Skills and MCP tagged “debugging”

investigate-first JuliusBrussee skill The skill keeps the agent in diagnosis mode: gather evidence, rank hypotheses, name the cause. Only then does it touch code. Claude Code CX Codex Cursor +1 104,400installs surgical-patch JuliusBrussee skill The skill constrains AI coding agents to the narrowest layer responsible for a bug. It prevents unwanted refactoring and demands focused regression checks. Claude Code CX Codex Cursor +1 103,800installs debugging-and-error-recovery addyosmani skill This skill guides an agent from reproducing a failure to checking the fix. Use it when tests fail, a build breaks, or runtime behavior differs from expectations. Claude Code CX Codex Cursor +1 62,200installs chrome-devtools official github skill Controls a live Chrome browser through Chrome DevTools MCP for page actions, debugging, and performance traces. Use it when an agent needs to inspect a web interface. GitHub Copilot 15,258installs mentoring-juniors official github skill This skill mentors junior developers through questions instead of ready-made answers. Use it for learning code, debugging, and getting started with Copilot. GitHub Copilot 6,900installs debugger VoltAgent Community subagent Diagnoses software failures, reads stack traces, and isolates root causes to fix elusive bugs. Helpful when logs alone do not explain a crash. Claude Code 13,459installs debugging-strategies Seth Hobson skill This skill gives an agent a step-by-step way to investigate bugs, crashes, and performance problems. Use it when a project behaves unexpectedly. Claude Code CX Codex Cursor 13,414installs memory-safety-patterns Seth Hobson skill This skill applies ownership, RAII, smart pointers, and resource management to Rust, C++, and C. Use it for systems code or memory-bug debugging. Claude Code CX Codex Cursor 11,746installs error-detective VoltAgent Community subagent A Claude subagent that digs into failures: correlates errors across services, traces cascades and suggests how to prevent them. Claude Code 7,557installs extract Alireza Rezvani skill Turns a recurring pattern or debugging fix into a standalone skill with instructions and examples. Use it when you want to carry a solution into another project. Claude Code 1,613installs ios-memgraph-leaks official OpenAI skill This skill captures a memgraph from a running simulator and breaks leaks down by type. Useful when objects stay alive after the flow that should release them. CX Codex GP ChatGPT 1,054installs connectivity-triage Seth Hobson skill Diagnoses active macOS network failures without modifying system settings. Helps isolate API timeouts, MCP disconnects, and DNS lookup issues. Claude Code CX Codex Cursor 743installs focused-fix Alireza Rezvani skill Enforces a five-phase protocol to repair broken features end-to-end. Helps when isolated bug fixes fail and an entire module needs systematic overhaul. Claude Code 600installs bug-reproduction-brief official github skill Turns a vague or intermittent bug report into a minimal reproduction with evidence. Use it when the failure depends on the environment or is hard to repeat. GitHub Copilot 62installs frontend-testing-debugging official OpenAI skill Guides coding agents through structured frontend testing, UI checks, and bug investigations. Runs validation loops using Browser tools or local Playwright. CX Codex GP ChatGPT 159installs bug-receipt official github skill Closes defects and incidents using a mandatory BUG RECEIPT with VERIFIED, PARTIAL, or BLOCKED status. It stops the agent from guessing repairs. GitHub Copilot 43installs steno-mode official github skill Compresses assistant responses by ~40% tokens using shorthand and symbols while preserving exact code, identifiers, and paths. GitHub Copilot 32installs ios-debugger-agent official OpenAI skill A Claude skill that builds and launches your iOS app on a simulator through XcodeBuildMCP, then lets the agent poke at the UI and read logs. CX Codex GP ChatGPT 105installs build-run-debug official OpenAI skill Build, launch, and debug macOS apps through a shell-first Xcode and Swift workflow when startup or runtime failures need investigation. CX Codex GP ChatGPT 60installs tugboat official github skill A GitHub Copilot skill for stalled, high-stakes tasks under stress. It keeps the original goal intact and relies on verified evidence. GitHub Copilot 11installs superpowers obra plugin The plugin guides an agent from task discussion and planning through subagent development, code review, debugging, and TDD. Use it when the workflow matters. Claude Code CX Codex ★ 304,495repo stars verification official Vercel Labs skill Traces and tests full user flows end-to-end across browser, API, and data layers when a dev server starts or something breaks. CX Codex GP ChatGPT 8installs spinning-up-deep-rl Alireza Rezvani skill A deep RL knowledge base for Claude Code, covering algorithms, policy gradients, and silent bugs. Use it when building or checking RL experiments. Claude Code 8installs investigation-mode official Vercel Labs skill A Codex and ChatGPT skill that runs debugging in order: runtime logs, workflow status, browser check, deploy and env. It fires on its own when you say something is stuck. CX Codex GP ChatGPT 6installs java-debugging official github skill A skill that walks the agent through finding a Java bug: reproduce, narrow down, test one hypothesis, attach a debugger. Useful once logs stop explaining anything. GitHub Copilot 1installs Sensei - Junior Mentor official github subagent A Socratic mentor agent that guides junior developers through probing questions instead of handing out answers. It helps beginners understand code and debug issues independently. GitHub Copilot ★ 40,369repo stars DevTools Regression Investigator official github subagent Reproduces UI regressions in the browser and pinpoints root causes using network and console evidence. GitHub Copilot ★ 40,369repo stars Clojure Interactive Programming official github subagent Clojure pair-programming agent enforcing REPL-first workflows before saving files. It prevents silent fallbacks and protects pure functional architecture. GitHub Copilot ★ 40,369repo stars Blueprint Mode official github subagent Executes strict workflows (Debug, Express, Main, Loop) to deliver clean fixes without guesses or conversational fluff. Best for disciplined code changes. GitHub Copilot ★ 40,369repo stars debugview microsoft skill A skill that drives the Sysinternals DebugView CLI, so your agent can capture Windows usermode and kernel debug output from the terminal. Claude Code GitHub Copilot 15installs