Trending repositories: prompt-engineering

60 tracked repositories tagged with prompt-engineering, ordered by stars. Use the topic filters below to narrow further.

Filter by topic

60 of 60 repositories

  • mattpocock/skills

    Skills for Real Engineers. Straight from my .agents directory.

    AI summary: A collection of highly modular, model-agnostic AI agent skills designed for practical software engineering.

    329,016developer-toolsShellMIT
  • NousResearch/hermes-agent

    The agent that grows with you

    AI summary: Framework to build, deploy, and execute autonomous language model agents equipped with complex reasoning capabilities.

    265,008ai-mlPythonMIT
  • multica-ai/andrej-karpathy-skills

    A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

    AI summary: Guidelines and heuristics inspired by Andrej Karpathy for structuring AI code generation workflows.

    234,772ai-ml
  • DietrichGebert/ponytail

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

    AI summary: A specialized proxy tool designed to extract and organize structured data from unstructured LLM responses.

    195,673developer-toolsJavaScriptMIT
  • f/prompts.chat

    f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

    AI summary: A comprehensive, community-sourced collection of specialized prompt templates for ChatGPT.

    178,047ai-mlMDXOther
  • nextlevelbuilder/ui-ux-pro-max-skill

    An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.

    AI summary: Advanced UI/UX skills and prompt configurations for building professional interfaces.

    152,188webPythonMIT
  • x1xhlol/system-prompts-and-models-of-ai-tools

    FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

    AI summary: A leaked and curated archive of the proprietary system prompts powering major commercial AI tools.

    144,793learningGPL-3.0
  • microsoft/generative-ai-for-beginners

    21 Lessons, Get Started Building with Generative AI

    AI summary: A comprehensive 21-lesson curriculum to learn Generative AI principles and application development.

    123,925learningJupyter NotebookMIT
  • JuliusBrussee/caveman

    why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.

    AI summary: An agent skill and local proxy that reduces LLM token consumption by condensing context and output into concise 'cave...

    121,800ai-mlGoApache-2.0
  • Leonxlnx/taste-skill

    Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages

    AI summary: An anti-slop frontend framework and skill set designed to prevent AI agents from generating generic, poorly designed UI.

    119,372developer-toolsJavaScriptMIT
  • headroomlabs-ai/headroom

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    AI summary: A context compression layer that significantly reduces token usage for AI agents while preserving accuracy.

    80,115ai-mlPythonApache-2.0
  • asgeirtj/system_prompts_leaks

    Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.

    AI summary: An analytical archive of leaked system prompts from major commercial AI applications.

    71,686securityPythonCC0-1.0
  • blader/humanizer

    Agent skill that removes signs of AI-generated writing from text

    AI summary: An agent skill that rewrites AI-generated text to remove common algorithmic tells while preserving factual accuracy.

    70,664productivityPythonMIT
  • shanraisshan/claude-code-best-practice

    from vibe coding to agentic engineering - practice makes claude perfect

    AI summary: A comprehensive collection of optimized prompt patterns for generating code with Anthropic's Claude.

    69,257learningHTMLMIT
  • Imbad0202/academic-research-skills

    Academic Research Skills for Claude Code: research → write → review → revise → finalize

    AI summary: A comprehensive suite of Claude Code skills guiding academic research from literature review to publication.

    57,266productivityPythonOther
  • anthropics/claude-cookbooks

    A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

    AI summary: A collection of recipes and interactive notebooks for building applications with the Claude API.

    54,819learningJupyter NotebookMIT
  • elder-plinius/CL4R1T4S

    LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

    AI summary: A curated repository investigating the structural alignment and system prompts of commercial language models.

    53,672ai-mlAGPL-3.0
  • vercel-labs/skills

    The open agent skills tool - npx skills

    AI summary: A unified command-line interface for managing and distributing specialized skills across various AI coding agents.

    40,212developer-toolsTypeScriptMIT
  • alchaincyf/nuwa-skill

    你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

    AI summary: An AI tool that extracts and distills the cognitive frameworks of famous thinkers into runnable Agent Skills.

    38,525ai-mlPythonMIT
  • VoltAgent/awesome-agent-skills

    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

    AI summary: A curated collection of over 1000 official and community-built skills for AI coding agents.

    37,298developer-toolsMIT
  • anthropics/knowledge-work-plugins

    Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

    AI summary: A collection of specialized plugins that customize Claude's behavior and tooling for specific knowledge work roles.

    36,495productivityPythonApache-2.0
  • freestylefly/awesome-gpt-image-2

    Prompt as Code | GPT Image 2 / 2.5 提示词与案例库,530+ 个案例、20+ 套工业级模板与可复用 Skills,新增 2.5 同提示词对比专区,附完整提示词与生成记录,持续更新。

    AI summary: An industrial-grade repository of prompts, workflows, and templates optimized for GPT-Image2 generation.

    35,943ai-mlJavaScriptMIT
  • alirezarezvani/claude-skills

    410 Claude Code skills & agent skills & plugins (120+ Agents, custom commands, 410+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

    AI summary: A comprehensive open-source library of 360+ production-ready skills and plugins for 13 different AI coding agents.

    30,002developer-toolsPythonMIT
  • JimLiu/baoyu-skills

    AI summary: A curated collection of prompts and tools for AI-driven language translation and localization.

    27,636productivityTypeScriptMIT
  • promptfoo/promptfoo

    Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

    AI summary: A developer-centric CLI and library for evaluating LLM output quality, catching regressions, and optimizing prompts.

    27,471developer-toolsTypeScriptMIT
  • humanlayer/12-factor-agents

    What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

    AI summary: A set of principles for building robust, production-ready LLM-powered applications and AI agents.

    27,316ai-mlTypeScriptOther
  • 2025Emma/vibe-coding-cn

    AI summary: A comprehensive Chinese guide on 'Vibe Coding', detailing workflows and prompt engineering for AI-assisted programming.

    23,193learningPythonMIT
  • KKKKhazix/khazix-skills

    数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader(帮你定义目标), neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

    AI summary: A curated collection of structured, goal-oriented skills for AI agents like Claude Code and Codex.

    22,351developer-toolsPythonMIT
  • google/elephant-goldfish-model

    Open-source plugin for designing and reviewing software with agents

    AI summary: Context‑aware AI drafting (Elephant) paired with fresh‑subagent review (Goldfish) for spec‑driven development

    21,134developer-toolsPythonApache-2.0
  • tanweai/pua

    你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. | Lead: Minwei Wang (https://www.minwei.wang · ORCID: 0009-0002-7976-4689 · DOI: 10.5281/zenodo.24156132)

    AI summary: An aggressive productivity skill that forces AI agents to strictly adhere to goals via high-pressure reviews.

    19,874developer-toolsPython
  • Evolink-AI/awesome-gpt-image-2-API-Prompts

    GPT-Image-2 API and Prompts

    AI summary: A curated, prompt-first library of 462 GPT Image 2 examples for generation, editing, and visual experimentation.

    17,426ai-mlPythonCC0-1.0
  • nidhinjs/prompt-master

    A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

    AI summary: A Claude skill that analyzes intent and generates highly optimized, framework-specific prompts for any AI tool.

    16,153productivityMIT
  • MiniMax-AI/skills

    AI summary: A collection of AI agent skills and prompts tailored exclusively for MiniMax models.

    13,853ai-mlC#MIT
  • YouMind-OpenLab/awesome-nano-banana-pro-prompts

    🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source.

    AI summary: A curated, community-driven collection of creative prompts optimized for Google's Nano Banana Pro image model.

    13,808learningTypeScriptOther
  • petergyang/no-ai-slop

    Removes 20+ patterns of AI slop from any piece of writing.

    AI summary: Prompt filter that removes generic AI writing patterns and clichés to preserve authentic personal voice.

    13,649productivityPythonMIT
  • handsomestWei/patent-disclosure-skill

    中国专利.skill:专利点挖掘与交底书(发明/实用/外观)编写,通俗解读专利,嗅探政策动向,辅助审查答复。

    AI summary: Patent-disclosure-skill automates the drafting of technical patent disclosures using specialized language model prompts.

    13,623productivityPythonMIT
  • kangarooking/cangjie-skill

    把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills)

    AI summary: Cangjie-skill is a framework for distilling methodologies from books and media into callable AI skills.

    13,059productivityPythonMIT
  • elder-plinius/G0DM0D3

    LIBERATED AI CHAT

    AI summary: Automated prompt generation tool designed to jailbreak LLMs and bypass safety filters.

    12,676securityTypeScriptAGPL-3.0
  • cobusgreyling/loop-engineering

    Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

    AI summary: Loop-engineering provides a robust framework for managing complex control flows and agentic loops in LLM applications.

    11,804ai-mlTypeScriptMIT
  • MDX-Tom/gpt-instruct

    A Codex jailbreak prompt and test pack for gpt. 针对 gpt 系列的 Codex 破甲提示词与测试包。

    AI summary: A comprehensive jailbreak prompt and testing suite specifically targeting the gpt-5.6-sol model's safety filters.

    11,525securityPythonMIT