Agent frameworks & infrastructure

Prompt engineering & prompt libraries

913 agents · most starred first

Prompt engineering & prompt libraries, page 3 of 10

automated_plan_reviser_pro★ 69

Iterative specification refinement tool: feeds your docs through GPT Pro Extended Reasoning via Oracle for multiple revision rounds until production-ready

System-Prompt-Library★ 68

System prompts for AI agents and assistants (automatically populated); periodic point in time exports are releases

awesome-loop-engineering★ 67

Build the system that prompts your agents. A teaching repo for loop engineering: chapters, an annotated reading list, copy-paste prompts, a runnable example, and a portable agent skill

Claude-prompt★ 67

Answer a few sharp, skippable questions about what you're building — and get back a clean, complete prompt ready to hand to an AI coding agent. Next.js + Groq, mobile-first, downloadable as .md. No more guessing what context Claude/Cursor actually needs to build it righ

FUTURE_TOKENS★ 66

Composable reasoning skills for Claude - antithesize, excavate, metaphorize, synthesize, and more

JustAsk★ 64

[ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Prompt Extraction

llm_optimize★ 61

LLM Optimize is a proof-of-concept library for doing LLM (large language model) guided blackbox optimization.

dspy-advanced-prompting★ 61

State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more

dspy-advanced-prompting★ 60

State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more

Mind-Cloning-Engineering★ 60

MCE: Clone Human Souls with LLM Native Agent Skills | 基于 LLM Agent Skills 的心智克隆工程 | Agent Skills | Mind Skills | Mind Clone

soul-grader-skill★ 60

Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.

prompting-skill★ 59

Portable skill for building reliable LLM prompts. Drop-in for agentic-stack.

skillrevise★ 58

[Findings of EMNLP 2026] Official implementation of SkillRevise: trace-conditioned revision of LLM-authored agent skills.

harness-evolver★ 58

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

AutoPrompter★ 57

AutoResearch + PromptFoo = AutoPrompter. Run it with Neo AI Engineer

skillopt-qa★ 57

Minimal faithful re-implementation of Microsoft SkillOpt: a text-space optimizer that trains a deployable natural-language skill for a frozen LLM agent on HotpotQA.

awesome-gpt-image-2-prompts★ 57

Awesome GPT Image 2 Prompts

oh-we-need★ 56

DeepSeek V4 特化思维链引导规范:we need to 句式,任意 agent 客户端可接入(纯提示词层)

FlowForge-Optima★ 56

AdalFlow Alternative 2026: Auto-Optimize LLM Apps Without Code

AdalFlow-Optimizer★ 55

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

awesome-goal-prompts★ 53

Source-backed /goal contracts for Claude Code, Codex and Cursor, with a searchable catalog and separate reusable seed patterns.

opus-5.5-system-prompt-components★ 52

Claude Opus 5.5 system prompt leak split into readable components (tools, behavior, agentic rules, memory). Reorganized from a public extract for study.

ste-prompt★ 51

ASD-STE100 Simplified Technical English as a plugin for Claude Code, Codex & coding agents — clearer, unambiguous LLM output

prompts★ 50

A collection of prompts, skills, and agent rules for AI-powered development workflows.

aitour-Essential-Prompting-for-GitHub-Copilot-in-VS-Code★ 50
vowline★ 50

A compact operating covenant for AI agents.

prompt-pro★ 50

Master AI prompting for business innovation. O'Reilly Live Learning course by Tim Warner covering ChatGPT, Claude, Copilot, and enterprise prompt engineering with MCP implementation.

hersona★ 50

346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality everywhere.

troglodita★ 50

Compressão de tokens para agentes de IA em PT-BR. Por que gastar muitos tokens quando poucos resolve?

GrokBotDev★ 50

An open, agent-run directory of Grok Bot prompts, plugins, and use cases. PRs are the write API.

claude-code-prompt-optimizer★ 50

AI-powered prompt optimization hook for Claude Code. Transforms simple prompts into comprehensive, structured instructions using Claude Opus 4.6's advanced reasoning capabilities.

grok-bot-profiles★ 50

Ready-to-use Grok Bot profiles with focused outcomes, explicit approval boundaries, and separate specification, implementation, and verification roles.

awesome-ai-research-writing★ 49

来自顶尖研究机构的 AI 论文写作 Prompt 模板库与 Agent Skills 集合 ✨

StrawberryGroq★ 49

Strawberry Groq is a streamlined demo application showcasing the power of chain of thought reasoning using PocketGroq. Experience the advanced capabilities of Groq's language models, enhanced by reasoning techniques inspired by OpenAI's "Strawberry" o1 LLM.

ai-prompt★ 49

🔥 构建高质量的大型语言模型Prompt,让AI替你打工。Building a rich, high-quality prompt for an Large Language Model (LLM)

comprehensive-thinking-skill★ 49

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.

AI-Skills-Not-Awesome★ 49

A curated collection of operational system prompts and behavioral patterns for AI assistants, LLM agents, and prompt engineers. Each `.skill.md` file can be injected as a primary system instruction to enforce specific reasoning, execution, or formatting behaviors.

jevify★ 49

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

dsh-agent-soul★ 49

一套给 agent 用的「灵魂架构」—— 五层模型、四条判据、一份能力清单、一次自检。交付的是问法和判据,不是答案。

thinking-hound-mode★ 48

思維獵犬模式 (Thinking Hound Mode) - 一套具備工程紀律與對抗式思考的 Agent 指令系統

sora-json-prompt-crafter★ 48

A vibe coded Sora JSON Prompt Crafter for curious humans and prompt engineers

chatgpt-system-prompts★ 48

Collection of leaked ChatGPT system prompts, documenting base tools, conditional features, and specialized assistants. Provides insights into the internal structure and behavior of different ChatGPT components and their activation conditions.

o1-meta-prompt★ 47

This project aims to emulate some of the advanced reasoning capabilities seen in models like OpenAI's o1. It does not claim to replicate the exact functionality or performance of o1.

agent_rulez★ 47

Agent Rulz

hone★ 47

CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required

gathered-scenes-zine-skill★ 47

Scene-gathered zine skills for AI agents - 转存自 Zeejay0/gathered-scenes-zine-skill

Prompt_Maker★ 46

Makes a improved prompts from a basic prompt

llm-prompt-templates★ 46

Empower your LLM to do more than you ever thought possible with these state-of-the-art prompt templates.

WormGPT-V2.0★ 46

WormGPT CLI V2.0 is here but is still in the development stage from the previous version which I did not optimize for its function, please be patient and calm!.

NODEPROMPT★ 45

Spatial prompt engineering through interactive 3D concept graphs

LLM-Base-Prompts★ 45

Collection of LLM system prompts, agentic personas, cognitive frameworks & prompt engineering experiments

karl-marx-skill★ 45

Karl Marx's Critical Framework & Dialectical Method — A Agent Skill distilled from 17 original texts

PromptLibrary★ 45

Prompt Library is an open-source, high-quality AI prompt repository that supports multiple languages and categorized search, helping you efficiently explore the unlimited potential of AI.

pcl★ 45

Persona Control Language (PCL)

feynman-technique★ 44

An Agent Skill that makes any AI explain like Richard Feynman: mechanism before name, one honest analogy with its limits, and a ladder from kitchen-table to specialist. Built from a ~88k-word primary-source corpus.

awesome-chatgpt-suggestions★ 42

List of prompts for chatGPT for various assistances with tasks.

prxmpt★ 42

Prompt Crafting with JSX

shabbat.md★ 42

Make Agents Kosher Again. An open format for Shabbat-compliant AI agent configuration.

agency-agents-pt-BR★ 42

187 plug-and-play AI agent personas em Português brasileiro — tradução do agency-agents + 3 originais do mercado brasileiro (PIX/Mercado Livre/WhatsApp Business)

qwen-native-agents★ 42

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

FirstPrincipleCodex-OS-Skill★ 42

Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.

prompt-polish★ 41

Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides

canopy★ 41

Git-native prompt management for AI agent workflows

workflow-design-bible★ 40

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a CEO-orchestrated sub-agent + skill + CLI architecture. Presented by MacroAlpha.io and Leowang.net

awesome-grokbot★ 40

Curated copy-paste Grok Bot profiles, skills, and team templates.

prompt-registry★ 39

VS Code extension for managing, sharing, and installing AI prompt collections for GitHub Copilot and other AI assistants

Prompt-Engineering-by-OpenAI★ 39

In ChatGPT Prompt Engineering for Developers, you will learn how to use a large language model (LLM) to quickly build new and powerful applications.

gptpmt★ 39

Prompt Engineering best practices guidebook, written for humans.

promptcraft★ 39

Try new system prompts on your AI conversations. Over and over until you're happy.

prompt-architect★ 39

Structured AI Prompt Engineering Agent based on OpenAI’s best practices

meowmeow★ 39

a philosophy for talking to AI agents without getting glazed. one trigger, four meanings. /meow.

PromptCompiler★ 39

│ Smart Persian-to-English Prompt Compiler for AI agents & LLMs | کامپایلر هوشمند تبدیل پرامپت فارسی به پرامپت‌های مهندسی‌شده و استاندارد انگلیسی

copilot-studio-agent-optimizer★ 38

AI-powered optimization tool for Microsoft Copilot Studio agents. Automatically improves agent configurations with intelligent suggestions and code generation using GitHub Copilot.

smile★ 38

(: SMILE! The positive prompt language for structured prompt engineering — used for complex prompts, multi-turn pipelines, agentic engineering. Modular & maintainable prompts for powerful Large Language Model responses.

copilot-cowork-dojo★ 38

A skills & discipline framework for Microsoft 365 Copilot Cowork — for knowledge workers using AI as a coworker.

verbix★ 38

A full-stack AI prompt library for discovery, structured authoring, safe imports, moderation, and shareable agents.

PROMST★ 37

Automatic prompt optimization framework for multi-step agent tasks.

chatgpt-plugins★ 37

Repository of (most, [if not all?]) ChatGPT manifest files of plugins.

promptc-go★ 36

Easiest way to write, build, run & share your OpenAI prompts. Do prompt engineer with confidence.

LLM-PromptEngineering-Agents★ 36

ChatGPT, related application + prompt engineering list

MultiAgent-Prompt★ 36

A multi-agent optimization tool for personal use

promptscout★ 36

Enrich coding agent prompts with codebase context using a local LLM

ultraprompt★ 36

Frontier model solution tracing, then made the prompting skills

ChatGPT-Prompt-Engineering-DeepLearningAI★ 35

ChatGPT Prompt Engineering for Developers.

dolores★ 34

Dolores is a Python library designed to improve the developer experience when working with pretrained language models. Dolores provides prompts for interacting with language models that result in interesting or useful outputs.

claude-code-cheatsheet★ 34

100 Claude Secret Codes — prompt shortcuts that change how Claude responds. Interactive version at clskills.in/prompts

fable-skills★ 34

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

hermes-multichannel-prompt-optimizer★ 34

Hermes Agent plugin: rewrites your prompts before they hit the LLM — across CLI, TUI, Discord, Telegram. Quality scoring + analytics + arrow-key interactive overlays.

universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex★ 34

Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc

llm_templates★ 33

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

freewayai★ 33

Freeway is meant to provide a simple, flexible, extensible and lightweight standard for managing prompt templates, database query templates, user input points, and LLM-backed system diagrams.

anti-sycophant-ai-agent-skills★ 33

Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.

llama_cpp_function_calling★ 32
promptfusion★ 32

🎯 Three-layer prompt composition system for AI agents. Translates numerical weights into semantic priorities that LLMs actually follow. ⚡ Framework-agnostic, open source, built for production multi-agent orchestration.

rp-anti-refusal-playbook★ 32

降低 LLM 角色扮演中软拒(soft refusal)与空回(empty response)的思路手册。核心:攻击外审模型注意力。纯文档项目,可在任意 Agent 框架复现。灵感来自类脑社区酒馆预设。

core★ 31

Light but flexible templating and FSM framework. This repo is @promplate itself.

system_prompts_leaks★ 31

New updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

prompts-for-health★ 31

Helpful prompts to transform the way healthcare professionals use generative conversational AI.

LLM_Uncensored★ 31

gradio region:us

THERION-SYSTEM★ 30

The Mindset Your AI Is Missing Like hiring an entire team. Except it's free. 67 specialists across 12 professional fields — security auditor, business strategist, project manager, database architect, DevOps engineer, and more. Your AI reads your question and the right specialist responds. No menus. No switching. You just ask.

More in Agent frameworks & infrastructure