Найдите подходящую возможность для вашего агента.
DynamoDB patterns for sender tracking. Client setup, marshall/unmarshall, CRUD operations, GSI queries, batch writes. Triggers on "dynamodb", "sender tracking", "known senders", "batch write".
Design and implement automated workflows combining visual logic with custom code. Create multi-step automations, integrate APIs, and build AI-native pipelines. Use when designing automation flows, integrating APIs, building event-driven systems, or creating LangChain-style AI workflows.
Comprehensive SQLModel skill for Python database operations with SQL databases. Use when working with SQLModel for (1) Designing database models and table schemas, (2) Creating relationships between tables (foreign keys, one-to-many, many-to-many), (3) Integrating SQLModel with FastAPI for CRUD APIs, (4) Writing queries with select, where, joins, and filtering, (5) Implementing best practices for session management, migrations, and performance optimization. Covers the multiple model pattern (Base, Table, Create, Public, Update), dependency injection, pagination, error handling, and production-ready patterns.
Complete migration validation checklist for Flow to Output SDK. Use after migration to verify completeness and correctness.
Provides patterns and guidance for implementing user-scoped data filtering and multi-tenancy in web applications. Use this skill when you need to: (1) Restrict data access based on user identity, (2) Implement ownership checks for database operations, (3) Build multi-tenant applications with organization-level data scoping, (4) Implement admin bypass for viewing all data, (5) Create audit trails for data access. This skill focuses on Python, FastAPI, and SQLAlchemy.
概念データモデル（CDM）、論理データモデル（LDM）、物理データモデル（PDM）を段階的に設計・出力するSkill。 「データモデルを作って」「ER図を書いて」「テーブル設計して」「DDLを生成して」「エンティティを整理して」「データ辞書を作って」 「概念モデル」「論理モデル」「物理モデル」などの依頼で発動する。 出力はMermaid ER図、Markdown（用語集・データ辞書・設計書）、SQL DDL。
Use when creating new skills or editing existing skills - combines official skill authoring best practices with TDD methodology (test with subagents before deployment, iterate until bulletproof). Activates when user wants to create/update a skill that extends Claude's capabilities.
Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".
Documentation for Kubernetes Agent Sandbox - a CRD-based system for managing isolated AI agent execution environments. Use for queries about Sandbox CRDs (Sandbox, SandboxTemplate, SandboxClaim, SandboxWarmPool), Python SDK (SandboxClient, SandboxRouter, ComputerUseExtension), network policies, security configurations, and implementation examples. Keywords kubernetes sandbox, agent sandbox, CRD, python sdk, agentic-sandbox-client, isolated environment, gvisor, network policy.
Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach", or needs to (1) create/start/stop/restart/fork sessions, (2) attach/detach MCPs, (3) manage groups/profiles, (4) get session output, (5) configure agent-deck, (6) troubleshoot issues, or (7) launch sub-agents. Covers CLI commands, TUI shortcuts, config.toml options, and automation.
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts. USE WHEN user says 'start observability', 'agent dashboard', 'monitor agents', 'watch agent activity', 'multi-agent monitoring', 'track subagents', or needs to debug multi-agent workflows. **Key Features:** - 🔴 Real-time event streaming via WebSocket - 📊 Agent swim lanes showing parallel execution - 🔍 Event filtering by agent, session, event type - 📈 Live charts for tool usage patterns - 💾 Filesystem-based (no database required) **Inspired by [@indydevdan](https://github.com/indydevdan)**'s work on multi-agent observability. **Our approach:** Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.
Adaptive teaching skill that frames explanations in student's interest domain and uses their preferred learning style. Auto-invoked when teaching programming concepts, creating problems, or providing feedback.
Track AI code contributions for auditing and attribution. Use this skill BEFORE writing, editing, creating, or modifying any code files. Enables automatic detection of AI-authored vs human-authored code changes. Required for code attribution compliance.
Integrating AI and LLM capabilities into applications for enhanced functionalities. Use when implementing AI features, processing data with ML models, building generative workflows, or integrating AI APIs.
Checklist สำหรับตรวจสอบและกำจัด bloat ใน context, prompt, และ response เพื่อลด token cost และเพิ่ม signal-to-noise ratio
Comprehensive guide and instructions for integrating Google Cloud, Vertex AI, and Gemini 3 models into the indiiOS ecosystem.
Guide implementation of production-ready Python RAG components by enforcing correct abstractions, error handling, observability, and safety at coding time.
Draft scientific research manuscripts from research data. Use when user wants to write a research paper, has a project folder with papers, data, figures, and a GitHub repository link. Orchestrates context-ingestion, scoping, literature-review, code-analyzer, results-interpreter, synthesis, and assembler sub-skills.
Develop pre-fluency cognitive habits: recognize when not to use AI, separate thinking from generation, resist automation bias and output authority.
