Developer Tools

This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs". Use for Node.js/Express/Fastify development, PostgreSQL optimization, API security, and backend architecture patterns.

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

This skill should be used when the user asks to "perform cloud penetration testing", "assess Azure or AWS or GCP security", "enumerate cloud resources", "exploit cloud misconfigurations", "test O365 security", "extract secrets from cloud environments", or "audit cloud infrastructure". It provides comprehensive techniques for security assessment across major cloud platforms.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

Search the web, generate fast AI answers with verifiable references, and extract web content using You.com's schema-driven JSON CLI tools — optimized for bash-based AI agents (OpenClaw, Claude Code, Codex, Cursor, etc.). Faster than builtin search APIs with simultaneous livecrawl, instant content extraction, and citation-backed answers. Schema discovery via --schema flag enables programmatic query building.

Standalone single-agent skill for papercli. Prefer driving work via the CLI (commands/flags/files) because it’s the most efficient and safest path—typically saving ~99% of context/tokens versus pasting large code/docs.

Manage Coder workspaces and AI coding agent tasks via CLI. List, create, start, stop, and delete workspaces. SSH into workspaces to run commands. Create and monitor AI coding tasks with Claude Code, Aider, or other agents.

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.

Find silent failures and error swallowing in code. Use when reviewing error handling or auditing catch blocks.