llm AI Agent Skills
Browse 32 skills related to llm
llama-factory
davila7Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
axolotl
davila7Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
trulens-evaluation-setup
trueraConfigure feedback functions and selectors for TruLens evaluations
trulens-instrumentation
trueraInstrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization
trulens-running-evaluations
trueraExecute TruLens evaluations and view results
trulens-dataset-curation
trueraCreate and curate evaluation datasets with ground truth for TruLens
trulens-evaluation-workflow
trueraSystematically evaluate your LLM application with TruLens
vertex-agent-builder
jeremylongshoreBuild and deploy production-ready generative AI agents using Vertex AI, Gemini models, and Google Cloud infrastructure with RAG, function calling, and multi-modal capabilities
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
enact-docs-guide
aiskillstoreLLM guide for creating, publishing, and running Enact tools
enact-firecrawl
aiskillstoreScrape, crawl, search, and extract structured data from websites using Firecrawl API - converts web pages to LLM-ready markdown
testing-patterns
yonatangrossComprehensive testing patterns for unit, integration, E2E, pytest, API mocking (MSW/VCR), test data, property/contract testing, performance, LLM, and accessibility testing. Use when writing tests, setting up test infrastructure, or validating application quality.
rag-retrieval
yonatangrossRetrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
LLM Security Testing
PramodDuttaSecurity testing for LLM-powered applications including prompt injection, jailbreak detection, data leakage prevention, and AI safety testing.
LLM Output Testing
PramodDuttaTesting LLM-powered features including output quality validation, hallucination detection, token usage monitoring, and prompt regression testing.
ai-engineer
curiositechBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
prompt-engineer
curiositechExpert prompt optimization for large language models and AI systems. Use PROACTIVELY when designing AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.
langchain-orchestration
manutejComprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration
langchain_patterns
vuralserhat86Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
model_finetuning
vuralserhat86Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Convex Agents
powroomBuilding AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration
plain-text
SimHackerText files are forever. No lock-in. No corruption. No transformation.
yaml-jazz
SimHackerYAML is sheet music. The LLM is the jazz musician. Comments are the soul.
langchain-agents
LangConfigExpert guidance for building LangChain agents with proper tool binding, memory, and configuration. Use when creating agents, configuring models, or setting up tool integrations in LangConfig.
openrouter
bobmatnycOpenRouter unified AI API - Access 200+ LLMs through a single interface with intelligent routing, streaming, cost optimization, and model fallbacks
MCP
bobmatnycMCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
local-llm-ops
bobmatnycLocal LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.
vercel-ai-sdk-best-practices
oimiragieoBest practices for using the Vercel AI SDK in Next.js 15 applications with React Server Components and streaming capabilities.
pi-cli
mkSteadyUnified project analysis CLI tool. Supports DAG scheduling, LLM batch tasks, dependency graph construction, test analysis/repair, documentation generation, code auditing, and a Web Dashboard. Functionality is fully consistent with project-index and is recommended as the unified entry point.
prompt-engineering-apex
fratilanicoUse when writing prompts for Claude or any LLM, when agent outputs are inconsistent or low quality, when structuring system prompts for APEX OS agents, or when implementing CoT/ToT reasoning patterns. Triggers on: prompt design, system prompt, instruction engineering, output quality, JSON schema enforcement.
shopping_assistant
fhammerSmart Shopping Assistant - a truly intelligent shopping assistant powered by LLMs
recommendation_explanation
fhammerGenerate natural-language recommendation explanations that tell users why these items are recommended.