Browse Skills

Use when designing or reviewing an HTTP API. Covers resource modeling, status codes, pagination, idempotency, versioning, error formats, and the contract details that break clients when you get them wrong.

Use when an LLM must return machine-readable data. It covers schema design, native structured-output modes, validation and repair, and extraction from messy input.

Use when building retrieval-augmented generation. Covers chunking, embedding and hybrid search, reranking, grounding and citation, and diagnosing whether a bad answer is a retrieval failure or a generation failure.

Write and improve prompts for language models. Covers instruction design, few-shot examples, reasoning elicitation, output formatting, and systematic failure diagnosis.

Helps select the right LLM for a task by evaluating capability, cost, latency, and routing strategies. Use when choosing a model for a new feature, reducing costs, or evaluating model migrations.

Build and operate reproducible machine learning pipelines. Covers feature engineering, train/serve consistency, drift monitoring, and retraining to avoid silent model degradation.

Use when building a Model Context Protocol server. Covers tool, resource, and prompt design, transport choice, authentication, error handling, and testing against a real client.

Use when integrating an LLM API into an application. Covers streaming, retries and rate limits, timeouts, caching, fallback across providers, and the production concerns that a tutorial integration ignores.

Provides a systematic approach for measuring LLM feature quality, including building evaluation sets, selecting metrics, using LLM-as-judge, regression testing, and production evaluation. Use before iterating on prompts or models to avoid guesswork.

Optimize LLM feature costs by identifying where tokens are spent and applying caching, context reduction, model routing, batching, and output limits without degrading output quality.

Guides the decision to fine-tune versus prompt engineering or retrieval, and provides a rigorous process for dataset construction, training with LoRA or full fine-tuning, and evaluation to achieve reliable performance improvements.

Manage what an LLM sees by budgeting the context window, retrieving relevant information, compacting history, and pruning tool results to prevent attention degradation.