Skill UI

Guides engineering teams on compressing long agent conversations by focusing on tokens-per-task rather than tokens-per-request, using structured summaries, triggered strategies, and probe-based evaluation to keep artifact trails intact.

Explains what makes up a language model’s context state and how engineers should structure prompts, tools, retrieval, history, and outputs to guide agent behavior and manage token budgets.

Provides elite guidance on dynamic context management, vector databases, knowledge graphs, intelligent memory, RAG, and multi-agent workflows so AI systems maintain relevant, actionable information across enterprise scenarios.

Designs scalable batch and streaming pipelines, modern warehouses, and analytics platforms with Spark, dbt, Airflow, cloud data stacks, and governance practices.

Guides ML engineers through the Databricks secondary workflow that links Feature Store engineering, MLflow experiment tracking, model registry versioning, and serving so production-grade models can be trained and deployed.

Automatically activates when you mention feature engineering helper, offering guidance on data preparation, model training, hyperparameter tuning, and experiment tracking for ML projects.

Provides expert guidance for GRPO training with TRL, covering dataset prep, reward engineering, structured outputs, and multi-objective alignment when preference pairs are scarce.

Generate high-quality videos from text prompts via Kling AI, tuning duration, resolution, and aspect ratio while monitoring progress and downloading results—ideal for creators or learners honing prompt engineering.

Defines scalable, secure Kubernetes platform architecture, multi-cluster strategy, and GitOps automation (ArgoCD/Flux) while advising on service mesh, platform engineering, and cost-efficient operations for enterprise container workloads.

This skill guides users through advanced prompt optimization techniques for Large Language Models (LLMs). It functions as an expert prompt engineer coach, applying methodologies like Constitutional AI and Chain-of-Thought reasoning. Use it to transform basic, raw instructions into highly effective, production-ready prompts, significantly improving accuracy, reducing hallucinations, and optimizing token usage for cost efficiency.

Designs, optimizes, and evaluates prompts for LLM applications by defining success criteria, choosing chain-of-thought or few-shot formats, testing diverse cases, enforcing structured schema outputs, and documenting guardrails so deployments stay accurate and efficient.

Document describes structured prompts, chain-of-thought guidance, few-shot examples, system prompt design, and tooling advice for building reliable prompt engineering workflows in LLM-augmented products.