Découvrez les skills Bases de données, comparez leurs dépôts et consultez leurs instructions.
This skill should be used when implementing Convex query functions. It provides comprehensive guidelines for defining, registering, calling, and optimizing queries, including pagination, full text search, and i...
Create, validate, and refine Claude Code plugin hooks for automating workflows. Use when building new hooks from scratch, validating existing hooks against best practices, or improving hook quality for producti...
Context-Driven Development methodology overview. Shows available Draft commands and guides you to the right workflow.
Sets up a web UI for testing, debugging, and developing agents without code. Use this to manually test agents, browse conversation history, and verify behavior in real-time.
Implements Retrieval-Augmented Generation (RAG) patterns to enhance agents with custom knowledge bases. Use this when agents need to search through documents, retrieve context from a knowledge base, or ground r...
Customizes what information the LLM receives for each generation. Use this to control message history, implement RAG context injection, search across threads, and provide custom context.
Sets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creating conversation threads, and generating basic text or structured responses from LLMs. Essen...
Sends, saves, retrieves, and manages messages within agent conversations. Use this when handling user messages, displaying conversation history, and working with UIMessages for rich rendering.
Create, validate, and refine Claude Code subagents for reliable delegation. Use when building new subagents, validating existing ones, improving quality, scoping tool access, configuring permission modes, or se...
Display current progress of Draft tracks and active tasks. Shows phases, completion percentages, and blocked items.
Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level.
Execute tracer bullet development - implement tasks with validation, code review gates, demos, and learning propagation.
Create a well-formatted git commit following best practices
Generate syntactically correct Mermaid diagrams for technical documentation
Guide on caching with cachified, SQLite cache, and LRU cache for Epic Stack
Update GitHub PR or GitLab MR descriptions with AI session export summaries. Use when user asks to add session summary to PR/MR, document AI assistance in PR/MR, or export conversation summary to PR/MR descript...
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 an agent's capabilities with specialized knowledge, workflows, or...
This skill provides guidance for building workflow visualizations using Vercel AI Elements and React Flow. It should be used when implementing interactive node-based interfaces, workflow diagrams, or process fl...
This skill provides comprehensive documentation for all 23 Vercel AI Elements components organized by category (Message, Conversation, Input/Interaction, Content Display, AI Processing, Advanced Features). Use...
Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.
Multi-repository codebase exploration. Research library internals, find code patterns, understand architecture, compare implementations across GitHub/npm/PyPI/crates. Use when needing deep understanding of how...
Guide on React patterns, performance optimization, and code quality for Epic Stack
Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead...
AST Builder component patterns for Marble's rule/condition builder. Use when working with AstBuilder components, editing AST nodes, node state management with sharpstate, validation flows, or any rule builder U...
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.