Найдите подходящую возможность для вашего агента.
Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from interactions, short-term for session context. Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions.
Scaffold and initialize a Docusaurus project with the specific structure for the Physical AI textbook. Agent: BookArchitect
Expertly integrate Agents Playbook MCP into external AI frameworks and design sophisticated workflows using 2026 models.
AI出力の品質を自動検証するスキル。事実確認、論理性、一貫性、幻覚（ハルシネーション）検出、バイアス分析、安全性チェックを実施し、改善提案を提供。
Research voids (cognitive gaps, unchartable territories). Daily. Outputs research notes for voids articles.
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatch, describe, grep, sample.
Handle comprehensive project language and user setup workflows including language selection, agent prompt configuration, user profiles, team settings, and domain selection
対話形式の質問を通じてユーザーの技術的背景、開発スタイル、AI協働の好みを把握し、最適化されたCLAUDE.mdを生成するスキル。ユーザーが「CLAUDE.mdをカスタマイズしたい」「AIの振る舞いを自分に合わせたい」「開発スタイルに合わせた設定がしたい」と言った時に使用する。新規ユーザーのオンボーディングや、既存CLAUDE.mdの見直し時にも有効。
Initialize and configure OpenAI Agents SDK for building AI-powered chatbots. Uses NATIVE MCP integration via MCPServerStreamableHttp - no @function_tool wrappers needed! Use when setting up AI agents for Phase 3 chatbot implementation.
Structure a multidisciplinary design review for LLM-powered products, producing actionable risks, fixes, and evidence gaps across UX, architecture, AI safety, and operations.. Use when Use this skill when the task matches its description and triggers..
Complete guide to MoAI-ADK agents, delegation patterns, and agent orchestration for intelligent task distribution
Expert guidance for integrating Ollama local AI models with Python applications, including installation, configuration, model management, and production deployment
Use when evaluating LLMs, running benchmarks like MMLU/HumanEval/GSM8K, setting up evaluation pipelines, or asking about "NeMo Evaluator", "LLM benchmarking", "model evaluation", "MMLU", "HumanEval", "GSM8K", "benchmark harnesses"
Generate project documentation including CONTENTS.md navigation files and AGENTS.md instructions. Use when creating documentation structure, project indexes, or AI agent configuration files.
Guidance for using Brain semantic memory effectively. Applies Zettelkasten atomic note principles with observations and relations. Use when deciding whether to query or create notes, structuring note content, or understanding the semantic knowledge graph.
Codex-native skill creator. Self-contained 4-phase methodology for creating production-ready Claude Code skills. Adapted from SkillCreator v3.2 for Codex agents with embedded methodology and simulated synthesis panel.
Mise configuration and runtime management expert. Use when: - Installing programming language runtimes (node, python, go, rust, etc.) - Configuring tool versions globally or per-project - Questions about mise.toml, global config, or shims - Installing CLI tools (especially AI CLI tools like gemini, codex, opencode) - Troubleshooting "command not found" for mise-managed tools - Comparing mise to nvm, pyenv, rbenv, goenv - Setting up development environments Do NOT use for: - General coding questions unrelated to tooling - Questions about specific programming languages (use language-specific agents)
Write SKILL.md for the user using all available wisdom and documented guidance about how Agent Skills are made. New skills are written carefully to be orthogonal to the existing skills in the same repo.
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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
