GitHub
opence-compound
Document learnings, capture repeatable workflows as skills, and prepare to compound an opence change.
Skills IA content media llm ai
Découvrez les skills content media llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: content media llm ai
content media llm ai Effacer les filtres
Explorer
GitHub
prompt-sync-workflow
Coordinate prompt and skill updates across related changes
GitHub
create-plan
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
GitHub
retrace
This skill should be used when the user asks to "find past conversations", "recall what was done", "search history", "look up previous work", "how did we handle X", "what was that implementation", "find similar...
GitHub
web-research
Web search with automatic Qdrant storage for building persistent knowledge
GitHub
rag-builder
Build Retrieval-Augmented Generation systems with vector databases
GitHub
agent-builder
Build specialized sub-agents for the workflow system
GitHub
knowledge-ingestion-patterns
Patterns for ingesting knowledge into vector databases and RAG systems
GitHub
prompt-template
Create and manage reusable prompt templates
GitHub
task-decomposition
Break down complex tasks into actionable, atomic steps that can be executed by individual agents.
GitHub
embedding-comparison
Compare and evaluate embedding models for semantic search
GitHub
ai-video-generation
AI video generation patterns using Sora, Runway, Pika, and other AI video tools. Use when generating videos from text prompts, image-to-video conversion, AI video editing, or integrating AI video APIs.
GitHub
qdrant-patterns
Store and retrieve documents using Qdrant for RAG workflows. Use for persistent memory, research storage, and semantic search.
GitHub
rag-wrapper
Patterns for wrapping any agent with RAG context from Qdrant. Use to add persistent memory to imported or external agents.
GitHub
mcp-server-builder
Build Model Context Protocol servers for Claude Code integration
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...
GitHub
deep-research
Conduct comprehensive, multi-source research on any topic using web search, documentation lookup, and critical analysis. This skill should be used when users request thorough investigation, deep research, or co...
GitHub
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
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). Use for complex artifacts requiring state management, rou...
GitHub
nano-banana
Generate images using Google's Nano-Banana (Gemini 2.5 Flash Image) model. Use when the user asks to generate, create, or make an image, picture, or illustration.
GitHub
realistic-ugc-video
Create realistic long-form AI talking head/UGC videos that don't look AI-generated. Use when user wants to make "realistic AI video", "UGC video", "talking head video", "AI spokesperson", "AI ad content", "vide...
GitHub
writing-guide
Use when creating or reviewing technical documentation. Provides guidelines for natural, readable Japanese writing without AI-generated artifacts. Triggers: (1) creating technical documents or READMEs, (2) proo...
GitHub
claude-code-frontmatter
Use when creating or editing Claude Code skills, agents (subagents), or slash commands. Provides complete YAML frontmatter property reference.
GitHub
gemini
Use when delegating tasks to Gemini. Two execution modes: (1) CLI mode (default): Subagent runs gemini CLI iteratively until task complete. Progress visible, suitable for large investigations. (2) MCP mode: Dir...
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.