Найдите подходящую возможность для вашего агента.
Use when "deploying ML models", "MLOps", "model serving", "feature stores", "model monitoring", or asking about "PyTorch deployment", "TensorFlow production", "RAG systems", "LLM integration", "ML infrastructure"
Launch background Claude sessions to explore and analyze business ideas. Say "Idea: [description]" to trigger.
Meta-skill that orchestrates other skills into intelligent, self-coordinating workflows. Use when complex tasks require multiple skills working together, need automated skill routing based on task analysis, want to save and replay successful skill combinations, need state persistence across skill boundaries, or building multi-stage processing pipelines. Provides 4 modes - QUICK (1-2min, single skill), STANDARD (5-10min, multi-skill chains), DEEP (15-30min, DAG composition), EXPERT (custom, learning optimization).
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
External persistent memory for cross-session knowledge. Use when storing error patterns, retrieving learned solutions, managing causal memory chains, or persisting project knowledge.
Creates new Claude Skills following Anthropic best practices with proper structure, progressive disclosure, and security. Activates when user mentions "create skill", "new skill", "skill for", "make a skill", "создать skill", "помоги создать skill", or wants to package expertise into reusable capability. Self-contained with templates, examples, and knowledge embedded.
Deep code and system analysis using the Quantum Cognitive OS. Use when analyzing code, architectures, or complex systems that benefit from multi-dimensional reasoning.
Generate production-ready Workscript workflow JSON files for the Workscript Agentic Workflow Engine with built-in defensive guards and complexity detection. Use when asked to create workflows, automations, data pipelines, or generate workflow JSON. IMPORTANT - For complex requests that would result in deeply nested or overly complex workflows, this skill will STOP and suggest developing new custom nodes first using /new-node, then return to create a simpler, more linear workflow. All generated workflows include data validation (validateData node) for structured JSON outputs, input guards, array length checks, and error handling edges. Fetches up-to-date node documentation from the Reflection API when available. Outputs validated .json files to the sandbox prompts folder. Also suitable for Claude Code subagents needing to compose workflows programmatically.
Provides specialized knowledge and content creation for Physical AI and Humanoid Robotics topics with focus on accuracy and peer-reviewed sources.
Core agent steering with HHH framework (Helpful, Honest, Harmless), exploration-before-implementation workflow, and anti-sycophancy rules. Use when guiding AI agent behavior, handling disagreements, or establishing interaction patterns. Always active for all agent interactions.
Universal guide for creating production-ready Claude Code skills for any project. Includes 6-step workflow (understand, plan, initialize, edit, package, iterate), progressive disclosure design, YAML frontmatter templates, validation scripts, reference organization patterns, and 10 community-proven innovations. Use when creating new Claude Code skills, converting documentation to skills, improving existing skills, or learning skill development best practices for any domain.
Invoke this skill first when authoring any AI agent instructions. Foundational principles for writing LLM instructions (skills, CLAUDE.md, rules, commands). Covers token economics, imperative language, formatting for LLM parsing, emphasis modifiers, terminology consistency, and common anti-patterns.
Manage Gemini Deep Research API quotas with rate limiting, exponential backoff, and client-side tracking. Use when handling API quota errors, implementing rate limiting, batch job submission, or when asked about quota limits, rate limiting, throttling, or API quotas.
Intelligent Kubernetes operations using the kubectl-ai plugin. Use when generating, applying, or debugging Kubernetes resources via natural language.
AI агент для ABM. Используй для автоматизации ABM кампаний и персонализации outreach.
Research external APIs/services/libraries for feature implementation. Interviews user, researches options, confirms choice, gathers implementation notes. Creates .claude/plans file.
Plan and guide Repo Prompt integration and usage in AI coding workflows. Use when integrating Repo Prompt with editors/agents.
Help user START tasks with activation support for ADHD. Use when user is stuck, overwhelmed, or asking what to do next. Auto-triggers on phrases like "I'm stuck", "can't get started", "overwhelmed", "what should I do", "next step", "where do I start", "jag fastnar", "kan inte börja", "vad ska jag göra", "nästa steg".
