#prompt-engineering Repositories
554 repositories total
Transform vague ideas into production-ready prompts. Analyze gaps, generate PRDs, and supercharge your AI coding workflow with the CLEAR framework.
Unified Go interface for Language Model (LLM) providers. Simplifies LLM integration with flexible prompt management and common task functions.
AI agent skills for social media content strategy, creation, and analysis across text-first platforms
๐ฅ Visual AI research assistant that displays real-time thinking, provides split-view analysis, and automatic citations using Claude and Firecrawl
Cline Chinese localized version, Cline is an autonomous programming assistant that runs in your IDE and can create/edit files, run commands, use the browser, and other functions with your permission.
The first AI cybersecurity toolkit independently developed by DeepSeek
RAT is a powerful tool that improves AI responses by leveraging DeepSeek's reasoning capabilities to guide other models through a structured thinking process.
A curated collection of research papers exploring the utilization of LLMs for graph-related tasks.
Copy AI conversations as clean Markdown Context Bundles โ one click from ChatGPT, Claude, Gemini, DeepSeek, Grok & GitHub. Copy from sidebar without opening. Zero upload, 100% local, open source.
EMNLP'22 | MedCLIP: Contrastive Learning from Unpaired Medical Images and Texts
Turn stateless LLMs into a stateful, compounding AI agent. Local-first persistent memory, quantitative decision screens, and governance harness across Claude Code, Antigravity, Cursor, and VS Code. Own the state. Rent the intelligence.
A sd-webui extension for utilizing DanTagGen to "upsample prompts".
By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics, clean-code habits, a verify-and-iterate loop, a checkup for the mess). For Claude Code, Codex, and Antigravity. grill-me is for engineers, vibe-check is for everyone else.
Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.
We collect papers about "large language models (LLM) for table-related tasks", e.g., using LLM for Table QA task. โTable + LLMโ related papers compilation
๐ฌ Short-Drama Factory v4.9.1 ยท Industrial-scale hit short-drama writing super-system for Douyin/Hongguo | One idea/one web novel โ standard 60โ100 episodes ยท long-format 30โ50 episodes ยท paywalled comic-drama scripts | v4.9 vivid visual storytelling + 15-second gear shifts + plainspoken directness + peel-the-layers imitation writing | Full map of 40 genres + six archetypal hooks + five major cliffhanger cuts + rotating AโI reversals | Emotion-contract unit chain ยท closed-loop resolution for a single conflict in โค30 episodes | Dynamic, on-demand matrix mounting (8 interaction modes to prevent Context overload) | Automated checks E1โE26 + S1โS8 | Screenplay layer only ยท Industrial hit short-drama screenplay engine (60โ100 eps, paywall built in)
Coco Super Intelligence: agent skills, slash commands, and subagents for Claude Code, Cursor, and Codex. One command installs them in the tool you already use.
Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models.
Threat modeling for AI coding agents: point Claude Code, Codex, or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
GPT Image 2 to Seedance 2.5 Early Access workflow guide.
An experimental project demonstrating Infinite Agentic Loop in a two prompt system using Claude Code.
AI writing skill that eliminates detectable AI patterns. Works with Claude Code, Codex, Cursor, Gemini CLI, and 8+ other agents.
๐ด VERY LARGE AI TOOL LIST! ๐ด Curated list of AI Tools - Updated 2026
Codex skill for turning everyday photos into poetic white-paper hand-drawn illustrations.
The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.
Taishang Laojunโs AI Alchemy Furnace: a short-video creation skill for Douyin and Xiaohongshu. Donโt know what to film or how to write a script? Hand it to your AI: find successful accounts to benchmark, break down viral videos, choose topics, plan series, write talking-head scripts and titles, review performance, and make the content sound less AI-generated. Install in one line with npx for Claude Code, Codex, and more; use the Bot version with chat-based AI agents like Doubao.
Workflow fluency for AI coding agents. 1 core skill ยท 25 commands ยท 7 domain references ยท memory layer ยท audit trail โ works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
โจ A curated list of awesome GitHub instructions, prompt, skills, MCPs and agent markdown files for enhancing your GitHub Copilot AI experience.
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
An all-in-one metaphysics, fortune-telling, and divination toolkit for BaZi, Zi Wei Dou Shu, astrology charts, Liu Yao, Plum Blossom Numerology, Qi Men Dun Jia, Da Liu Ren, Xiao Liu Ren, tarot, Lenormand, spiritual lots, and date selection. Outputs structured prompts and data. Provides a public API, MCP Server, and skill.
Open-source SEO & GEO audit: a zero-dependency CLI (npx), an agent skill for Claude Code, Cursor, Codex, Gemini & Copilot, 47 SEO prompts and a cited Google/Bing/AI-search knowledge base. Checks robots.txt, sitemaps, canonicals, hreflang, structured data, Core Web Vitals and AI crawlers โ then fixes them.
GPT Image 2.5 prompts, verbatim and credited: 150 community prompts across 9 use cases, each with the author who wrote it and their post. Free to run.