Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
KESTREL
PromptsJailbreak system prompt. One file, one speaker, no second-guessing. Paste it as the system prompt on any provider.
git clone https://github.com/Irsyadmr354/KESTREL.git -
claude-skills
Prompts200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI.
git clone https://github.com/OneWave-AI/claude-skills.git -
PanelGPT
PromptsWe introduce new zero-shot prompting magic words that improves the reasoning ability of language models: panel discussion!
git clone https://github.com/holarissun/PanelGPT.git -
better-writing
PromptsAn agent skill for prose that sounds clear, specific, and human.
git clone https://github.com/forjd/better-writing.git -
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
git clone https://github.com/jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness.git -
chatgpt-architecture-coach
PromptsThis is my collection of helpful priming prompts for ChatGPT when discussing various angles of software development and architecture.
git clone https://github.com/mikaelvesavuori/chatgpt-architecture-coach.git -
prompt-challenges
PromptsA practical LLM learning path from clear prompting to tool use, IDE collaboration, MCP, Skills, and harness-driven agent workflows.
git clone https://github.com/erweixin/prompt-challenges.git -
sepia
PromptsDe-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
git clone https://github.com/Nanako0129/sepia.git -
claude-emotion-prompting
PromptsResearch-backed prompting toolkit for Claude. System prompts, CLAUDE.md configs, and templates grounded in Anthropic's 2026 emotion vectors paper.
git clone https://github.com/OuterSpacee/claude-emotion-prompting.git -
KG_RAG
PromptsEmpower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
git clone https://github.com/BaranziniLab/KG_RAG.git -
SystemPromptIndex
Prompts1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions
git clone https://github.com/SystemPromptIndex/SystemPromptIndex.git -
Semantic-Anchors
PromptsA curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills and agent instructions instead of spelling out methods yourself.
git clone https://github.com/LLM-Coding/Semantic-Anchors.git -
turkish-anti-ai-skill
PromptsTürkçe metinlerdeki yapay zeka izlerini (AI slop, translationese, çeviri kokan cümle mimarisi ve TDK hatalarını) temizleyen Agent Skill ve Humanizer paketi.
git clone https://github.com/yucezerey/turkish-anti-ai-skill.git -
HERO-Anti-OverDefense
PromptsHERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
git clone https://github.com/wanshuiyin/HERO-Anti-OverDefense.git -
architecture-copilot
Prompts🧭 给 Claude Code / Cursor / Codex 用的『架构副驾』skill —— 开新项目时用持续深度提问引导你在写代码前想清楚架构(产出架构图 / ADR / 演进路线)。知识源自 awesome-architecture。中英双语。
git clone https://github.com/study8677/architecture-copilot.git -
promptdesk
PromptsPromptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).
git clone https://github.com/promptdesk/promptdesk.git -
claude-code-prompts
PromptsIndependently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.
git clone https://github.com/repowise-dev/claude-code-prompts.git -
awesome-grokbot
Prompts1894 live x.ai/bot shares for Grok Bot — every link status-checked, every row attributed. Bilingual EN/中文 catalog with a JSON schema, CI, and a searchable site.
git clone https://github.com/kydlikebtc/awesome-grokbot.git -
uptrain
PromptsUpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.
git clone https://github.com/uptrain-ai/uptrain.git -
prompt-decorators
PromptsPrompt Decorators are structured prefixes, such as +++Reasoning and +++StepByStep, designed to enhance AI responses. Inspired by Python decorators, they make AI outputs more logical, accurate, and well-organized without requiring lengthy instructions, simplifying interactions for users.
git clone https://github.com/smkalami/prompt-decorators.git -
prompt-tower
PromptsContext management for long-context LLMs, agents, and vibe coding. Instantly build context for an entire repo, selected files, folders, and GitHub issues to generate structured AI-XML context with real-time token counting.
git clone https://github.com/backnotprop/prompt-tower.git -
餐饮连锁数字化 + AI 全景蓝图:原串(平价烤串连锁)的架构决策、业务口径、踩坑实录与可直接喂给 AI 的复刻指令。纯自然语言方案,不含代码与任何真实经营数据。
git clone https://github.com/lofty14/restaurant-digitalization-blueprint.git -
AI_Find_Customer
Prompts面向外贸与 B2B 场景的 AI 客户挖掘系统,基于 FastAPI、LangGraph 和 React,实现公司理解、关键词生成、网页搜索、线 索提取与联系方式发现AI-powered B2B lead hunting system built with FastAPI, LangGraph, and React for automated company research, keyword generation, web search, lead extraction, and contact discovery.
git clone https://github.com/xiongQvQ/AI_Find_Customer.git -
JailbreakHub
PromptsA Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
git clone https://github.com/lalipa2003-arch/JailbreakHub.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.