Loading...
Loading...
Found 2,163 Skills
Auditing memory traces and debugging.
AI-powered enterprise debugging orchestrator with Context7 integration, intelligent error pattern recognition, automated root cause analysis, predictive fix suggestions, and multi-process debugging coordination across 25+ languages and distributed systems
Use when testing MCP servers, debugging MCP tool responses, exploring MCP capabilities, or diagnosing why an MCP tool returns unexpected data
Answer questions about Module Federation (MF) — configuration, runtime API, build plugins (Webpack/Rspack/Rsbuild/Vite), framework integration (React/Vue/Next.js/Modern.js/Angular), shared dependencies, exposes, remotes, debugging, troubleshooting, and micro-frontend architecture. Use this skill when the user asks anything about module federation, remote modules, shared deps, mf-manifest, federation runtime, or micro-frontends with MF.
Operate the Google Cloud gcloud CLI safely and effectively. Authenticates users, reads cloud resource state freely for debugging and exploration, and creates, updates, or deletes resources only after explicit user confirmation. Use when working with gcloud, Google Cloud CLI, GCP resources, cloud debugging, reading logs, managing Compute Engine, Cloud Run, Cloud Functions, GKE, IAM, networking, Cloud Storage, Cloud SQL, Pub/Sub, or when the user mentions any gcloud command, Google Cloud project, or needs to authenticate with GCP.
Use a persistent Codex sidecar thread from the local `codex-sidecar` CLI for design review, implementation advice, debugging, and context-preserving follow-up questions while keeping the current agent as the primary executor.
Embedded serial port debugging tool for serial port scanning, real-time monitoring, data sending, log recording, and Hex viewing. Automatically triggered when users mention serial port, COM port, UART, AT command debugging, baud rate, Hex streaming, serial port log capturing, serial port monitoring, viewing MCU output, or binary protocol joint debugging. It also supports explicit invocation via /serial. Even if users only say "check serial port output", "send an AT command", or "capture logs", this skill should be triggered as long as the context involves serial port communication.
Inspect eval manifests and portable validators for trace-friendly skill signals. Use when debugging skill invocation gaps. NOT for live LLM trace capture.
The single interface for building, improving, and debugging exo workflows. Routes to one of three intents. BUILD takes a rough idea through interrogation, assessment, resource creation in dependency order, and one manual run, then hands off. IMPROVE runs the observe-and-iterate loop over recent runs, proposing and applying changes behind two gates. DEBUG diagnoses one failed or misbehaving run by walking the dependency graph of everything it touched. Use whenever the user wants to create a new exo workflow, iterate on or improve an existing one, or find out why a specific run failed.
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
Structured debugging skill for methodical root cause analysis. Use when investigating bugs, unexpected behavior, or errors. Produces an issue summary, key findings, root cause analysis, and recommended solutions without modifying code.
[Fix & Debug] ⚡⚡ Fix a GitHub issue with systematic debugging