Loading...
Loading...
Found 1,573 Skills
Implement a task with automated LLM-as-Judge verification for critical steps
Start Here. Use when the user asks about Narev Cloud, the Pricing API, model pricing (API reference skill vs applied workflows on top of that API), live LLM pricing, token costs, cost calculation, pinning or snapshotting model rates, Narev SDK, @ai-billing/core, provider middleware packages, Vercel AI SDK billing, Next.js App Router route handlers, framework-specific billing patterns, usage-based billing, billing integrations (Polar, Stripe, Lago, OpenMeter), FOCUS format, Narev Self-Hosted (ThinOps), deployment, COGS, customer tagging, FinOps for AI, or this documentation site. Guides you to the right skill or documentation path based on their task.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
Use this skill for web search, extraction, mapping, crawling, and research via Tavily’s REST API when web searches are needed and no built-in tool is available, or when Tavily’s LLM-friendly format is beneficial.
AI agent patterns with Trigger.dev - orchestration, parallelization, routing, evaluator-optimizer, and human-in-the-loop. Use when building LLM-powered tasks that need parallel workers, approval gates, tool calling, or multi-step agent workflows.
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when "prompt engineering, system prompt, few-shot, chain of thought, prompt design, LLM prompt, instruction tuning, prompt template, output format, prompts, llm, gpt, claude, system-prompt, few-shot, chain-of-thought, evaluation" mentioned.
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
Amazon Bedrock AgentCore Evaluations for testing and monitoring AI agent quality. 13 built-in evaluators plus custom LLM-as-Judge patterns. Use when testing agents, monitoring production quality, setting up alerts, or validating agent behavior.
Build voice agents with the Cartesia Line SDK. Supports 100+ LLM providers via LiteLLM with tool calling, multi-agent handoffs, and real-time interruption handling.
Complete knowledge domain for Firecrawl v2 API - web scraping and crawling that converts websites into LLM-ready markdown or structured data. Use when: scraping websites, crawling entire sites, extracting web content, converting HTML to markdown, building web scrapers, handling dynamic JavaScript content, bypassing anti-bot protection, extracting structured data from web pages, or when encountering "content not loading", "JavaScript rendering issues", or "blocked by bot detection". Keywords: firecrawl, firecrawl api, web scraping, web crawler, scrape website, crawl website, extract content, html to markdown, site crawler, content extraction, web automation, firecrawl-py, firecrawl-js, llm ready data, structured data extraction, bot bypass, javascript rendering, scraping api, crawling api, map urls, batch scraping
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model), LangChain (orchestration), LlamaIndex (RAG), and streaming patterns.