GitHub
fastapi-patterns
Automatically applies when creating FastAPI endpoints, routers, and API structures. Enforces best practices for endpoint definitions, dependency injection, error handling, and documentation.
Skills IA Développement
Découvrez les skills Développement, comparez leurs dépôts et consultez leurs instructions.
Catégories: Développement
Développement Effacer les filtres
Explorer
GitHub
api-endpoint-design
REST API design standards for FanHub's Express backend. Use when creating or modifying API endpoints to ensure consistency.
GitHub
managing-specs
Set up specs directory with templates for PRDs, TRDs, and ADRs. Use when creating or organizing spec structure.
GitHub
self-improving
Use when starting infrastructure, testing, deployment, or framework-specific tasks - automatically searches PRPM registry for relevant expertise packages and suggests installation to enhance capabilities for th...
GitHub
gem-integration
Skill especializado en integración de Gem Bundles compilados por Gem Builder Compiler en AGCCE v4.0. Permite configurar agentes MAS dinámicamente desde Gems versionados.
GitHub
deterministic-math-guidelines
Use when writing game logic code - ensures deterministic math operations across platforms
GitHub
dspy-optimization
DSPy optimizers (teleprompters), evaluation metrics, and optimization workflows. Use when compiling programs with BootstrapFewShot, KNNFewShot, MIPROv2, GEPA, or defining custom metrics.
GitHub
iterate-implementation
iterate on implementation based on user feedback
GitHub
evaluating-rag
Evaluate RAG systems with hit rate, MRR, faithfulness metrics and compare retrieval strategies. Use when testing retrieval quality, generating evaluation datasets, comparing embeddings or retrievers, A/B testin...
GitHub
openai-api
The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.
GitHub
implementing-rag
Set up RAG pipelines with document chunking, embedding generation, and retrieval strategies using LlamaIndex. Use when building new RAG systems, choosing chunking approaches, selecting embedding models, or impl...
GitHub
gemini-vision
Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, a...
GitHub
ralph-tui
Run ralph-tui task loops for automated PRD execution. Covers headless mode, PRD preparation, agent selection (opencode/claude), session management, and troubleshooting. Use when asked to "run ralph-tui", "execu...
GitHub
llm-tuning-patterns
LLM Tuning Patterns
GitHub
plan-agent
Planning agent that creates implementation plans and handoffs from conversation context
GitHub
uloop-get-provider-details
Get Unity Search provider details via uloop CLI. Use when you need to: (1) Discover available search providers, (2) Understand search capabilities and filters, (3) Configure searches with specific provider opti...
GitHub
patterns
Common agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for proxy mode, TodoWrite integration, and quality checks.
GitHub
dspy-configuration
DSPy configuration, LM setup, caching, and version management. Use when configuring language models, enabling caching, managing dependencies, or setting up multi-provider configurations.
GitHub
sub-agents
Create and configure Claude Code sub-agents with custom prompts, tools, and models
GitHub
wan2122-i2v-comfyui
This skill should be used when the user asks to "implement Wan I2V", "set up Wan2.1", "configure Wan2.2", "image to video with Wan", "ComfyUI video generation", "low VRAM video generation", "GGUF Wan model", "s...
GitHub
recall
Query memory system for relevant learnings from past sessions
GitHub
agentica-claude-proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
GitHub
math-help
Guide to the math cognitive stack - what tools exist and when to use each
GitHub
sag
ElevenLabs text-to-speech with mac-style say UX.
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.