Discover research llm ai skills, compare source repositories and read the instructions for each workflow.
Expert prompt engineer specializing in designing, optimizing, and managing prompts for large language models. Masters prompt architecture, evaluation frameworks, and production prompt systems with focus on reli...
Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization. Masters task decomposition, agent selection, and coordination strategies with focus on achieving optim...
Opinionated constraints for building better interfaces with agents.
Assist with code review, refactoring, and explanations. Use when analyzing or improving code.
Summarize text, documents, or conversations. Use when you need a concise overview.
Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specializ...
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended...
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like D...
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text,...
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the...
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven task...
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models...
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, musi...
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation,...
Comprehensive evaluation toolkit for analyzing Claude skills across security, quality, utility, and compliance dimensions. This skill should be used when users need to evaluate a skill before installation, revi...
OpenContext를 활용한 AI 에이전트 영구 메모리 및 컨텍스트 관리. 세션/레포/날짜 간 컨텍스트 유지, 결론 저장, 문서 검색 워크플로우 제공.
Expert Morphir application architect providing guidance on AST design, functional programming patterns, IR transformations, and code generation for morphir-dotnet. Triggers include "architecture", "design patte...
{Brief description for Claude Code skill invocation. Include primary triggers and capabilities.}
Helps write Python code using the everyrow SDK for AI-powered data processing - transforming, deduping, merging, ranking, and screening dataframes with natural language instructions
Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.
Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.
iterate with spawned agents until stable. use for verification with BOUNDED scope and explicit exit criteria. NOT for generating opinions to reconcile.
record context that would help in future sessions. use after learning something, discovering a gotcha, or making a decision worth preserving. test: would a future agent starting fresh benefit from knowing this?
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.