Loading...
Loading...
Found 2,163 Skills
For HarmonyOS NEXT and ArkTS development, especially when handling .ets files, implementing @ComponentV2 components, or debugging errors. Provides development guidance based on official standards and maintains categorized error logs for efficient troubleshooting.
CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.
Expert-level Deno knowledge for code review, debugging, and best practice enforcement. Use when reviewing Deno code or answering advanced Deno questions.
Use Codex CLI in full-auto mode to fix issues iteratively until tests pass. Autonomous debugging and test-fixing loop with sandbox safety.
Tail and inspect Cloudflare Worker logs from the CLI. Use when debugging API 401/500, openclaw auth, or web app errors. Covers both the homepage worker (apps/web) and the API worker (apps/api).
Active diagnostic tool for analyzing skill prompts to identify token waste, anti-patterns, trigger issues, and optimization opportunities. Use when reviewing skill prompts, debugging why skills aren't triggering, optimizing token usage, or preparing skills for publication. Provides specific, actionable suggestions with examples.
Asks Gemini CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.
Use when animation "feels wrong" but you can't pinpoint why—debugging floaty movement, stiff characters, unclear action, or any motion that isn't working and needs systematic troubleshooting.
Use when writing, reviewing, or debugging Jest + React Testing Library tests, before writing test code or when tests fail
Debug Crossplane compositions, functions (KCL, Go templates, patch-and-transform, auto-ready), and managed resources. Use when troubleshooting composition rendering issues, function errors, resource creation failures, dependency problems, or claim status issues. Supports remote cluster debugging when composition files are not available locally. Triggers on keywords like "crossplane", "composition", "XR", "claim", "function-kcl", "managed resource", or when debugging Kubernetes resources created by Crossplane.
Use when ANY runtime debugging is needed — setting breakpoints, inspecting variables, evaluating expressions, analyzing threads, or reproducing crashes interactively with LLDB
Diagnose and fix runtime issues, errors, and bugs through systematic reproduction, root cause analysis, and targeted fixes. Use for debugging production issues, test failures, performance problems, and any type of software defect.