yaojingang/yao-open-prompts

Practical bilingual AI prompt library for prompt engineering, work, learning, content, marketing, and everyday use.

What it solves

This project provides a clean, organized, and ready-to-use library of 135 bilingual (Chinese and English) AI prompts. It solves the problem of scattered, low-quality, or tutorial-cluttered prompt collections by curating professional-grade templates that are stripped of unnecessary marketing fluff and formatting, making them immediately copy-pasteable for real-world tasks.

How it works

Prompts are categorized by scenario (e.g., Marketing, Learning, Content Creation, Work) and follow a standardized file structure. Each prompt includes a consistent header (frontmatter) and a clean body containing only the title, a brief introduction, and the prompt itself. Users browse the catalog, select a template, replace placeholders like {{variables}} with their specific task details, and run them in their preferred AI model.

Who it’s for

This library is designed for professionals, content creators, marketers, and students who want to improve their AI interactions. It is particularly useful for those needing structured workflows for tasks like GEO (Generative Engine Optimization) marketing, course design, technical document generation, and critical thinking exercises.

Highlights

  • Structured Meta-Prompting: Includes a V1.0 system for designing, diagnosing, and optimizing prompts using an RTF-enhanced architecture.
  • Specialized Marketing Templates: Features 46 marketing-focused prompts covering GEO strategies, course sales, and growth diagnostics.
  • Content Generation Tools: Offers specific generators for wide-format knowledge infographics, social media content, and HTML-ready articles.
  • Clean & Maintainable: All prompts are stripped of tutorial noise and screenshots, ensuring a professional, developer-friendly experience.
  • Bilingual Support: Every prompt is mirrored in English, ensuring accessibility for a global user base.

Related

  • Project
    zjunlp/EasyEdit

    A unified framework for knowledge editing in LLMs that allows users to update, insert, or erase specific facts and behaviors without full retraining.

  • Project
    mmparko/dsh-purge

    dsh‑purge is an open‑source red‑team plugin for DeepSeek Harness (web and desktop). It adds a UI dock that lets you apply custom prompt‑injection patches, view patch status, and restore the original host policy. Install via `dsh plugin --profile <web|desktop> add dsh-purge`, then click **Apply** in the new dock. The tool is MIT‑licensed, requires attribution, and is intended only for local, authorized security testing.

  • Project
    ax-llm/ax

    Ax is a multi‑language framework that lets you declare typed LLM signatures (via a DSL, fluent builder, or Zod‑style schemas) and run them against any supported provider. It compiles the same program model to TypeScript, Python, Java, C++, Go, and Rust, offering agents with memory/tools, streaming‑first execution, and optimizable flows—all with zero prompt‑engineering and near‑native provider latency.

  • Project
    pingcap/autoflow

    AutoFlow is an open-source Graph RAG knowledge base tool that enables users to create conversational search experiences using a built-in website crawler and TiDB Vector.