Data Ai skills for AI agents

Craft effective prompts for AI image generation models to produce high-quality visual outputs. Use this skill when the user asks about creating AI-generated images, writing image prompts, improving their generated image results, or wants guidance on composition, style references, negative prompts, or iterating on visual outputs from any text-to-image system.

Guides the design and development of AI-powered products. Trigger when users ask about UX for AI features, handling AI uncertainty in products, human-in-the-loop design, AI failure modes, building user trust in AI, AI ethics in products, or designing AI-first experiences. Covers the intersection of product thinking, user experience, and AI capabilities.

Guides exploratory data analysis, statistical methods, and insight extraction. Trigger when users ask about EDA, data cleaning, pandas or SQL patterns, hypothesis testing, summary statistics, data profiling, outlier detection, or extracting insights from datasets. Covers practical analysis workflows from raw data to actionable findings.

Guides data visualization design, chart selection, and dashboard creation. Trigger when users ask about choosing chart types, dashboard design, storytelling with data, color palettes for data, visualization libraries, Matplotlib, Plotly, D3, or presenting data effectively. Covers principles of visual communication and practical implementation.

Guides A/B testing, experimentation design, and statistical analysis of experiments. Trigger when users ask about A/B tests, statistical significance, sample size calculation, experiment design, randomization, multivariate testing, experiment analysis, or common experimentation pitfalls. Covers the full experimentation lifecycle from hypothesis to decision.

Guides feature engineering for machine learning models. Trigger when users ask about feature selection, feature transformation, encoding categorical variables, creating temporal features, text feature extraction, feature stores, or preparing data for ML models. Covers practical patterns for turning raw data into predictive signals.

Guides model fine-tuning decisions, data preparation, and training strategies. Trigger when users ask about fine-tuning LLMs, when to fine-tune vs use prompting, training data preparation, LoRA and parameter-efficient fine-tuning, evaluation of fine-tuned models, deployment of custom models, or cost optimization for fine-tuning. Covers the full lifecycle from decision to production.

Guides ML model evaluation, metrics selection, and monitoring. Trigger when users ask about choosing evaluation metrics, cross-validation strategies, detecting model bias, fairness in ML, A/B testing models in production, monitoring model drift, or understanding model performance. Covers rigorous evaluation from development through production.

Guides end-to-end ML pipeline design and MLOps implementation. Trigger when users ask about building ML pipelines, data ingestion, feature engineering workflows, model training infrastructure, model deployment, model monitoring, CI/CD for ML, or MLOps best practices. Covers orchestration, reproducibility, and production-grade machine learning systems.

Design effective prompts for large language models to produce accurate, consistent, and useful outputs. Use this skill when the user asks about writing better prompts, improving LLM outputs, using chain-of-thought reasoning, few-shot examples, system prompts, or wants guidance on advanced prompting techniques for any AI language model.

Guides LLM prompt design and optimization. Trigger when users ask about writing system prompts, few-shot learning, chain of thought prompting, structured output from LLMs, prompt evaluation, prompt templates, or optimizing LLM behavior. Covers practical prompt patterns for building reliable AI applications.

Guides Retrieval Augmented Generation system design and implementation. Trigger when users ask about RAG pipelines, chunking strategies, embedding models, vector databases, semantic search, hybrid search, retrieval quality, document processing, or knowledge base systems. Covers the full RAG stack from document ingestion to answer generation.