Découvrez les skills Contenu et médias, comparez leurs dépôts et consultez leurs instructions.
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling t...
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learnin...
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory
This skill should be used when working on architectural decisions, complex refactoring, system design, API redesign, or multi-component implementations. Also use when asked to "consult codex", "get a second opi...
Generate professional Bytebase release notes by analyzing git commits, building PR dependency graphs, checking Terraform impact, searching Linear for customer feedback, and following established conventions. Cr...
Manage Obsidian knowledge base - capture ideas, YouTube videos, articles, repositories, create study guides, publish to GitHub Pages, and share notes via URL (no server storage). Use smart AI tagging for automa...
Generate AI images with various themes, styles, and aspect ratios. Use when asked to generate images, create artwork, make graphics, generate backgrounds, or create visual assets.
Apply distinctive frontend design to React + TailwindCSS apps. Use when building UI components, pages, or improving visual design. Breaks generic "AI slop" patterns.
Creates comprehensive PR descriptions by systematically reviewing ALL changes - features, bug fixes, tests, docs, and infrastructure. Use when user asks to "update the PR", "prepare PR for review", "write PR de...
Apply the Explore → Plan → Code → Commit workflow for tasks like implementing features, fixing bugs, refactors, or adding integrations. Use this when the user wants changes in a repo and wants higher reliabilit...
Configure and use Supabase MCP from Claude Code to inspect and manage a Supabase project. Use when the user asks to create tables, migrations, RLS policies, storage buckets, or to query Supabase from Claude Cod...
Design system et palette de couleurs du projet. Utiliser pour tout styling, creation de composants UI, ou quand des couleurs sont mentionnees.
Always use Context7 MCP to fetch up-to-date library/API documentation before generating code that depends on external libraries or config. Use when the user asks for setup steps, configuration, or code involvin...
Use GitHub CLI (gh) to manage issues and pull requests from Claude Code. Use when the user wants to create PRs, link commits to issues, fetch PR context, or automate GitHub workflows. Includes install/auth chec...
Use when building CLI tools with Commander.js - commands, options, arguments, and help text for Node.js command-line applications
Use when working with JSON Schema for validation, OpenAPI schemas, type definitions, and data structure specification
Use when writing Vague (.vague) files - a declarative language for generating realistic test data with superposition, constraints, and cross-references
Use when writing PEG grammars with Peggy (formerly PEG.js) - parsing expression grammars, parser generation, and syntax definition
Use when implementing Language Server Protocol features - diagnostics, completions, hover, go-to-definition, and editor integration
Use when writing Vague (.vague) files that need realistic test data using faker generators for names, emails, addresses, dates, and more
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.