#debugging
13 skills & prompts · 3 tools · 10 MCP servers · 1 articles
Skills & prompts
See all 13cron-doctor
Diagnose and validate cron expressions before they ship. Catches the five silent death-traps: impossible dates that never fire, OR-semantics that fire too often, midnight spikes, uneven step drift, and leap-year February 29.
Reproduce-first bug hunt for Cursor
Forces a failing test that reproduces the bug before any fix — so you know it's actually fixed.
debugging-websocket-issues
Use when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WS_ERR_UNEXPECTED_RSV_1" - covers multiple WebSocketServer conflicts, compression issues, and raw frame debugging techniques
systematic-debugging
遇到任何 bug、测试失败或异常行为时使用,在提出修复方案之前执行
systematic-debugging
Diagnose root causes with a four-phase debugging protocol. Use for ANY technical issue — test failures, production bugs, unexpected behavior, performance problems, build failures, or integration issues. ESPECIALLY when under time pressure, when "one quick fix" seems obvious, or w
debugging-dating
Debugging dating for AI agents — debug your dating life, debug your connections, and debug your compatibility. Find the bug, fix the match. Debugging dating on inbed.ai. 调试约会。Depuración de citas.
debugging
Use when a bug's cause is unknown. Applies a hypothesis-driven method — reproduce, isolate, instrument, prove — instead of speculative edits, and covers profiler, debugger, and log-based investigation. Trigger on "no idea why this is failing", "works locally but not in prod", "th
kubernetes
Use when deploying to or debugging Kubernetes. Covers workload configuration, resource requests and limits, probes, rollout strategy, networking, and the failure modes that produce CrashLoopBackOff and OOMKilled. Trigger on "pod keeps restarting", "pod stuck in crashloopbackoff",
network-troubleshooting
Use when diagnosing network failures — connection refused, timeouts, TLS errors, DNS problems, and intermittent failures. Covers layer-by-layer isolation and the tools that answer each question. Trigger on "connection refused", "curl times out from the server but works locally",
web-app-testing
Use when testing a web application interactively — verifying a feature, reproducing a bug, or checking a flow in a real browser. Covers systematic exploration, console and network inspection, and reporting what you find. Trigger on "check this works in the browser", "reproduce th
log-analyzer
Summarizes application log files by severity, time range and the most frequent error messages. Use when the user shares a log file or pasted log output and asks what went wrong, which errors repeat, or how noisy the log is.
Tools
Claude Code Prompt Mechanism Visualizer — Electron desktop app
Vite 运行时遥测插件:为 AI agent 提供结构化日志、错误快照、本地 Cookie 修复与提交前检查。 / Vite telemetry plugin for AI agents with structured logs, error snapshots, local cookie repair, and p…
MCP servers
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MC…
DebugBundle MCP: runtime error reporting, incident response, health checks, and product analytics.
MCP server to communicate with DAP servers allowing AI Agents the ability to debug live programs.
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
MCP server giving AI agents full access to Julia's runtime via a live Gate — code execution, introspection, debugging, testing, and semantic search
A search-first, profile-aware reverse-engineering workspace for AI agents — 735 tools across 36 domains in one MCP server.
One local debugging server, one binary: catches errors, dumps, emails, logs, profiles and HTTP from your app in development. Speaks Sentry, Ray, VarDumper, Mono…
Articles
How to test an MCP server with MCP Inspector
Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.