AI agent skills for debugging
Debugging skills exist because agents, like people, want to fix the first plausible cause and move on. The useful ones force the sequence: reproduce, isolate, form a hypothesis that predicts something, test that prediction, only then edit. They are worth installing precisely when you are in a hurry, which is exactly when you will not want to use them.
People land here searching for “claude code debugging skill”, “agent skill root cause analysis”, “systematic debugging skill”.
260 debugging skills Refine in search →
-
obra Bundle Systematic DebuggingFind root causes of bugs, test failures, or unexpected behavior before proposing any fixes.
Audited 247k -
rajanthar Bundle Ce DebugSystematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.
Audited 0 -
bobmatnyc Bundle Root Cause TracingSystematically trace bugs backward through call stack to find original trigger
Audited 71 -
lucassantana-dev Bundle DebugSystematic root-cause analysis for bugs, errors, and unexpected behavior
Audited 1 -
livelybug Skill Gstack Openclaw InvestigateUse when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.
0 -
pproenca Bundle Root CauseUse when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
-
poteto Skill DebuggingSystematic root-cause debugging methodology. Use for any technical problem — errors, failures, unexpected behavior, or when stuck. Triggers: "debug", "fix this", "what's wrong", "investigate".
-
cogine-ai Skill InvestigateSystematic root-cause debugging. Use when: diagnosing bugs, investigating failures, debugging flaky tests, tracing unexpected behavior. Triggers on: '/investigate', 'debug this', 'why is this failing', 'find the root cause', 'flaky test'.
-
ahonn Skill InvestigateSystematic root-cause debugging. Use when: diagnosing bugs, investigating failures, debugging flaky tests, tracing unexpected behavior. Triggers on: '/investigate', 'debug this', 'why is this failing', 'find the root cause', 'flaky test'.
-
atomicinnovation Skill Research IssueInvestigate production issues and bugs through hypothesis-driven debugging. Accepts stacktraces, logs, error messages, or vague behavioral descriptions and produces a root cause analysis.
-
johnlindquist Skill DebugUnified debugging workflow enforcing root cause protocol. Investigate → Understand → Reason → Fix. Use when debugging bugs, errors, or unexpected behavior.
- obra Bundle Root Cause Tracing
Systematically trace bugs backward through call stack to find original trigger
Audited 247k -
luokai0 Bundle DebuggingSystematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. For validating bug reports before fixing, use bug-reproduction-validator agent.
10 -
luan Skill DebuggingSystematic root cause investigation before proposing fixes. Triggers: bugs, test failures, unexpected behavior, 'why is this failing', 'not working', 'broken'.
-
swestash Bundle Bug InvestigatingSystematic debugging and root cause analysis using structured methodology — reproduce, isolate, hypothesize, verify. Triggers: this doesn't work, I'm getting an error, something is broken, bug, debug this, why is this happening, unexpected behavior, regression, root cause, stack trace, error message.
-
nvidia Bundle Mcore Create IssueInvestigate a failing GitHub Actions job, extract the root cause, and file a well-structured bug issue against NVIDIA/Megatron-LM.
Audited 2.2k -
arcadeai Skill DebugRoot cause debugging before fixes. Use when investigating bugs, diagnosing test failures, troubleshooting unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline.
-
timlai666 Skill InvestigateSystematic debugger. Root cause before any fix. Iron Law: no fixes without investigation. This skill MUST be invoked when the user reports a bug, and MUST NOT be skipped because the cause looks obvious. SHOULD also be invoked on 為什麼會這樣, 壞掉了, failing, broken, or flaky. Hypothesis-driven — form 3-5 hypotheses, test them cheaply before touching code. Stop after 3 failed fix attempts and escalate.
1 -
costa-marcello Bundle DebugGuides systematic root-cause debugging through four phases. Use when encountering any bug, test failure, or unexpected behaviour, before proposing fixes.
-
professor-gpt Bundle Debug DetectiveMethodical debugging assistant that diagnoses bugs, runtime errors, memory leaks, and race conditions using structured root cause analysis.
-
flowerf19 Skill Debug InvestigatorSystematically investigate the root cause of a bug, test failure, performance issue, or unexpected behavior before any fix.
Audited -
antigravity Bundle Bug HunterSystematically find and fix bugs using proven debugging techniques, tracing from symptoms to root cause, implementing fixes, and preventing regression.
42.4k -
05-deepak-patidar Skill Root Cause DebuggingSystematic debugging and incident diagnosis — finding the actual cause instead of patching symptoms. Use when investigating a bug, a production incident, flaky behavior, "works on my machine", data corruption, or when the user says "debug", "why is this happening", "broken", "investigate", "root cause", or pastes an error/stack trace.
-
duthaho Skill Investigate Root CauseUse when encountering ANY bug, error, test failure, or unexpected behavior. Activate for keywords like "bug", "error", "failing", "broken", "doesn't work", "unexpected", "crash", "exception", "TypeError", "undefined", stack traces, or any error message. Also trigger when tests fail unexpectedly, when behavior differs from expectations, when investigating production incidents, or when flaky/intermittent issues appear. Investigation produces evidence and a written hypothesis before any fix is attempted. Always investigate root cause before proposing fixes -- never guess at solutions.
How to install a debugging skill
- Compare the skills. Read the debugging skills below — each page shows the full SKILL.md, its safety verdict, and the capabilities it declares.
- Install it. Run npx skillmds@latest add <owner>/<name>. The CLI writes the skill into every agent directory it detects, or use --agent to pin one.
- Use it. Restart your agent. It loads the skill on demand the next time you ask for something that matches — you do not have to name the skill.
What makes a good debugging skill?
Debugging skills exist because agents, like people, want to fix the first plausible cause and move on. The useful ones force the sequence: reproduce, isolate, form a hypothesis that predicts something, test that prediction, only then edit. They are worth installing precisely when you are in a hurry, which is exactly when you will not want to use them.
Every skill listed here is a plain SKILL.md file in the format Anthropic documents for Agent Skills, read unchanged by Cursor, OpenAI Codex and 60+ agents. Each passes a safety review before it is publicly listed; the verdict and declared capabilities are on every skill's page.
Frequently asked questions
What is an agent skill for debugging?
Debugging skills exist because agents, like people, want to fix the first plausible cause and move on. The useful ones force the sequence: reproduce, isolate, form a hypothesis that predicts something, test that prediction, only then edit. They are worth installing precisely when you are in a hurry, which is exactly when you will not want to use them.
How is a debugging skill different from just asking the agent to fix a bug?
Asking for a fix gets you a fix for whatever the agent guessed first. A debugging skill makes it state the hypothesis and the evidence before it touches code, which is what catches the case where the obvious cause is not the real one. The cost is a few extra steps; the payoff is not shipping the wrong fix twice.
Which agents can use these debugging skills?
Any agent that reads SKILL.md files: Claude Code, Claude.ai, Cursor, OpenAI Codex, Windsurf, OpenCode and 60+ others. The format is not vendor-specific, so the same file works everywhere — each agent just keeps its skills in a different directory, listed at /agents.
Are these debugging skills free?
Yes. Searching, reading and installing skills on SkillMD is free and needs no account. Individual skills carry their own licence, shown on each skill's page.