Найдите подходящую возможность для вашего агента.
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
Update ClaudeKit Engineer projects to the latest version. Capabilities include update single projects (safe mode with test branches), batch update multiple projects, find all ClaudeKit projects in home directory, verify updates with automated checks, preserve user settings and code, create timestamped backups, handle git workflows (branch, commit, merge), and rollback if needed. Use when user wants to update ClaudeKit framework, upgrade to latest version, apply new features/skills/commands, or maintain multiple ClaudeKit projects.
Detects AI writing patterns and fixes them. Use when reviewing any written output, including docs, READMEs, messages, PRDs. Based on Wikipedia's AI Cleanup patterns.
Semantic search using vector embeddings and similarity metrics. Apply when implementing search with embeddings (OpenAI, Sentence Transformers) or distance-based ranking. Covers cosine similarity, Euclidean distance, dot product, and threshold selection.
Central skill registry for demeter project. Use to discover available skills, understand skill conventions, and find the right skill for a task.
Use to find the right n8n skill for a task, browse available skills, discover workflow patterns, or get an overview of all n8n automation capabilities
Manage Kai's task queue - capture topics to work on when Claude usage is available. Commands: - /kai-todo add <topic> - Add a new task to the queue - /kai-todo list - Show all queued tasks - /kai-todo next - Start working on the next priority task - /kai-todo done <id> - Mark a task as complete - /kai-todo remove <id> - Remove a task from the queue
Complete operating system for AI-empowered creators with multi-agent orchestration
FastAPI development assistant for building modern Python web APIs. Provides guidance on routing, request/response handling, dependency injection, authentication, middleware, WebSockets, testing, and Pydantic models. Use when: (1) Creating FastAPI applications or endpoints, (2) Implementing CRUD operations, (3) Setting up authentication/authorization, (4) Working with request parameters (path, query, body, headers, cookies, forms, files), (5) Configuring middleware or CORS, (6) Implementing WebSocket connections, (7) Writing tests for FastAPI apps, (8) Defining Pydantic models for validation.
Generate and edit images using AI models (Gemini, OpenAI, BFL FLUX, or Poe). Use this skill when you need to create images from text prompts, edit existing images, or generate variations. Supports multiple providers with automatic API key detection from environment variables.
This skill should be used when designing agent coordination, implementing context handoffs, reducing context overhead, creating multi-agent workflows, optimizing agent communication, implementing progressive disclosure, selecting architectural patterns (hierarchical vs swarm), or debugging agent context issues. Provides SOTA patterns for multi-agent systems achieving 78%+ context reduction while maintaining analysis quality.
Comprehensive guide to using LLMs as judges for automated evaluation including prompt patterns, calibration, bias reduction, and multi-judge ensembles
Guide for creating effective subagents with concise prompts and skill integration. This skill should be used when users want to create a new subagent, improve existing subagent definitions, or need guidance on subagent architecture. Triggers on "create subagent", "create agent", "new subagent", "improve agent", or "subagent definition".
Orchestrates complex multi-agent workflows for features requiring coordinated work across multiple GitHub Copilot agents. Triggers on "orchestrate workflow", "coordinate these agents", "manage agent execution", or when dealing with complex features spanning multiple domains.
Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"
This skill should be used when building ChatKit-based AI assistant servers with the OpenAI Agents SDK. It provides guidance for implementing SSE streaming, thread persistence, context passing, RAG integration, and frontend ChatKit widget integration. Use when creating conversational AI backends that need real-time streaming, thread management, or agentic tool use.
智能小说生成器v2.0，支持长篇小说的断点续传、智能上下文管理、三层压缩机制、章节跳转、智能导入设定、AI辅助编辑和记忆管理。当用户需要创作长篇小说、管理复杂故事结构、从外部资源导入设定、或需要AI辅助进行持续性的创意写作时使用此技能。
