Browse AI and ML workflow skills for model integration, prompt engineering, evaluations, and LLM automation across major IDEs.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Collection of role-based AI personas (e.g. senior-frontend-developer, security-engineer, technical-writer) with .claude and .cursor rules/skills. Copy a persona’s config into your project to get domain-tuned behavior, plus ready-made workflows for docs, PRs, and automation.
Use when you need to PROVE a claim with evidence, run quality/security scans, or validate that work is actually complete. Evidence before claims -- no should work allowed.
Minimalist yet powerful AI-assisted development framework. Production-ready CLAUDE.md & AGENTS.md system with 35+ guardrails, 4D methodology, and auto-loading language guides for TypeScript, Python, Go, and Rust.
Umbrella skill for all Convex development patterns. Use when starting a new Convex project, unsure which specific Convex skill to use, or need an overview of available Convex development skills. Routes to specific skills like convex-functions, convex-realtime, convex-agents, convex-schema-validator, etc.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
/Lumina-Intelligence, /Luminor-intelligence & /StarlightOrchestrator building Arcanea with swarm intelligence that overlays any AI. Ten Gates, Guardians & Godbeasts, context that compounds, and the creative civilization OS for creators who build universes.
Создатель субагентов - это способность, которая позволяет определять и использовать специализированные субагенты для обработки конкретных доменов с ИИ Агентами
Prepare and iterate changelists/pull requests using Google-style author practices. Use when writing clear CL descriptions, splitting large changes, bundling tests, handling reviewer comments, and keeping dependent CLs build-safe.
Release a new version of cqs. Bumps version, updates changelog, publishes to crates.io, creates GitHub release.
Implement ReasoningBank adaptive learning with AgentDBs 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
Что такое генератор SBOM для проектов Python? Это инструмент, создающий PR, которые проходят CI до создания
Legacy system analysis and microservices refactoring agent system for Claude Code