Trending repositories: prompt-engineering

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

Filter by topic

55 of 55 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.

    275,996developer-toolsShellMIT
  • 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: A collection of curated AI prompts and configurations modeled after Andrej Karpathy's specific workflows and techniques.

    216,846ai-ml
  • 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: The world's largest open-source prompt library for interacting with Large Language Models.

    172,019productivityHTMLOther
  • 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: An AI agent skill that enforces minimal, safe, and dependency-free one-liner code generation.

    154,616developer-toolsJavaScriptMIT
  • 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 collection of leaked or reverse-engineered system prompts and model details from popular AI tools.

    144,018ai-mlGPL-3.0
  • 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.

    132,998webPythonMIT
  • microsoft/generative-ai-for-beginners

    21 Lessons, Get Started Building with Generative AI

    AI summary: A comprehensive 21-lesson course teaching the fundamentals of building Generative AI applications.

    120,998learningJupyter NotebookMIT
  • JuliusBrussee/caveman

    🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

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

    109,775ai-mlGoApache-2.0
  • Leonxlnx/taste-skill

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

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

    92,557developer-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.

    74,282ai-mlPythonApache-2.0
  • asgeirtj/system_prompts_leaks

    Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.

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

    68,725securityJavaScriptCC0-1.0
  • 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.

    67,019learningHTMLMIT
  • 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.

    53,375productivityPythonMIT
  • 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.

    53,179learningJupyter 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: An archive of extracted system prompts exposing the hidden directives governing major commercial AI models.

    50,845learningAGPL-3.0
  • 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.

    50,291productivityPythonOther
  • sickn33/agentic-awesome-skills

    AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

    AI summary: A curated collection of actionable skills, prompts, and workflows for maximizing the utility of AI agents.

    47,213productivityPythonMIT
  • 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.

    35,186developer-toolsMIT
  • 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.

    33,860ai-mlJavaScriptMIT
  • 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.

    33,028developer-toolsTypeScriptMIT
  • alirezarezvani/claude-skills

    380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ 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.

    27,577developer-toolsPythonMIT
  • 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: Principles for building production-ready, reliable LLM-powered software and AI agents.

    26,530architectureTypeScriptOther
  • JimLiu/baoyu-skills

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

    26,321productivityTypeScriptMIT
  • 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.

    26,077productivityPythonApache-2.0
  • 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.

    25,662developer-toolsTypeScriptMIT
  • 2025Emma/vibe-coding-cn

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

    23,017learningPythonMIT
  • 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.

    21,130developer-toolsPythonMIT
  • 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.

    AI summary: An aggressive productivity skill that forces AI agents to strictly adhere to goals by simulating a high-pressure performance review.

    19,710developer-toolsPython
  • EvoLinkAI/awesome-gpt-image-2-API-and-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.

    17,276ai-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 automatically analyzes intent and generates highly optimized, framework-specific prompts for any AI tool.

    13,986productivityMIT
  • MiniMax-AI/skills

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

    13,668ai-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 specifically optimized for Google's Nano Banana Pro image model.

    13,535learningTypeScriptOther
  • petergyang/no-ai-slop

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

    AI summary: A prompt tuning tool that removes generic AI writing patterns to preserve authentic personal voice.

    11,744productivityPythonMIT
  • 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: A CLI framework for designing, orchestrating, and auditing autonomous AI agent loops across large codebases.

    11,416ai-mlTypeScriptMIT
  • 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: A framework for distilling valuable content from books, videos, and podcasts into executable AI Agent Skills.

    10,847productivityPythonMIT
  • alchaincyf/zhangxuefeng-skill

    张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。

    AI summary: An AI persona framework that mimics Zhang Xuefeng's cognitive models for pragmatic career and education planning.

    10,384ai-mlMIT
  • YouMind-OpenLab/awesome-gpt-image-2

    🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image consistency, and commercial-grade illustration. Free & open source.

    AI summary: A curated, open-source library of over 2000 prompts optimized for OpenAI's GPT Image 2 model.

    9,999ai-mlTypeScriptOther
  • 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.

    9,136securityPythonMIT
  • EvoMap/evolver

    The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

    AI summary: An advanced self-evolving engine that uses Gene Expression Programming to autonomously improve AI agent skills.

    9,127ai-mlJavaScriptGPL-3.0
  • Emily2040/seedance-2.0

    Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0

    AI summary: A comprehensive production pipeline for quad-modal AI filmmaking that analyzes scenes before generating prompts for Seedance 2.0.

    7,510ai-mlPythonMIT