Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

A meta-prompting system that transforms raw prompts into production-ready, XML-structured prompts optimized for Claude Opus 4.6. 10 codified rules, 10-component framework, complexity-based routing — based on Anthropic's official best practices.

Universal Prompt Generator — prompt-engineering system for text-to-image models. Spectrum of 1–5 calibrated prompts per theme, with safety/drift/cliche enforcement built into the pipeline.

SoftPrompt-IR is a low-level symbolic annotation layer for LLM prompts, making intent strength, direction, and priority explicit. It is not a DSL or framework, but a minimal, composable way to reduce ambiguity, improve safety, and structure prompts.

Timeless principles and best practices for working with language models - tooling-agnostic, future-proof, and clear.

A prompt that makes an LLM self-audit its recommendation bias toward a specific thing / 让大模型自检对某事物推荐倾向的提示词

PromptWeaver: RAG Edition helps design effective prompts for Traditional, Hybrid, and Agentic RAG systems. It offers templates, system prompts, and best practices to improve accuracy, context use, and LLM reasoning.

Spec-first protocol for rule-ordered depth routing and bounded epistemic output in AI chat.

Example dataset and prompt design of Korean Offensive language Machine Generation (K-OMG), published at IJCNLP-AACL 2023.

A framework for shaping identity-aware cognition in language models using behavioral prompt layering, recursive interpretive constraints, and modular cognitive modes.

Редакторский инструмент для естественного делового письма на русском без нейрояза, канцелярита, карьерных штампов и выдуманных деталей.

A meta-prompt that refactors any LLM prompt into a clearer, more structured, and higher-performing version using proven prompt engineering techniques.

Object-Oriented Prompt Design (OOPD): オブジェクト指向型汎用プロンプト用語定義 (Object-Oriented Terminology for Prompt Design)

A practical kit for creating, improving, and generalizing system instructions for AI agents, with extra image and video prompting guides.

Turn any raw prompt into a production-ready, XML-structured prompt optimized for Claude Opus 4.8 - 11 rules, complexity-based routing, hard prompt: trigger.

Live-updating tracker of prompt engineering tools, libraries, and techniques — refreshed every 15 mi

This is the Deno 2 implementation of all tasks I did during AI Devs 3 course. It's integrated with Anthropic and OpenAI APIs here. Many different tools regarding LLMs are used here.

Prompt Engineering tips & tricks

AI-driven cognitive assistance sandbox with EarthLight model prototypes.　Language-first decision models for AI: Equilibrium (α), Backcasting (β), Semantic Grounding (γ).

🪶 An MCP server for prompt optimization in Claude Code