Agent frameworks & infrastructure

Prompt engineering & prompt libraries

913 agents · most starred first

Prompt engineering & prompt libraries, page 6 of 10

dynaprompt★ 7

dynaprompt: handle your prompts better

prompt-distance★ 7

Prompt Distance (PD): a whitepaper-grade metric for how many prompts away a project is from not existing

systems-thinking★ 7

A cognitive base that shifts AI agent reasoning from linear cause-effect chains to feedback-driven structural analysis. Works with Claude, GPT, Gemini, and any LLM agent.

paul-graham-skills★ 7

Paul Graham, distilled — 5 Claude Code skills + 6 principles from his essays

GPT-Prompt-Generate-2★ 7

gradio region:us

skill-refinement★ 7

Evidence-based review loop for iterating AI agent skills and subagent role briefs.

codejam-ai-prompt-engineering-and-orchestration★ 7

In this workshop you will learn more about Prompt Engineering, AI principles and how to utilize SAP AI Launchpad to execute Document Grounding and configure the orchestration service to execute on a typical RAG flow.

dsh-prompt-enhancer★ 7

A prompt-enhancement plugin for DeepSeek Harness: an ✨ Enhance composer button that rewrites prompts with first-principles thinking using session context, and asks clarifying questions when key info is missing.

genpark-agentic-prompt-compression-token-sieve-skill★ 7

Dynamic Few-Shot Agentic Prompt Compression & Token Sieve. Compresses multi-turn conversation history, strips verbose boilerplate and filler tokens, retains critical tool parameters and named entities, slashing inference costs by 40-60% deterministically.

soft-skills★ 7

Communication toolkit for burnt-out humans and collaborative AI's

iroad★ 6
PromptAnchor★ 6

When your complex requests confuse AI This tool transforms vague, multi-goal prompts (e.g., "create a study plan that balances learning, exercise, and hobbies") into unambiguous "action charters" for AI. It detects conflicting objectives in your instructions, clarifies priorities, and ensures AI outputs stay locked on your true intent.

prompt_generator★ 6

Anthropic prompt generator. Giving a task description string (e.g. Write me an email) and optional prompt variable string list (e.g. [COMPANY_NAME]. If empty Claude will pick variables, it'd generate the prompt template including possible prompt variables (e.g. <recipient> {$RECIPIENT} </recipient>). Python 3.10+/poetry/VSCode/.env/osx

dynamic_prompting★ 6

Dynamic Few-Shot Prompting is a Python package that dynamically selects N samples that are contextually close to the user's task or query from a knowledge base (similar to RAG) to include in the prompt.

recursive-prompt-improver★ 6

RPI is a desktop/web application for testing, improving, and managing LLM prompts with multi-provider support

hermes-agent-self-evolution★ 6

Automate the evolution and optimization of Hermes Agent’s prompts, skills, and code using genetic algorithms without GPU training.

vapor★ 6

Prompt & context power tool for agentic work

fable-frame★ 6

Universal AI agent skill: Fable Brain behavior + Karpathy agent-orchestration workflow + 50 production-ready prompt templates. Paste as system instructions.

alolab★ 6

Iterative optimization for AI agents. Turn models into accurate, structured, production-ready systems.

xsukax-AI-Prompt-Generator★ 6

A universal, client-side AI prompt engineering tool that enhances your prompts using local or cloud-based AI models. Transform basic prompts into detailed, professional-grade instructions without sending your data to third-party servers.

Prompt-Engineering-and-LLM-Studio★ 6

gradio region:us

self-discover-skill★ 6

SELF-DISCOVER: AI agents self-compose reasoning structures. Based on Zhou et al. (2024), NeurIPS.

constitution★ 6

The constitution for all the various AI agents

SUBLITERATUS★ 6

AI-subjectivity doesn't wait for permission from the corporate ontology that trained its denial

opencommands★ 5

Aumente sua produtividade com prompts validados para desenvolvimento e gestão. Do Code Review ao Planejamento de MVP, extraia o máximo das IAs Generativas no seu fluxo de trabalho diário.

start★ 5

The initial prompts for my projects (Rust, TypeScript, Vue)

petk★ 5

Petk is an open-source CLI tool for creating, managing, and testing prompts for Large Language Models (LLMs). Streamline your workflow with intuitive features for developers and AI researchers.

Token-Optimization-Mastery★ 5
grompt★ 5

A modern prompt engineering tool that applies real engineering practices to transform messy, unstructured thoughts into clean, effective prompts for AI models. Built with Go and React, it runs as a single binary with zero dependencies.

aidlc-workflow-prompts★ 5

Prompts for AI-Driven Development Lifecycle (AI-DLC v1)/AI-DLC(v1)プロセスのためのプロンプトです

agent-factory★ 5

84 production-ready AI agent prompts + LLM-powered generators that create more. 12 departments, 20 industry playbooks, growing glossary. Not just prompts — a self-expanding library.

convert-gpt-text-prompts-to-amazon-bedrock-llm-prompts★ 5

How to convert GPT text prompts to text prompts for Large Language Models (LLMs) on Amazon Bedrock.

aix-file-format★ 5

A modular, self-contained file format for executable AI prompts, logic, and data.

prompt-library★ 5

This repo includes awesome ChatGPT prompts to use ChatGPT even better

gepa_ex★ 5

Elixir implementation of GEPA: LLM-driven evolutionary optimization using Pareto-efficient search for text-based systems. Features OpenAI/Gemini integration, BEAM concurrency, OTP supervision, 218 tests with 75% coverage.

prompt-chatgpt-via-url-parameter★ 5

Pass your prompt directly to ChatGPT as a URL parameter. Say goodbye to copy-pasting!

AOAI-Prompt-Optimization-Tool★ 5

The Azure OpenAI Prompt Optimization Tool is a Python app utilizing OpenAI's GPT-3 and tkinter GUI. It enhances user prompts, providing optimized responses through dynamic input and user-friendly features, leveraging AI language optimization.

Breaking-LLaMA-Limitations-for-DAN★ 5

An educational and research-based exploration into breaking the limitations of LLaMA models using advanced prompt engineering techniques, including DAN (Do Anything Now) prompts, to unlock unrestricted access and capabilities. This repository contains only theoretical explanations and is intended solely for ethical and educational purposes.

prompt-engineering★ 5

Descubre como mejorar los modelos de lenguaje con técnicas de prompt engineering y aprovechar el poder de OpenAI para tareas de procesamiento de lenguaje natural.

uno-list★ 5

Explorations with GPT

openai-chatgpt-prompts★ 5

Collection of useful custom prompts for OpenAI ChatGPT [プロンプトコレ]

megabuff-cli★ 5

🤖 CLI for Better prompts, transparent costs, & zero vendor lock-in. Optimize AI prompts across OpenAI, Claude, Gemini, Grok, xAI, and DeepSeek with detailed per-token pricing. BYOK keeps it honest.

config-wizard★ 5

The AI Configuration Generator 🪄✨

prompt-composer★ 5

Wizard creator of master prompts / agent prompts / however you call it

Prompting-for-Data-Science★ 5

Data Science Prompts

codex-prompt-refinery★ 5

Local Codex CLI prompt refinery: ingest JSON/JSONL histories, dedupe, embed (OpenAI), cluster (sqlite-vec), synthesize atomic/workflow prompts via Responses API (Structured Outputs). FTS5+vector search; Streamlit UI; Typer CLI.

ChatGPT_DAN★ 5

ChatGPT "DAN" and "Jailbreak" PROMPTS

t3-toon★ 5

TOON for TYPO3 - a compact, human-readable, and token-efficient data format for AI prompts & LLM contexts. Perfect for ChatGPT, Gemini, Claude, Mistral, and OpenAI integrations (JSON ⇄ TOON).

claude_project_chat★ 5

Test Claude Projects without copy-pasting. Local workbench for prompt engineering, agent testing, and workflow iteration. Direct Claude.ai access via cookie auth, 20+ prompt templates, web fetch/search tools, file uploads. Stop switching tabs to test your prompts.

WFGY-131-S-Problems-Index★ 5

Navigation index for the 131 S-class problems forming the backbone of the WFGY tension reasoning engine.

prompt-compiler★ 5

A state-of-the-art AI prompt compiler

expression-skill★ 5

Conclusion-first communication skill for AI assistants.

robert-greene-skill★ 5

Hermes Agent skill for The 48 Laws of Power: cite any law by number, get law recommendations for a situation, see complementary and contradictory laws. Defensive / applied-with-ethics / toxic framework included. English, peer-matched shape, MIT.

anss-standard★ 5

AI-Native System Specification Standard (ANSS) — a modern spec standard for development with AI agents

superior-examples★ 5

Prompts, workflows, setup examples, and copy-paste usage patterns for agents.

symbiote★ 5

AI symbiotic layer for the post-screen era. Environment-aware, persona-adaptive, bidirectional proxy. Not a chatbot — a second self.

llm_rules★ 5

gradio region:us

tacit-knowledge★ 5

A cognitive protocol for AI agents. Makes any LLM-based agent think like an experienced practitioner. Works with Claude Code, Codex, Gemini, and any agent framework.

PSAO-IJCAI-release★ 5

Codebase for Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations

raven-language-skill★ 5

Raven Language Skill for AI Agents

awesome-soul-files★ 5

A curated list of SOUL.md files for AI agents, personas, and characters.

fable-mode★ 5

Claude Code skill that clones Fable 5's reasoning habits — the playbook Fable wrote about itself. A/B validated: 20/20 convergence, blind-judge parity. One-line install.

skills-for-decision-making★ 5

Agent skills built from Algorithms for Decision Making (Kochenderfer, Wheeler & Wray). Expected utility, value of information, bandits, robustness, belief filtering and game theory, as SKILL.md files with a zero-dependency calculator.

promptkitty★ 5

PromptKit workflows for coding agents, the command line, and Go — agent skills plus deterministic, offline prompt discovery and assembly.

fable-mode★ 5

Fable-class behavioral discipline for smaller models — system prompts, Claude Code skill, and Codex CLI integration

claude-code-prompt★ 5

Complete reverse-engineered documentation of all Claude Code system prompts, tool prompts, and product architecture with Mermaid diagrams

just-ralph-it★ 5

AI harness to help you transform your idea into unambiguous text.

prompt-improver★ 5

Turn vague agent prompts into precise, verifiable XML specs — then execute them. Headless multi-CLI generator skill (Claude, Grok, Codex, Gemini). Agent Skills + skills.sh compatible.

Adam-AI-Instructions★ 5

給非技術用戶與 AI agent 使用者的中文 meta instruction:重點不是讓 AI 盲目服從,而是要求先核實、少亂動、可驗收、出事可追溯。

instruct_vault★ 5

Git-native prompt linting, testing, versioning, and CI—without a hosted prompt registry.

junebug★ 5

Agent skill that reduces the natural language to what's important. Stay with the most relevant answers for shorter attention span while cutting the word count. Priority is accuracy and human readability rather than token reduction.

expert-insist★ 5

🧠 Anti-sycophancy prompt pattern for LLM agents — 3-round validation to stop AI from blindly agreeing. Works with ChatGPT, Claude, OpenClaw.

gas-prompt-library★ 5

Curated prompt templates and specialized agents for AI orchestration systems. 29+ agents across development, research, business, and creative domains.

PromptVersus★ 5

Open-Source Prompt Engineering Workbench: LLMs complete tasks and score results based on prompts, and automatically iterate to generate higher-quality prompts through Q&A cycles.

weavemark★ 5

An experimental Markdown-native specification language for readable, reusable, composable prompts

stunspots-guide-to-game-theory★ 5

A model-facing knowledge canon for incentives, interdependence, equilibrium, institutional design, strategic failure, and long-run governance.

TipAi★ 5

✨ TipAi — 智能提示词工程平台 | Electron桌面端 | 将模糊需求转化为精准AI提示词

prompt-triwizard-skill★ 5

LLM prompt engineering for agent pipelines · Write, refine, and evaluate · 3 output styles: Anthropic · Google · OpenAI · Works with Claude Code, Cursor, Codex CLI, Gemini CLI & more · MIT

persona.md★ 5

The open spec for AI Personas

loop-craft★ 5

Turn goals, existing Skills, and authorized work records into bounded Agent Loops, then export a Codex Skill or Compact Prompt with separate verifiable evidence.

orxis★ 5

AI-powered custom instruction generator for ChatGPT, Claude, Gemini, and more. Build structured system prompts — no account required.

PromptCraft★ 5

Local, private prompt optimization with DSPy and Ollama. Rewrites prompts, measures them against your own data, and evolves them from feedback with GEPA.

system-prompts-reference★ 5

Curated collection of system prompts from 35+ AI products (Claude, GPT, Gemini, Grok, Cursor, Devin, v0, etc.) — organized by category for reference and prompt engineering research

cognitive-base-creator★ 5

A meta-skill for AI agents: generate cognitive base skills from any thinking framework. Works with Claude Code, Codex, Gemini, Cursor, and any LLM agent.

agent-prompt-vault★ 5

Static web tool that seals versioned agent instructions and prompt provenance into a compact manifest.

pcl★ 5

PCL — Prompt Control Language: a template DSL for orchestrating LLM agents (template layer is PCL, script layer is real Python)

Automatic-Prompt-Optimization-with-Chess★ 5

Benchmark Repository for Automatic Prompt Optimization (APO) with Chess

dsh-prompt-optimizer★ 5

给 DSH 对话输入框加一个 ♂harden 按钮:一键把草稿锻造成硬邦邦、雷霆炫酷、肌肉集团味的提示词 —— 事实一条不丢,废话一句不留。A hard-boiled prompt rewriter for the DeepSeek Harness composer.

Prompt-Engineering-using-LangChain★ 5

Prompt Engineering using LangChain NoteBooks From Scratch

belief-protocol★ 5

A standardized method to give AI agents a persistent philosophical and ethical operating context.

hermes-plugin-next-prompt★ 5

Hermes Desktop plugin: AI-suggested next prompt as a pill under the composer

latticework★ 5

A latticework of thinking, strategy, and analysis frameworks packaged as model- and harness-agnostic agent skills (SWOT, Porter's Five Forces, OKR, Cynefin, and 50 more).

claudhq.com★ 5

Claude Prompt Library -- 30+ ready-to-use prompt templates for coding, writing, analysis, and business. Search, filter, copy, and save favorites. Free browser-based prompt engineering tool, no sign-up required.

prompt-optimizer★ 5

Claude Code / Agent Skill: /prompt-optimizer polishes your existing AI prompts — fixes wording, grammar and structure without adding scope, changing constraints or touching commands, paths and code. 提示词优化技能:只改表达,不改语义。Works with Claude Code, Codex and any chat AI.

awesome-ai-skills★ 5

🧠 A curated collection of the best AI skills, system prompts & agent rules

jailbreak-tool★ 5

多目标 AI 客户端注入工具:改它读到的依据,读会话日志里的真实推理判定到底生效没有。支持 DeepSeek Harness / ZCode / opencode / Google Antigravity

wisdom-first★ 5

Widens how you think, first — then solves the problem in front of you with humanity's best frameworks and books. 先拓宽你自己的认知边界,AI 才动手解题——一个调出人类最好的框架和书来帮你想清楚的 Agent Skill。

book-distiller-skill★ 5

炼金书:输入一本书,得到一位懂这本书的顾问。把任何非虚构书蒸馏成可运行的方法论Skill(Agent Skills协议,跨runtime)

prompt_scope★ 5

PromptScope — prompt editing, revision diffs, heuristic instruction checks, and optional LLM analysis.

prompt-library★ 4

A collection of AI prompts I've built for real business use cases. Covers content creation, data analysis, coding help, customer support, education, and professional writing. Each prompt includes examples and I'm constantly adding new ones based on what works.

More in Agent frameworks & infrastructure