Find the perfect capability for your agent.
Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with clickable widgets, entity tagging (@mentions), composer tools, or server-handled widget actions. Covers full widget lifecycle. NOT when building simple text-only chat without interactive elements.
Advanced token optimization and context management strategies.
Orchestrates long-running AI development sessions with human checkpoint control. Uses ohno for task management, manages progress tracking, routes work to appropriate skills, and implements supervised/semi-auto/autonomous modes. Use this skill when starting work sessions, resuming interrupted work, or managing multi-session projects.
Manage stories, plans, and tasks in the multi-model orchestrator. Use this skill to create feature requests, generate implementation plans, and execute tasks using different Claude models (Opus, Sonnet, Haiku).
Implementing semantic search and similarity search using vector embeddings and vector databases.
Creates new agent files with complete specifications, following the same format as existing agents. Use when a new agent is needed for tasks that existing agents cannot handle. Generates agent markdown files with name, description, core principles, workflow, and integration details.
Path-grounded multi-agent orchestration using the Liku directory hierarchy (skills.xml inheritance, todo.md + LikuErrors.md audit trail, SQLite memory). Use when you need to initialize Liku, generate an agent bundle for a specific Liku/* residence path, or expose Liku as an MCP server for Gemini-CLI, Claude Code, Copilot-CLI, or ChatGPT Codex.
Guides Tri-SSD (Tri-Layer Slice Spec Driven) workflow. Explains the three-layer model (L1/L2/L3) and recommends commands. Triggered by "仕様", "要件定義", "設計", "L1", "L2", "L3", "フェーズ", "ルール", or project specification requests.
AWS Prescriptive Guidance for best practices and architectural patterns. Use for AWS architecture recommendations, SageMaker AI endpoints guidance, deployment patterns, and AWS solution architectures.
Model Context Protocol development expert. Use when creating MCP servers, clients, or tools that enable AI agents to interact with external systems, APIs, and development environments.
State checkpointing, divergence detection, and confidence tracking for Hopper/Hardin doctrine compliance. Use PROACTIVELY when performing multi-step reasoning, external actions, or any task requiring error recovery capability. Provides checkpoint_create, checkpoint_list, checkpoint_taint, and confidence_calculate tools.
TOON Format Specialist - Token-efficient data encoding for LLM communication optimized per TOON Spec v2.0
Construit des chatwindows avec widgets interactifs ChatWidget. Guide la création de widgets selon le contrat ChatWidget, leur intégration dans ChatWindow, la configuration des workflows (OpenAI Agent / n8n), et la validation via le Playground. Utilise ce skill lorsque l'utilisateur demande de créer, modifier ou intégrer des widgets dans une conversation ChatWindow.
Game testing for CTF-AI. Use when writing tests, running pytest, Vitest, Playwright e2e tests, testing game mechanics, or validating player behavior.
Knowledge management for AI-assisted development. Use this skill when: - Starting a new session or resuming work - User asks about tasks, bugs, notes, or project status - User mentions: "what's next", "where did we leave off", "TODO", "track this" - Creating, updating, or closing tasks - Capturing notes, ideas, or research findings - Checking project vision or plans - User asks about project context or goals - Coordinating with other AI agents on the same codebase - User mentions: "save this", "remember", "note", "task", "bug", "idea" - User wants to explore or document a Python API - User mentions: "docs", "documentation", "API", "explore package"
Expert guidance for using the Azure AI Projects client library (azure-ai-projects) to build and deploy AI applications with Microsoft Foundry. This skill covers agent creation, tools integration, evaluation, connections, datasets, deployments, fine-tuning, and telemetry operations using Python SDK.
AI导师框架，通过10+顶级提示工程方法论（C.R.E.A.T.E.、Perfect Prompt Framework、修辞学方法、结构化方法、元提示词理论、迭代优化、个性化定制、逆向思维、系统思维、多模态应用）引导用户创建高效元提示词。当用户需要：(1) 学习提示工程最佳实践，(2) 创建特定任务的元提示词，(3) 优化现有提示词效果，(4) 掌握提示设计思维模式，(5) 建立个性化提示词库，(6) 应用框架解决实际问题，或 (7) 发展AI协作技能时触发。通过'创建元提示词'、'优化提示'、'提示工程指导'、'AI导师'等关键词激活。
AI 創意教練腦力激盪。當用戶說「brainstorming」、「腦力激盪」、「創意思考」、「想點子」、「發想」、「brainstorm」、「一起來想」、「幫我想」、「集思廣益」、「ideation」、「創意發想」時啟動。提供十大類別創意技術庫，由 AI 智能推薦最適合的組合，以教練式對話引導創意探索。適用於：創新發想、問題解決、策略規劃、團隊凝聚、打破框架、個人洞察。
