Browse the directory

MIT-licensed skill and plugin framework by Jesse Vincent for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and other AI coding agents, covering brainstorming, planning, TDD, systematic debugging, subagent-driven development, code review, git worktrees, and finish-the-branch workflows.

Community reusable agent prompt for debugging Claude Code behind corporate HTTP proxies and mTLS using official network-config docs: HTTP_PROXY variables, certificate trust, downloads reachability, and remote MCP URL failures.

Official Chrome DevTools MCP server that lets Claude inspect and debug a live Chrome browser, capturing performance traces, network activity, console messages, and DOM state through the Chrome DevTools Protocol.

Official visual testing and debugging tool for Model Context Protocol servers.

Official MCP server for agent-device, Callstack's device automation CLI for inspecting, controlling, debugging, recording, and collecting evidence from iOS, Android, TV, macOS, Linux, React Native, Expo, Flutter, and native apps.

Official remote MCP server for connecting Claude and other AI coding tools to Cypress Cloud runs, failures, flake data, accessibility reports, and UI Coverage results.

MCP server that connects Claude to Windows CDB/WinDbg for crash dump discovery, dump triage, remote debugging targets, custom debugger commands, debugger cleanup, and CTRL+BREAK interrupts.

MCP server for controlling the Godot game engine, launching the editor, running projects, capturing debug output, and editing scenes and resources.

JADX plugin and companion Python MCP server that lets Claude inspect, search, refactor, and debug decompiled Android APKs from JADX-GUI.

Slash command that triages a failing GitHub Actions run: it pulls the failed job logs with the GitHub CLI, isolates the first real error, classifies the failure (test, lint, type, build, dependency, or flaky), and proposes a targeted, minimal fix with the exact command to reproduce it locally.

MIT-licensed CDP browser-control harness from Browser Use that lets Claude Code, Codex, and other coding agents connect to a real or cloud Chrome browser, use screenshots and coordinate clicks, edit task-specific helpers, and optionally learn reusable domain skills for web automation workflows.

Expert skill for reviewing Playwright trace artifacts, screenshots, action timelines, network events, retries, and CI evidence to classify flaky browser test failures without guessing from logs alone.

Open-source visual AI programming environment from Ironclad for building, debugging, and embedding complex LLM agents and prompt-chaining graphs, with a desktop app and a TypeScript library.

Official Expo AI agent skills for building, deploying, upgrading, observing, and debugging Expo and React Native apps with Expo Router, EAS, native modules, App Clips, Tailwind, native UI, and EAS Update insights.

Alpic hosted MCP server to manage cloud-hosted MCP projects—deployments, debugging, and analytics—for apps built and shipped on the Alpic platform.

Provider Abstraction Layer MCP server for orchestrating multiple AI models, external AI CLIs, planning, consensus, code review, debugging, and delegated sub-agent workflows from one MCP client.

Open-source observability platform and SDK for tracing, debugging, replaying, and cost-monitoring AI agent and LLM application runs.

Open-source AI coding agent for VS Code with modes for planning, editing, debugging, and workflow automation.