GitHub
rag
Retrieval-Augmented Generation (RAG) for grounding LLM responses with external knowledge. Covers document chunking, embeddings, vector stores (pandas, ChromaDB), similarity search, and conversational RAG pipeli...
Skills IA devops llm ai
Découvrez les skills devops llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: devops llm ai
devops llm ai Effacer les filtres
Explorer
GitHub
huggingface
Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use imported models for inference.
GitHub
localai
LocalAI local inference API management via Podman Quadlet. Provides an OpenAI-compatible API for local model inference with GPU acceleration. Use when users need to configure, start, or manage the LocalAI servi...
GitHub
python
Official ollama Python library for LLM inference. Provides a clean, Pythonic interface for text generation, chat completion, embeddings, model management, and streaming responses.
GitHub
pods
Aggregate management for all AI pod services. Provides status overview and bulk operations across all pod containers (ollama, jupyter, comfyui, openwebui, localai, fiftyone, jellyfin, runners).
GitHub
openai
OpenAI compatibility layer for Ollama. Use the official OpenAI Python library to interact with Ollama, enabling easy migration from OpenAI and compatibility with LangChain, LlamaIndex, and other OpenAI-based to...
GitHub
ollama
Ollama LLM inference server management via Podman Quadlet. Single-instance design with GPU acceleration for running local LLMs. Use when users need to configure Ollama, pull models, run inference, or manage the...
GitHub
comfyui
ComfyUI node-based Stable Diffusion interface. GPU-accelerated image generation with custom node support and CivitAI model downloads. Use 'ujust comfyui' for configuration, lifecycle management, and model/node...
GitHub
langchain
LangChain framework for LLM applications. Covers model wrappers (HuggingFace, Ollama), prompt templates, few-shot learning, output parsing, and chaining techniques for building sophisticated LLM workflows.
GitHub
peft
Parameter-efficient fine-tuning with LoRA and Unsloth. Covers LoraConfig, target module selection, QLoRA for 4-bit training, adapter merging, and Unsloth optimizations for 2x faster training.
GitHub
evaluation
LLM evaluation and prompt optimization with Evidently.ai. Covers text descriptors, dataset metrics, LLM-as-a-Judge patterns, and automated prompt optimization for classification and generation tasks.
GitHub
reward
Reward model training for RLHF pipelines. Covers RewardTrainer, preference dataset preparation, sequence classification heads, and reward scaling for stable reinforcement learning. Includes thinking quality sco...
GitHub
telegram-keyboard-design
Design Telegram bot keyboards, buttons, and conversational flows with proper UX patterns. Includes inline keyboards, reply keyboards, button callbacks, and progressive disclosure for better mobile UX.
GitHub
prompt-improver
Improve prompts for AI agents and Telegram bots using OpenAI's prompt engineering best practices. Analyzes clarity, specificity, context, and output format. Returns structured improvements.
GitHub
telegram-bot-ui-design
Expert in designing Telegram bot interfaces with keyboards, buttons, conversational flows, and mobile-first UX patterns.
GitHub
fastapi-async-patterns
Create async FastAPI endpoints with proper error handling, dependency injection, service/repository patterns, and type safety. Includes async database queries, pagination, filtering, and Gemini integration.
GitHub
fastapi-project-builder
Builds FastAPI projects from beginner to professional level, including project structure, database integration, authentication, testing, and deployment. Use when creating new FastAPI projects, adding features,...
GitHub
ralph-prompt-generator
Generate optimized Ralph Wiggum prompts for Claude Code iterative loops. Use when the user wants to create a Ralph prompt, needs help structuring an iterative task for Claude Code, mentions Ralph Wiggum plugin,...
GitHub
cc-actions
Configure Claude Code GitHub Actions workflows effectively. Covers automatic mode detection, event routing, subagent coordination, hooks for quality gates, MCP server integration, reusable workflows, performanc...
GitHub
vibe-kanban-orchestration
Dispatch AI agents via Vibe Kanban MCP, monitor agent status, send follow-up messages, read agent outputs, manage worktrees. Use when orchestrating agents, spawning parallel tasks, checking agent status, or any...
GitHub
develop-fastapi-app
Build production-ready FastAPI applications with best practices for project structure, async patterns, Pydantic models, dependency injection, database operations, and testing. Use when developing FastAPI backen...
GitHub
housekeeper
Automatically triggers when users ask about upgrading, updating, or checking versions of Oh My Opencode or other development tools. Use for version checks, upgrade procedures, maintenance recommendations, and k...
GitHub
opencode-agent-factory
This skill should be used when users want to "create an agent", "add an agent", "write a subagent", "configure agent parameters", or need guidance on agent structure, system prompts, tool permissions, or agent...
GitHub
claudish-usage
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly reque...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.