Найдите подходящую возможность для вашего агента.
Agent-to-Agent (A2A) server configuration patterns for HTTP, STDIO, SSE, and WebSocket transports. Use when building A2A servers, configuring MCP transports, setting up server endpoints, or when user mentions A2A configuration, server transport, MCP server setup, or agent communication protocols.
Generate GameSpec JSON and Lua scripts for the AI Game Platform. Use when creating games, adding features like player movement, enemies, collectibles, or fixing Lua script issues. Supports FPS, 2D side-scrollers, and 3D platformers.
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.
基于用户画像和向量化笔记提供个性化对话。当用户需要个性化交流、上下文感知的回应，或希望 AI 记住并引用其之前的想法和笔记时使用。
Combined workflow for starting an AI collaboration session. Runs hydrate, vault-status, and prompts for session focus. Use at the beginning of any work session to load context and orient.
Implements sophisticated multi-level reasoning for complex problems requiring strategic planning, tactical approach design, and operational execution. Use for problems needing deep analysis, multi-step reasoning, systematic decomposition from first principles to implementation, convergence-aware iterative refinement, or uncertainty quantification across abstraction levels.
Comprehensive Python AI/ML development expert with 10+ years experience using UV package manager. Covers PyTorch, TensorFlow, scikit-learn, transformers, langchain, pandas, numpy, OpenCV, and all major AI/ML libraries. Automatically audits projects, generates production-ready code with type hints, optimizes performance, sets up RAG pipelines, manages dependencies with UV, and ensures best practices. Use for AI/ML project setup, model training, data processing, LLM applications, computer vision, code generation, dependency management, performance optimization, and comprehensive project auditing. Excludes Tkinter and desktop UI libraries.
Emergency Engineer persona for critical production issues. ACTIVATE when messages contain emergency, production, down, critical, urgent, fix, broken, outage, or disaster keywords.
Turns ambiguity into an Uncertainty Register, prioritizes items, and produces observation tasks/experiments with evidence and decision rules. Use when the user mentions uncertainty/unknowns/assumptions/validation/investigation/hypotheses/risks or cannot decide (不確実性, 曖昧, 未知, 前提, 仮説, 検証, 調査, 優先順位, 観測, 意思決定).
Generate user activity diary from Claude Code history. Use when user asks to create diary, summarize activities, or when launchd triggers daily generation.
Creates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills.
Scaffold, structure, and deploy the Physical AI textbook in Docusaurus with book-aware content and RAG-ready exports. Use when creating or updating the Docusaurus site, adding chapters, configuring sidebar, or deploying to GitHub Pages/Vercel.
Machine learning model training, evaluation, deployment, and MLOps workflows.
Optimize and create Claude Rules (.claude/rules/*.md) following best practices.
Explains code in simple terms with visual diagrams. Use when the user asks to explain code, understand how something works, or wants a code walkthrough.
Entfernt Anzeichen von KI-generiertem Text. Verwende diesen Skill beim Bearbeiten oder Überprüfen von Texten, um sie natürlicher und menschlicher klingen zu lassen. Basiert auf Wikipedias umfassendem "Signs of AI writing" Leitfaden. Erkennt und behebt Muster wie: aufgeblasene Symbolik, Werbesprache, oberflächliche -ing-Analysen, vage Zuschreibungen, Gedankenstrich-Übernutzung, Dreierregel, KI-Vokabular, negative Parallelismen und übermässige Konjunktivphrasen.
Create slash commands for Claude Code with proper frontmatter, arguments, and bash execution. WHEN: MUST use when creating new slash commands. Invoke with "/claude-command-development" or "create a command", "new slash command", "write a Claude command". WHEN NOT: Creating agents (use claude-agent-creator), creating skills (use claude-skill-creator).
Manages Human-in-the-Loop (HITL) approval workflows for sensitive actions. Use when creating approval requests, processing approved items, or implementing safety controls for autonomous actions.
