Agent frameworks & infrastructure
Prompt engineering & prompt libraries
913 agents · most starred first
Prompt engineering & prompt libraries, page 7 of 10
Caret^ cuts repeated agent instructions down to compact notation. Across our sample set, prompt length was reduced by 95.8% by rewriting agent skill and persona files using Caret notation. This is for you if you ever draft or use Markdown files as agent skills or personas. If you design harnesses, it is a no brainer.
Edit AI chats with AI
useful utilities for prompt engineering (independent with @promplate)
Leverage large language models (LLMs) and LLM Agents to craft impactful and effective prompts
This project include the prompts to initalize a genral scientific project including: coding writing, code review, documentaiton and publication level summary and further checklist.
Meta-prompt system for agentic CLIs. Classifies your task, loads domain-specific best practices, and generates a tailored prompt that scaffolds the work — across code, data, writing, research, and more.
"Prompt Engineer"
PromptAI Application
Analyze your writing samples and generate AI style prompts that capture your unique voice, tone, and patterns. Works with local files or Google Drive.
PromptBoard is an open-source AI prompt management system that provides a streamlined interface for creating, organizing, and executing AI prompts. Built with Next.js and integrated with OpenAI models, and 1 click deploy to Vercel
ChatGPT Prompt Engineering for Developers
This collection includes jailbreak prompts utilized in different LLMs for research objectives. The outcomes of our study are detailed in the research paper named "RogueGPT: Unleashing Jailbreak Prompts on LLMs."
Prompt Engineering Tooling for OpenAI (chatgpt) or VertexAI (google cloud) APIs . With more APIs to follow
A practical guide to saving money and avoiding limits on Claude for developers and consumer users
an approach to optimizing large language model (LLM) responses by extracting, reranking, and refining their internal chain-of-thought (CoT). By focusing on the most coherent and relevant parts of the CoT, we can minimize contradictory reasoning and potentially reduce token usage—ultimately leading to more reliable and efficient outputs.
Give your OpenClaw agent a soul — not a prompt. YAML seeds → evolving AI personalities.
Complete step-by-step AI workflows for study, research, writing, business, and more — built for non-technical users. No coding required.
Complete reverse-engineered documentation of all Claude Code system prompts, tool prompts, and product architecture with Mermaid diagrams
Interactive browser-based wizard for generating OpenClaw agent soul configuration prompts (SOUL.md, AGENTS.md, IDENTITY.md, USER.md). Zero dependencies, bilingual UI, works offline. https://xhua.eu.org/openclaw-soul/
Offline prompt evolution engine for multi-agent systems, benchmark suites, and inspectable prompt DNA.
GPT4o, GPT4o-mini, and GPT4 Turbo jailbreak prompt for Research/IoC Development Purposes
✍️ Write effective AI prompts with this structured prompt engineering library and Claude Code skill, featuring 300+ curated examples for high-quality results.
gradio region:us
gradio region:us
10 copy-paste superprompts + 100 agent-ready goals for ChatGPT connectors (Gmail, Drive, Calendar), Claude Code, Codex, and MCP agents. Authored with Claude Fable 5, executed by GPT-5.5 xhigh or cheaper models. Includes LOOPS.md-inspired agent-loop templates.
Collection of 100+ battle-tested LLM prompts for coding, writing, and analysis. Works with GPT-4, Claude, Gemini. Copy-paste ready.
Multi-layer token optimization for LLM applications — compress prompts, map codebases, reduce output. Zero required dependencies.
基于 Flarum的AI提示词prompts,收集,分享AI提示词,让您的工作效率和创造力得以无上限的提升。
A team-wide prompting coach. Scores every prompt sent through Claude Code, Claude.ai, VS Code or Copilot Chat on 5 dimensions in real time, coaches the weak ones, and feeds the strong ones into a team wiki that gets injected back into the next person's context.
Cross-LLM skills for personal planning, research writing, mathematical review, and assistant development.
Provide and generate AI agent prompts with industry guides, glossaries, and multi-provider LLM support for scalable, automated content creation.
Personal engineering skill framework for agentic AI development(Inspired by Karpathy) — fork and adapt
A generative, visual builder for SillyTavern preset kits - modules, variables, regexes, automations. The LLM never writes the JSON.
Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API costs, and speeding up responses. It works with any agent or framework: Claude Code, OpenAI, LangChain, OpenCode, Cursor, and more.
Prompt Creator – A lightweight Python GUI tool that visualizes project structures and automatically copies code to the clipboard, streamlining the creation of prompt contexts for ChatGPT.
Feynman first-principles skills for research projects. For when you're prompting agents without really understanding your own assumptions.
📝 Discover and use powerful prompts for LLMs to enhance your AI interactions and boost productivity in coding and creative tasks.
Türkçe prompt grader for Claude Code · real-time scoring + token counter
Commands for Artificial Intelligence (AI) and LLM in a developer interface.
Rule-based evaluation protocols as portable AI skills: a credibility checker and an AI-writing review, with porting guides for Claude, ChatGPT, and Gemini.
A/B test your Claude prompts side by side — run one input through two variants at once, compare output, cost and latency.
Claude plugin that builds production-grade prompts using the 10-block framework from Anthropic's "Prompting 101" workshop. Interview-style.
A no-fluff system prompt for Codex and coding agents.
Optimize your prompts for better AI interactions.
一个用于学习和实践开发型 AI 提示词工程的项目,包含了 Kilo Code 的 6A 开发模式指南和相关配置。
Advanced token reduction and prompt optimization framework for LLMs, featuring linguistic, algorithmic, and architectural patterns.
A compact language for AI workflows. One symbol (@) separates AI logic from code. Includes an AI-readable spec and a pure-Python runtime (kzl)
The agentic specification framework. Domain-first specs that AI can consume directly.
closedNote is a Git-inspired version control system for AI workflows enabling branching, versioning, and reproducible prompt execution pipelines. Next.js · TypeScript · Supabase RLS · dual OCR pipeline · AI refinement.
AI instructions repository
Toolkit for creating and managing custom AI assistants, engineering prompts, and ensuring they perfectly fit your project needs.
Prompts extracted from Anthropic’s Claude Code CLI — organized and translated for research.
curl for prompts. Run .prompt files against any LLM (Anthropic, OpenAI, Ollama) from the terminal. Treat prompts as code — version them, review them in PRs, and test them in CI.
Open-source Claude prompt library for GEO and AEO. 19 prompts for AI search visibility — no setup, no API key.
PRISM v3.4: Progressive Retrieval-Optimised Information Structure Maker - A methodology for transforming monolithic system prompts into Claude Projects-optimised knowledge architectures
Retired August 2026. Scaffold for Opus 4.x-class agentic discipline; Claude 5 models no longer need it. Code kept for older models.
Escaping the Median Trap in LLM Ideation — Semantic Tabu, Solution Taxonomy, and Orthogonal Insight Protocol tested across 196 solutions (8 conditions)
朱雀 Suzaku — AI 生成品質模組。諂媚抑制、建設性挑戰、輸出適配、上下文錨定、一致性守護。基於 LDRIT 設計。
A CLAUDE.md persona that stops Claude from agreeing with everything. Korean/English auto-detect. MIT.
TONE – Token-Optimized Notation Engine for LLMs is a compact, human-readable data format designed for AI and LLM contexts. It encodes JSON-compatible structures using far fewer tokens typically 40-60% less making it ideal for AI assistants, RAG systems, and conversational data pipelines.
Prompt engineering workbench for web, browser, desktop, iPhone, and iPad
Ctx2Skill — 自主上下文技能发现忠实复现:arXiv:2604.27660v2
Building app in databutton using LangChainAI's Constitutional Chain
AI-driven prompt generation and evaluation system, designed to optimize the use of Language Models (LLMs) in various industries. The project consists of both frontend and backend components, facilitating prompt generation, automatic evaluation data generation, and prompt testing.
Templates and copilot commands to create, edit and refine project specifications.
18720+ .production-ready AI agent prompts, tool schemas, and framework configs. The "Tailwind UI" for AI Agents — organized by department, industry, and compliance standard. Copy-paste into CrewAI, LangGraph, AutoGen, or Vercel AI SDK.
🛠 Enhance LLM prompts effortlessly with RPI, a tool for testing, improving, and managing prompts across various AI providers.
☯️ Five-Phase Cognitive Flywheel — structured analysis framework for complex problems. Built by an AI agent, open-sourced for all agents.
gradio region:us
gradio region:us
A simple web service with @promplate. Best practise for prompt engineering applications.
AI-driven prompt generation and evaluation system, designed to optimize the use of Language Models (LLMs) in various industries. The project consists of both frontend and backend components, facilitating prompt generation, automatic evaluation data generation, and prompt testing.
通过对话生成 Prompt 链路 + 覆盖审计 + 模型推荐的 AI 开发蓝图生成器(Next.js + LangChain RAG + DeepSeek/OpenAI)
Drop-in alignment rules for any AI agent (Claude Code, Cursor, GitHub Copilot, OpenClaw, Hermes or a plain LLM system prompt): the eight constitutional clauses of Laukkonen et al. (2025) for four contemplative axioms, quoted verbatim, with an Iterated Prisoner's Dilemma benchmark to measure what a prompt changes.
LLM Token Optimization Toolkit — cut AI agent token cost 60–99%: Decision Distillation, SkillWeaver routing, Quant token playbook. Reduce LLM API bill.
173 prompt engineering techniques, local LLMs via Ollama — dual-model generation, PII anonymization, no cloud, no signup.
Multi-agent AI system using CrewAI and Flask that transforms rough ideas into production-ready LLM prompts through intelligent orchestration of specialized agents with local/cloud model support
Prompt Cloud Intent Compression
About AIプロンプトの効率的な管理と活用を目的としたリポジトリです。
A modular, extensible system for constructing optimized AI prompts with layered composition and generating code from natural language prompts.
A living library of AI workflows, Patterns, Claude Skills & Custom GPTs built by Studio Brittany.
🌱 智能提示词生成器 - 将想法转化为AI就绪的开发提示词 | AI Prompt Generator - Transform ideas into AI-ready development prompts
A modern desktop application for managing and organizing AI prompts with dynamic variable substitution. Built with Python and Flet.
Win系统剪贴板AI增强:面向 Windows 的剪贴板增强工具,支持历史、托盘、热键、Prompt 优化与图片基础操作。
Local-first Chrome extension: inject selected web content into ChatGPT with reusable prompt templates.
Open spec for logging AI coding prompts to a JSONL file in your repo. Vendor-neutral. JSON Schema published. plf-1.
llmpress reduces the token cost of sending source code to an LLM by detecting repeated patterns, replacing them with short aliases, and transparently restoring the originals in the model's response.
⚔️ Transform weak prompts into elite, production-ready prompts using NVIDIA Llama 3.1 70B. Built for Google Prompt Wars 2026. Features: 8 prompt engineering techniques, Power Level Meter (1-10), Warrior Rank System, typewriter animation. Powered by NVIDIA NIM API + Python Flask.
AI prompt management platform. Build, version, and share dynamic LLM prompts
streamlit region:us
streamlit region:us
Local-first Chrome extension: inject selected web content into ChatGPT with reusable prompt templates.
OpenAI Codex Skill and system prompt generator for AI agents: build six-part XML LLM prompts, then execute them immediately.
Unified Governance Console & Rule Ingestion Dashboard for LLM-driven Engineering Architectures
Ultimate AI Spellbook Workflows 2026 – Build Multi-Platform Skills & Automation
Automate AI agent behavior tuning with human feedback, test small mutations, and keep what improves performance over time
OpenClaw Agent Configuration Templates - Lightweight prompt engineering framework for AI agents
DeepSeek Harness 极简 PTC 预设插件:Python / TypeScript 工具编排、Windows Git Bash 适配与宿主约束保留。欢迎提交 issues 和 PR。
Structural prompt analysis + output testing + rewriting. Model-agnostic via LiteLLM. FastAPI service.