prompts

Curated, original high-craft prompts for AI video ads (Seedance 2.0 / Veo 3 / Kling / Runway). Companion to HeyDreaming.

A companion guide for the blog post series, LangChain Decoded.

A wrapper of LLMs that biases its behaviour using prompts and contexts in a transparent manner to the end-users

Modular Prompting IDE - A lightweight web app allowing developers to componentize their prompt library for better, faster prompts.

470 AI web design prompts — Generate stunning landing pages in seconds. Works with Bolt.new, v0, GPT-Engineer. 100% original designs, MIT licensed.

🎨 AI-Powered Prompt Generator | Transform ideas into powerful AI prompts instantly with smart credit system, real-time streaming, and 14 specialized categories. Built with React, TypeScript, Supabase & deployed on Vercel. Try 3 free generations - no signup required! ⚡

Fold your whole codebase into one LLM-ready prompt.

专为学术小白打造的零门槛 AI 论文写作提示词库。彻底告别“AI八股文”与数据幻觉，只需复制粘贴，还原最真实的人类学术写作质感！

A beautiful and elegant chat GPT prompt management system

Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai

AI prompt database and builder skill for Claude Code. 2,500+ curated prompts across 19 categories and 17 AI models.

A collection of prompts for Llama

Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).

LLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases

Lightweight markdown-based workflow for collaborating with AI coding assistants using spec-driven development methodology

AI-powered project management framework based on an opinionated view on effective prompts and a highly modular approach to building effective agents, workflows, templates, prompts and context documents.

Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR)

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

一个内含 project-scoped skill 的 GitHub Template，用 Claude Code 或 Codex 把原始资料整理成可校验、可查询的本地知识库。

Rational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and reverse engineering. | 面向 Codex 与 LLM 的理性工程系统提示词：强调准确性、软件工程、AI、网络安全、漏洞研究与逆向工程。