Loading...
Loading...
Found 1,564 Skills
Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
Motto: The LLM is the dice. It narrates the outcome.
BullMQ queue system reference for Redis-backed job queues, workers, flows, and schedulers. Use when: (1) creating queues and workers with BullMQ, (2) adding jobs (delayed, prioritized, repeatable, deduplicated), (3) setting up FlowProducer parent-child job hierarchies, (4) configuring retry strategies, rate limiting, or concurrency, (5) implementing job schedulers with cron/interval patterns, (6) preparing BullMQ for production (graceful shutdown, Redis config, monitoring), or (7) debugging stalled jobs or connection issues
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).
Run vLLM performance benchmark using synthetic random data to measure throughput, TTFT (Time to First Token), TPOT (Time per Output Token), and other key performance metrics. Use when the user wants to quickly test vLLM serving performance without downloading external datasets.
This is a skill for benchmarking the efficiency of automatic prefix caching in vLLM using fixed prompts, real-world datasets, or synthetic prefix/suffix patterns. Use when the user asks to benchmark prefix caching hit rate, caching efficiency, or repeated-prompt performance in vLLM.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Deploy and use an LLM-powered public opinion analytics assistant that crawls 26 hot lists from 15 platforms, performs sentiment analysis, topic clustering, and multi-channel alerting
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.
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati
LLMs, prompt engineering, RAG systems, LangChain, and AI application development