Debugging Agent Skills

Debugging

185 skills
alirezarezvani
focused-fix
Systematically repair a broken feature or module by scoping, tracing dependencies, diagnosing all issues, fixing them in order, and verifying end-to-end.
20.4k
addyosmani
performance-optimization
Measures application performance first, identifies bottlenecks, and applies targeted fixes for frontend and backend systems.
69.5k
addyosmani
debugging-and-error-recovery
Provides a structured triage process for debugging test failures, build errors, runtime bugs, and production incidents, including steps to reproduce, localize, fix, and guard against recurrence.
69.5k
obra
systematic-debugging
Find root causes of bugs, test failures, or unexpected behavior before proposing any fixes.
247k · bundle
obra
dispatching-parallel-agents
Dispatch multiple independent tasks to parallel agents for faster debugging and problem-solving.
247k
nvidia
cuopt-developer
Modify, build, test, debug, and contribute to the NVIDIA cuOpt codebase (C++/CUDA, Python, server, CI). Includes guidance for solver internals, pull requests, DCO signoff, and code conventions.
2.2k · bundle
nvidia
dali-dynamic-mode
Write, review, and migrate code using NVIDIA DALI's imperative dynamic-mode API for efficient data loading and preprocessing.
2.2k · bundle
nvidia
mcore-create-issue
Investigate a failing GitHub Actions job, extract the root cause, and file a well-structured bug issue against NVIDIA/Megatron-LM.
2.2k · bundle
nvidia
mcore-linting-and-formatting
Lint and format Python code for Megatron-LM using ruff, black, isort, pylint, and mypy, with commands for autoformatting and import ordering.
2.2k · bundle
vuejs-ai
vue-debug-guides
Diagnose and fix Vue 3 runtime errors, warnings, async failures, and SSR/hydration issues with targeted debugging guides.
2.7k · bundle
affaan-m
gateguard
Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.
226k
affaan-m
error-handling
Provides patterns for robust error handling across TypeScript, Python, and Go, including typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.
226k
affaan-m
orch-fix-defect
Reproduce a bug as a failing regression test, fix until green, review, and commit via a delegated pipeline.
226k
affaan-m
click-path-audit
Trace every user-facing button through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI inconsistent.
226k
affaan-m
nodejs-keccak256
Prevents Ethereum hashing bugs by distinguishing Keccak-256 from Node's NIST SHA3-256, with code examples for ethers, viem, and web3.js.
226k
affaan-m
agentic-engineering
Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.
226k
antigravity
github
Interact with GitHub issues, pull requests, Actions runs, and the GitHub API using the `gh` CLI.
42.4k · bundle
antigravity
cpp-pro
Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.
42.4k · bundle
antigravity
gdb-cli
Analyze core dumps, debug live processes, and investigate crashes, deadlocks, and memory issues in C/C++ programs using GDB with source code correlation.
42.4k
antigravity
debugger
Provides a structured debugging workflow for analyzing errors, test failures, and unexpected behavior, including root cause analysis and fix recommendations.
42.4k
antigravity
java-pro
Provides expert guidance on modern Java 21+ development, including virtual threads, Spring Boot 3.x, GraalVM, and cloud-native patterns for building scalable enterprise applications.
42.4k
antigravity
mathguard
Guides AI agents to apply advanced mathematical and probabilistic techniques (Bloom filters, HyperLogLog, FFT, etc.) for large-scale data problems where classical algorithms are optimal but math offers better asymptotic bounds.
42.4k
antigravity
scala-pro
Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in Apache Pekko, Akka, Spark, ZIO/Cats Effect, and reactive architectures.
42.4k
antigravity
bug-hunter
Systematically find and fix bugs using proven debugging techniques, tracing from symptoms to root cause, implementing fixes, and preventing regression.
42.4k · bundle
antigravity
golang-pro
Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices.
42.4k
antigravity
python-pro
Write and review modern Python 3.12+ code with async patterns, performance optimization, and production-ready practices using the latest ecosystem tools.
42.4k
cloudflare
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices, covering configuration, request handling, architecture, observability, code patterns, and security.
2.1k · bundle
openai
gh-fix-ci
Debug and fix failing GitHub Actions PR checks by inspecting logs, summarizing failures, and implementing fixes after approval.
23.3k · bundle
openai
playwright-interactive
Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.
23.3k · bundle
android
android-cli
Create, build, and debug Android apps using the official Android CLI tool for project creation, SDK management, emulator control, and UI inspection.
6.1k · bundle
android
r8-analyzer
Analyzes Android build files and R8 keep rules to identify redundancies, broad package-wide rules, and rules that subsume library consumer keep rules.
6.1k · bundle
android
perfetto-trace-analysis
Analyzes Perfetto traces to find the root cause of latency, memory, or jank issues in Android apps.
6.1k · bundle
dotnet
mcp-csharp-debug
Run, debug, and interactively test C# MCP servers locally with IDE configuration, MCP Inspector, and GitHub Copilot Agent Mode integration.
4k · bundle
dotnet
dotnet-pinvoke
Correctly call native C/C++ libraries from .NET using P/Invoke and LibraryImport, covering function signatures, string marshalling, memory lifetime, SafeHandle, and cross-platform patterns.
4k · bundle
dotnet
eval-performance
Diagnose and improve MSBuild project evaluation performance by analyzing phases, glob patterns, import chains, and property functions.
4k
dotnet
dotnet-trace-collect
Guides developers through capturing diagnostic artifacts to diagnose production .NET performance issues, including tool selection and data collection across Windows, Linux, containers, and Kubernetes.
4k · bundle