debugging SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

debugging from autopus-ai/autopus-adk is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add autopus-ai/autopus-adk/debugging@git:20260928.877a6b1

Pins git:20260928.877a6b1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
autopus-ai/autopus-adk
Path
.omp/skills/debugging/SKILL.md
Versions recorded
2
Latest version
git:20260928.877a6b1, committed Sep 28, 2026
First version recorded
Aug 26, 2026
Size
10,278 bytes
Repository stars
110
License
MIT

체계적 디버깅 및 버그 수정 스킬.

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

# Debugging Skill

버그를 체계적으로 재현하고 근본 원인을 분석하여 수정하는 스킬입니다.

## 핵심 원칙

**이 버그에 red가 되는 피드백 루프를 먼저 만든다.** 루프가 있으면 이분법·가설 검증·계측이
그것을 소비해 원인에 닿는다. 루프가 없으면 코드를 아무리 들여다봐도 못 찾는다. 루프의 대표
형태가 재현 테스트다: 수정 전 FAIL, 수정 후 PASS.

탐색할 때 `CONTEXT.md`(있으면)로 관련 모듈의 어휘를 잡고, 그 영역의 Lore(`auto why`)를 확인한다.
둘 다 없으면 대상 상수·설정의 doc comment와 Makefile/CI 주석을 Lore로 읽는다 — "예산을 키우는
방식은 세 번 실패했다" 같은 한 줄이 가설 순위를 바꾼다.

**비밀은 먼저 가린다.** 명령·출력·캡처를 보여 줄 때 credential은 `<REDACTED>`로 바꾼다. 루프는
env var를 읽게 만들어 값이 출력에 나오지 않게 한다. 가린 출력으로 진단이 안 되면 그렇다고 말하고
사용자에게 묻는다.

## 디버깅 프로세스

### 1단계: 피드백 루프 만들기

**이 단계가 스킬의 전부다.** 나머지는 기계적이다. 여기에 불균형하게 많은 노력을 쓴다.
공격적으로, 창의적으로, 포기하지 않는다.

루프를 만드는 방법(대략 이 순서로):

1. 버그에 닿는 seam에서의 **실패 테스트** — unit, integration, e2e
2. 개발 서버에 대한 **curl/HTTP 스크립트**
3. fixture 입력으로 **CLI 호출**, stdout을 known-good 스냅샷과 diff
4. UI를 몰고 DOM/console/network를 단언하는 **headless browser 스크립트**
5. 실제 요청/페이로드/이벤트 로그를 저장해 격리된 코드 경로로 **replay**
6. 시스템 최소 부분집합만 띄우는 **throwaway harness**
7. **이미 있는 flaky 테스트**라면 바이너리를 한 번 빌드(`go test -c`)하고 K개를 동시에
   `-count=N`으로 돌려 부하를 재현한다. 라운드마다 바이너리/서브테스트 red 수를 표로 집계한다
8. "가끔 틀린다"면 무작위 입력 1000개로 **property/fuzz 루프**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add autopus-ai/autopus-adk/debugging@sha256:f1deaa766dec09e5

The line at the top of this page pins the label git:20260928.877a6b1, 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_jcrkzaibvj5slw5x.svg)](https://markdownregistry.com/a/art_jcrkzaibvj5slw5x)

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

Versions

The registry has recorded 2 versions of this file, between Aug 26, 2026 and Sep 28, 2026, about one every 33 days.

versioncommittedcommitsizeaudit
git:20260928.877a6b1 latest2026-09-28 877a6b1 10,278 BA view · diff
git:20260826.34a9b202026-08-26 34a9b20 2,753 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 (10278 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

autopus-ai/autopus-adk · 110 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jcrkzaibvj5slw5x
GET https://markdownregistry.com/api/v1/resolve?ref=autopus-ai/autopus-adk/debugging
GET https://markdownregistry.com/api/v1/blob/f1deaa766dec09e5b23ea4340bfc20d1944f2dfe3a33678c0d548e5d406db0c9

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 autopus-ai/autopus-adk

agent-pipeline SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/agent-pipeline/SKILL.md · Multi-agent pipeline orchestration skill
git:20261017.c6d588d · audit A · 110 stars
auto-canary SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-canary/SKILL.md · 배포 검증 — build, E2E, 브라우저 건강 검진을 실행합니다
git:20260928.877a6b1 · audit A · 110 stars
auto-dev SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-dev/SKILL.md · 풀 사이클 개발 — plan → go → sync를 순차 실행합니다
git:20260826.34a9b20 · audit A · 110 stars
auto-doctor SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-doctor/SKILL.md · 상태 진단 — 하네스 설치 상태와 플랫폼 wiring을 점검합니다
git:20260826.34a9b20 · audit A · 110 stars
auto-fix SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-fix/SKILL.md · 버그 수정 — 재현과 최소 수정 중심으로 문제를 해결합니다
git:20261009.e75c860 · audit A · 110 stars
auto-go SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-go/SKILL.md · SPEC 구현 — SPEC 문서를 기반으로 코드를 구현합니다
git:20261017.384439a · audit A · 110 stars
auto-goal SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-goal/SKILL.md · goal 관리 — 현재 세션이 지원하는 목표 생성, 상태 확인, 완료·차단 처리를 연결합니다
git:20260928.877a6b1 · audit A · 110 stars
auto-idea SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-idea/SKILL.md · 아이디어 브레인스토밍 — 멀티 프로바이더 토론과 ICE 평가로 아이디어를 정리합니다
git:20261009.e75c860 · audit A · 110 stars
auto-map SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-map/SKILL.md · 코드베이스 분석 — 구조, 엔트리포인트, 의존성을 빠르게 요약합니다
git:20260826.34a9b20 · audit A · 110 stars
auto-plan SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-plan/SKILL.md · SPEC 작성 — 코드베이스 분석 후 EARS 요구사항, 구현 계획, 인수 기준을 생성합니다
git:20261009.e75c860 · audit A · 110 stars
auto-qa SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-qa/SKILL.md · QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence
git:20261009.e75c860 · audit A · 110 stars
auto-review SKILL.md skill
autopus-ai/autopus-adk · .omp/skills/auto-review/SKILL.md · 코드 리뷰 — TRUST 5 기준으로 변경된 코드를 리뷰합니다
git:20261009.e75c860 · audit A · 110 stars

Every file in autopus-ai/autopus-adk

Other files named debugging

debugging SKILL.md skill
code-yeongyu/oh-my-openagent · packages/shared-skills/skills/debugging/SKILL.md · Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and…
git:20260930.888c46f · audit A · 70,277 stars
debugging SKILL.md skill
notque/vexjoy-agent · skills/process/debugging/SKILL.md · Debugging: guided diagnosis of application bugs, and post-mortem of failed agent sessions.
git:20260919.28d30f9 · audit A · 442 stars
debugging SKILL.md skill
romiluz13/cc10x · plugins/cc10x/skills/debugging/SKILL.md · Use when diagnosing a defect or regression: feedback loop FIRST, root cause before fix, blast radius after fix. Covers…
git:20261007.84fdb74 · audit A · 165 stars
debugging SKILL.md skill
insajin/autopus-adk · .omp/skills/debugging/SKILL.md · 체계적 디버깅 및 버그 수정 스킬
git:20260928.877a6b1 · audit A · 110 stars
debugging SKILL.md skill
mnemosyne-systems/orangu · contrib/skills/debugging/SKILL.md · Investigate a bug methodically before proposing a fix
git:20260620.6528cab · audit A · 50 stars
debugging SKILL.md skill
akillness/jeo-skills · .agent-skills/debugging/SKILL.md · Run a reproduce → isolate → verify debugging workflow for concrete bugs, regressions, flaky failures, and…
v2.1 · audit A · 48 stars
debugging SKILL.md skill
iliaal/ai-skills · skills/debugging/SKILL.md · Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests…
git:20260926.7b0520a · audit A · 43 stars
debugging SKILL.md skill
iliaal/whetstone · distillery/generated-skills/debugging/SKILL.md · Systematic root-cause debugging: reproduce, investigate, hypothesize, fix with verification. Use when asked to "debug…
git:20260227.215f429 · audit A · 35 stars

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