GitHub
prompt-engineering
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
☆ 13Voir le skill
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
context-engineering
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...
☆ 13Voir le skill
GitHub
rlhf
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...
☆ 13Voir le skill
GitHub
transformers
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,...
☆ 13Voir le skill
GitHub
qlora
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...
☆ 13Voir le skill
GitHub
agents
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...
☆ 13Voir le skill
GitHub
mlx
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...
☆ 13Voir le skill
GitHub
ai-multimodal
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...
☆ 13Voir le skill
GitHub
skill-developer
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,...
☆ 13Voir le skill
GitHub
skill-evaluator
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...
☆ 13Voir le skill
GitHub
opencontext
OpenContext를 활용한 AI 에이전트 영구 메모리 및 컨텍스트 관리. 세션/레포/날짜 간 컨텍스트 유지, 결론 저장, 문서 검색 워크플로우 제공.
☆ 13Voir le skill
GitHub
brain-expert
Personal knowledge management expert for the brain CLI. Use when users want to capture notes, search their knowledge base, or manage their second brain.
☆ 13Voir le skill
GitHub
morphir-architect
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...
☆ 12Voir le skill
GitHub
guru-id
{Brief description for Claude Code skill invocation. Include primary triggers and capabilities.}
☆ 12Voir le skill
GitHub
everyrow-sdk
Helps write Python code using the everyrow SDK for AI-powered data processing - transforming, deduping, merging, ranking, and screening dataframes with natural language instructions
☆ 12Voir le skill
GitHub
researching
Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.
☆ 12Voir le skill
GitHub
swarm-expert
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.
☆ 12Voir le skill
GitHub
rounds
iterate with spawned agents until stable. use for verification with BOUNDED scope and explicit exit criteria. NOT for generating opinions to reconcile.
☆ 12Voir le skill
GitHub
remember
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?
☆ 12Voir le skill
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
☆ 12Voir le skill
GitHub
local-llm-ops
Local LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.
☆ 12Voir le skill
GitHub
langchain-framework
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
☆ 12Voir le skill
GitHub
dispatching-parallel-agents
Use multiple Claude agents to investigate and fix independent problems concurrently
☆ 12Voir le skill
GitHub
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui)
☆ 12Voir le skill
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.