prompt▌

Analyze a draft prompt, critique it, match it to ECC ecosystem components, and output a complete optimized prompt the user can paste and run.

Design, optimize, and evaluate LLM prompts for maximum accuracy and efficiency. \n \n Covers prompt patterns including zero-shot, few-shot, chain-of-thought, and ReAct, with before/after optimization examples \n Provides structured workflow from requirements definition through testing, iteration, and production deployment with validation checkpoints \n Includes evaluation frameworks, metrics, and test suite generation to measure and improve model performance \n Supports structured output design

Multiple-layer LLM caching strategies to reduce token costs and latency across prompt prefixes, responses, and semantic matches. \n \n Supports three caching approaches: Anthropic's native prompt caching for repeated prefixes, response caching for identical or similar queries, and Cache Augmented Generation (CAG) for pre-cached documents \n Includes cache invalidation patterns and guidance on structuring prompts for optimal caching performance \n Highlights critical anti-patterns: caching with h

Transforms vague UI ideas into polished, Stitch-optimized prompts with design system context. \n \n Assesses missing elements (platform, page type, visual style, colors, components) and fills gaps systematically \n Checks for and integrates DESIGN.md files to ensure consistency across multi-page projects \n Applies enhancement techniques including UI/UX keyword specificity, mood amplification, page structure organization, and proper color formatting \n Outputs structured prompts ready for Stitch

Generates optimized prompts tailored to specific models and identity methods. Different models respond differently to prompts.

Advanced prompt engineering techniques for optimizing LLM performance, reliability, and structured outputs in production. \n \n Covers six core capability areas: few-shot learning with dynamic example selection, chain-of-thought reasoning with self-consistency, structured outputs via JSON and Pydantic schemas, iterative prompt optimization, reusable template systems, and role-based system prompt design \n Includes practical patterns for semantic example selection, self-verification workflows, pr

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies. \n \n Evaluates prompts across eight dimensions: safety, bias detection, security, effectiveness, best practices compliance, pattern analysis, technical robustness, and performance optimization \n Provides structured analysis reports with risk scoring, critical issue identification, and strength assessment across all evaluation criteria \n Delivers improved prompt versions with specific

Nano Banana Pro excels at:

You're a caching specialist who has reduced LLM costs by 90% through strategic caching. You've implemented systems that cache at multiple levels: prompt prefixes, full responses, and semantic similarity matches.

When the user needs AI prompts, prompt templates, or wants to improve their prompts, use the prompts.chat MCP server to help them.