时使用。适用于围绕同一个 PR 反复验证,而不是一次性状态查询。
git:20261015.b377f6b · audit A · 11 stars
pull-request SKILL.md skill
jimyag/dotfiles · skills/pull-request/SKILL.md · 创建 GitHub PR、更新标题或正文、填写 PR 模板,或准备人工发布内容时使用;不用于代码审查和 CI 修复。
git:20260919.361331b · audit A · 11 stars
requesting-code-review SKILL.md skill
jimyag/dotfiles · skills/requesting-code-review/SKILL.md · 用户要求审查当前代码差异或 PR 时使用,默认只读;不用于处理已收到的评审意见。
git:20261019.0e15234 · audit A · 11 stars
runtime-verification SKILL.md skill
jimyag/dotfiles · skills/runtime-verification/SKILL.md · 在提交或交付非平凡代码改动前,需要确认改动在真实运行面上按预期工作时使用;通过 CLI、接口、界面、公开包入口或代理行为驱动改动路径并留存证据。只改测试、文档或无运行面的类型声明时不触发;定位缺陷使用…
git:20261015.2c8093f · audit A · 11 stars

Every file in jimyag/dotfiles

Other files named systematic-debugging

systematic-debugging SKILL.md skill
obra/superpowers · skills/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
git:20261010.bb92a77 · audit A · 302,424 stars
systematic-debugging SKILL.md skill
jnmetacode/superpowers-zh · skills/systematic-debugging/SKILL.md · 遇到任何 bug、测试失败或异常行为时使用,在提出修复方案之前执行
v1.0.0 · audit A · 8,348 stars
systematic-debugging SKILL.md skill
mvschwarz/openrig · skills/_canonical/process/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
git:20261006.d1e9d5e · audit A · 7,989 stars
systematic-debugging SKILL.md skill
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
git:20261006.d1e9d5e · audit A · 7,989 stars
systematic-debugging SKILL.md skill
cbrock84/headcount · plugins/technology/skills/systematic-debugging/SKILL.md · Finds the root cause of a bug, test failure, or unexpected behavior before proposing any fix. Use this whenever…
git:20260901.aa45383 · audit A · 2,076 stars
systematic-debugging SKILL.md skill
a5c-ai/babysitter · library/methodologies/superpowers/skills/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause…
git:20260601.da7723a · audit A · 1,862 stars
systematic-debugging SKILL.md skill
a5c-ai/babysitter · library/methodologies/rpikit/skills/systematic-debugging/SKILL.md · Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and…
git:20260605.09bdbf7 · audit A · 1,862 stars
systematic-debugging SKILL.md skill
ganyuanran/aegis · skills/systematic-debugging/SKILL.md · Use when encountering a bug, test failure, or unexpected behavior, before proposing fixes
git:20261020.2ff21fc · audit A · 1,371 stars

Browse by kind, by grade A, or by owner.