Awesome AI AgentsPrompt Libraries

YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

⭐ 1855 TypeScript repository created 2026-01-21

This repository packages an agent skill that gives AI assistants the ability to search and recommend prompts for Nano Banana Pro, the Google Gemini image generation model. It bundles a curated library of more than 10,000 prompts organised by use case, each stored with sample images so the resulting style can be previewed before the prompt is copied. The skill installs into OpenClaw through its package hub, and into Claude Code, Cursor, Codex, Gemini CLI and Windsurf through the universal skills installer, which auto-detects the host assistant. It supports two modes of use. In direct search mode the user describes what they need in natural language, for example a cyberpunk avatar or a product photo on a white background, and the skill returns up to three recommendations with a translated title and description, the exact English prompt text, sample images and a note on whether reference images are required. In content illustration or remix mode the user pastes an article, video script or podcast notes, the skill proposes matching style templates, asks a few personalisation questions such as mood or setting, and produces a customised prompt for that content. Internally the skill identifies a category from keyword signals and then runs a grep-style search over the matching JSON file, deliberately never loading a full category file, which keeps token consumption low despite the library size. Categories include social media posts, product marketing, profile avatars, posters and flyers, infographics, e-commerce shots, game assets, comics and storyboards, YouTube thumbnails and app or web design mockups. Prompts are collected from public community posts and synced into the repository twice daily by a scheduled GitHub Actions job. Responses are multilingual while the generation prompt itself is always supplied in English.

https://github.com/YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

agent-skillspromptsimage-generationgeminiclaude-code

Also in Prompt Libraries

asgeirtj/system_prompts_leaks

This repository provides a collection of extracted system prompts from various large language models (LLMs) including Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and xAI's Grok, updated ...

HKUDS/RAG-Anything

RAG-Anything is a next-generation all-in-one multimodal Retrieval-Augmented Generation system that processes and queries diverse document content including text, images, tables, and equations within a unified framework.

dzhng/deep-research

Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.

dottxt-ai/outlines

Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.

microsoft/RD-Agent

RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.

arcee-ai/mergekit

mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.

icip-cas/PPTAgent

PPTAgent is an innovative system that automatically generates and evaluates high-quality presentations from documents using a two-phase approach and a comprehensive multi-dimensional evaluation framework.

serenakeyitan/awesome-notebookLM-prompts

A curated collection of NotebookLM and Kael.im slide prompts designed to generate presentation-ready decks from various content types.