Loading...
Loading...
Found 913 Skills
Develop, debug, and optimize SGLang LLM serving engine. Use when the user mentions SGLang, sglang, srt, sgl-kernel, LLM serving, model inference, KV cache, attention backend, FlashInfer, MLA, MoE routing, speculative decoding, disaggregated serving, TP/PP/EP, radix cache, continuous batching, chunked prefill, CUDA graph, model loading, quantization FP8/GPTQ/AWQ, JIT kernel, triton kernel SGLang, or asks about serving LLMs with SGLang.
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
Complete reference for integrating with 300+ AI models through the OpenRouter TypeScript SDK using the callModel pattern
Convert websites into LLM-ready data with Firecrawl API. Features: scrape, crawl, map, search, extract, agent (autonomous), batch operations, and change tracking. Handles JavaScript, anti-bot bypass, PDF/DOCX parsing, and branding extraction. Prevents 10 documented errors. Use when: scraping websites, crawling sites, web search + scrape, autonomous data gathering, monitoring content changes, extracting brand/design systems, or troubleshooting content not loading, JavaScript rendering, bot detection, v2 migration, job status errors, DNS resolution, or stealth mode pricing.
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
Guide for tool registration and tool UI in assistant-ui. Use when implementing LLM tools, tool call rendering, or human-in-the-loop patterns.
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks. Invoke for parameter-efficient methods, dataset preparation, or model adaptation.
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.
Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications