Use this skill when capturing user corrections, feedback, or learnings from a session to permanently improve other skills. This includes when users correct skill selection, suggest better approaches, validate successful patterns, or identify mistakes that should never be repeated. Invoked automatically by work-command-center at session end when feedback is detected.
Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy), machine learning (XGBoost, LightGBM, NGBoost, Torch MLP, Lightning, GP), ML utilities (Sklearn preprocessing, metrics, splits), conformal prediction (MAPIE), or model explainability (SHAP). Triggers for: (1) Writing East programs with @elaraai/east-py-datascience, (2) Derivative-free optimization with MADS, (3) Bayesian optimization with Optuna, (4) Discrete/combinatorial optimization with SimAnneal, (5) Gradient boosting with XGBoost or LightGBM, (6) Probabilistic predictions with NGBoost or GP, (7) Neural networks with Torch MLP or Lightning, (8) Data preprocessing and metrics with Sklearn, (9) Conformal prediction intervals with MAPIE, (10) Model explainability with Shap.
Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing
Beginner workflow for LlamaIndex agents (Python). Use when the user wants FunctionAgent or ReActAgent with tools.
Use when building AI agents with Google's Agent Development Kit (ADK) Python - multi-agent systems, workflow agents, tool integration, Vertex AI deployment, or agent evaluation.
Design patterns for automatic skill activation at plugin or project level. Use when implementing keyword-based skill suggestions.
Generates new Claude Code subagent configuration files from user descriptions. Use proactively when the user asks to create a new subagent or agent. Keywords include create subagent, new agent, build agent, agent architecture.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Trace and evaluate GenAI applications including LLM calls, agents, RAG pipelines, and multi-step AI systems in Domino. Uses the Domino SDK (@add_tracing decorator, DominoRun context) with MLflow 3.2.0. Captures token usage, latency, cost, tool calls, and errors. Supports LLM-as-judge evaluators and custom metrics. Use when building agents, debugging LLM applications, or needing audit trails for GenAI systems.
掌握高级提示工程技术，以最大化生产环境中LLM的性能、可靠性和可控性。在优化提示、改进LLM输出或设计生产提示模板时使用。
Techniques to extract model weights, architecture, and training data through API queries
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use when working with LLM features, chatbots, AI-powered applications, or agentic systems.
Manages memory tool integration with CLAUDE.md files for dual persistence and redundancy. Handles cross-conversation learning, memory sync, and context persistence.
Create a new Agent Skill following project standards and templates. Use this when you need to encapsulate a new capability or workflow.
Self-improving context loader that MUST be run before every prompt. Searches Graphiti for relevant past work, loads appropriate vibe, and provides intelligent recommendations.
Beginner workflow for OpenAI Agents SDK (Python or TypeScript). Use when the user wants a code-first agent app with tools, handoffs, streaming, and traces.
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
Core ML systems concepts including ML lifecycle, system architecture, requirements, and design principles for production ML.
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and context engineering.
Create new Agent Skills for the Momentum Firmware project
Display all loaded Claude Code skills by category with counts and paths
Using this skills to understand Agent Context Protocol when user mentioned or working with this.
Process and analyze text using modern NLP techniques - preprocessing, embeddings, and transformers
Fine-tune LLMs 2x faster with 80% less memory using Unsloth. Use when the user wants to fine-tune models like Llama, Mistral, Phi, or Gemma. Handles model loading, LoRA configuration, training, and model export.
