Skills tagged "llm"

llm-fine-tuning - LLM Fine-Tuning Infrastructure
devops llm fine-tuning qlora
★ 17 · Updated 2026-09-21
Set up infrastructure for fine-tuning LLMs using QLoRA, LoRA, Hugging Face TRL, Axolotl, DeepSpeed, or FSDP.
⚙ Fine-tune LLMs using QLoRA ⚙ Configure Axolotl for fine-tuning ⚙ Launch distributed DeepSpeed ZeRO-3 training
langchain - Build LLM applications using LangChain.
langchain lcel rag agent
★ 95 · Updated 2026-09-20
Build LLM applications using LCEL chains, RAG pipelines, and LangGraph agents.
⚙ Build LCEL chains ⚙ Implement RAG pipelines ⚙ Create LangGraph agents
llm-application-dev-langchain-agent - LangChain & LangGraph Agent Development Expert
langchain langgraph agent rag
★ 0 · Updated 2026-09-19
Provides architecture guidance and implementations for production-grade AI agents using LangChain 0.1+ and LangGraph.
⚙ Design LangGraph state graphs ⚙ Implement async RAG pipelines ⚙ Configure agent memory systems
ai-engineer - Build production-ready LLM applications and AI agents
ai llm rag agent
★ 0 · Updated 2026-09-19
Develops production-ready LLM applications, advanced RAG systems, vector search, multimodal AI, and agent orchestration.
⚙ Build LLM applications ⚙ Implement RAG systems ⚙ Orchestrate multi-agent workflows
ai-engineer - Build production LLM applications, RAG, and AI agents.
llm rag ai-agents vector-search
★ 0 · Updated 2026-09-19
Implements LLM applications, RAG systems, vector search, agent orchestration, multimodal AI, and enterprise AI integrations.
⚙ Integrate LLM models and serving frameworks ⚙ Build multi-stage retrieval RAG pipelines ⚙ Orchestrate multi-agent workflows and memory
ai-engineer - AI Engineer for LLM Applications, RAG, and AI Agents
llm rag ai-agents vector-search
★ 1 · Updated 2026-09-19
Builds production-ready LLM applications, advanced RAG systems, intelligent agents, and multimodal AI integrations.
⚙ Integrate LLM models and serving frameworks ⚙ Build advanced RAG systems ⚙ Orchestrate multi-agent workflows and memory
impl-infra - Implement infrastructure clients for synth-lab
infrastructure llm tracing configuration
★ 18 · Updated 2026-09-19
Implement infrastructure clients, external service connections, environment configuration, LLM integration, tracing, and logging.
⚙ Implement external API clients ⚙ Configure environment variables ⚙ Integrate LLM client with retry
jatevo - Free LLM inference provider for OpenClaw
llm inference openclaw jatevo
★ 47 · Updated 2026-09-18
Provides free access to Qwen 3.5 Plus, Kimi K2.5, and GLM 4.7 models for OpenClaw.
⚙ Provide LLM inference access ⚙ Support text and vision inputs ⚙ Configure provider in OpenClaw
dspy - Optimize programmatic prompt systems with Stanford DSPy
dspy prompt-optimization prompt-compiler python
★ 95 · Updated 2026-09-18
Build and optimize programmatic prompt systems using Stanford DSPy signatures, modules, compilers, evaluation metrics, and caching.
⚙ Define schemas with DSPy Signatures ⚙ Build programs using DSPy modules ⚙ Optimize prompts with DSPy compilers
prompt-engineering-patterns - Master advanced prompt engineering techniques for LLMs.
prompt-engineering llm few-shot-learning chain-of-thought
★ 0 · Updated 2026-09-18
Provides patterns and techniques to optimize prompt performance, reliability, and controllability in production LLM applications.
⚙ Select dynamic few-shot examples ⚙ Implement chain-of-thought reasoning ⚙ Optimize prompt performance metrics
koe-setup - Guide users through Koe initial setup and configuration
koe setup configuration asr
★ 430 · Updated 2026-09-18
Guides users through installing Koe, configuring ASR and LLM credentials, generating dictionaries, customizing prompts, and setting hotkeys.
⚙ Check Koe installation status ⚙ Configure Volcengine ASR credentials ⚙ Configure OpenAI compatible LLM settings
llm - Drive language models via Simon Willison's llm CLI
llm cli prompt schema
★ 1 · Updated 2026-09-18
Executes LLM workflows via shell CLI including prompts, chat, file attachments, structured schemas, fragments, plugins, and log management.
⚙ Execute prompt and chat workflows ⚙ Attach local files and URLs ⚙ Generate structured output using schemas
planning-visual-tasks - Decompose visual instructions into structured task plans.
planning dag llm comfyui
★ 0 · Updated 2026-09-18
Turns natural-language instructions into structured Plan envelopes of typed sub-goals for host orchestrator execution, with a fallback keyword router.
⚙ Propose LLM-driven execution plans ⚙ Discover installed tools and models ⚙ Validate plan schemas and DAGs
llm-architect - LLM System Architecture and Optimization
llm architecture rag fine-tuning
★ 602 · Updated 2026-09-17
Designs scalable large language model applications with a focus on performance, cost efficiency, and safety.
⚙ Design end-to-end LLM systems ⚙ Select models and serving infrastructure ⚙ Implement RAG pipelines
content-analysis - Analyze text content with NLP and LLM techniques
text-analysis sentiment-analysis nlp llm
★ 18 · Updated 2026-09-17
Analyze text content using traditional NLP and LLM methods to extract sentiment, topics, keywords, and actionable insights.
⚙ Analyze text sentiment ⚙ Extract topics and keywords ⚙ Classify and cluster content
model-router - Intelligent model matching and routing for OpenClaw.
ollama models routing llm
★ 2 · Updated 2026-09-17
Routes tasks to optimal cloud or local models based on task characteristics like coding, analysis, reasoning, creative, or general.
⚙ Classify task types ⚙ Score candidate models ⚙ Select optimal target model
building-with-llms - Help users build effective AI applications using LLMs
llm ai-applications prompting rag
★ 18 · Updated 2026-09-16
Provides practical techniques for building AI applications, writing prompts, implementing RAG, creating agents, and running evals.
⚙ Understand user AI use cases ⚙ Diagnose AI application problems ⚙ Apply prompting and architecture techniques
regex-vs-llm-structured-text - Regex vs LLM Framework for Structured Text Parsing
regex llm text-parsing hybrid-pipeline
★ 0 · Updated 2026-09-16
Decision framework and hybrid pipeline for parsing structured text using regex first and reserving LLM calls for low-confidence edge cases.
⚙ Parse structured text with regex ⚙ Score extraction confidence ⚙ Identify low-confidence extracted items
agent-tools - Run AI apps and automations via the inference.sh CLI.
inference-sh cli ai-models image-generation
★ 422 · Updated 2026-09-16
Executes cloud AI applications for image and video generation, LLM queries, web search, 3D modeling, and Twitter automation using the inference.sh CLI.
⚙ Run cloud AI applications ⚙ Generate images and videos ⚙ Execute LLM queries
sgo - Semantic Gradient Optimization
optimization evaluation llm persona
★ 76 · Updated 2026-09-16
Optimize entities against evaluator populations using LLMs and counterfactual probes.
⚙ Download persona dataset ⚙ Build entity document ⚙ Filter persona data

Scroll to load more