#prompt
GitHub repositories that have self-applied the topic "prompt" — a creator-tagged metadata that surfaces how AI projects describe themselves.
REPOS Repos for #prompt (top 14 by stars)
你只管憋屈,回消息的事交给它。潜台词翻译 + 三档回复(体面/绵里藏针/掀桌)+ 蒸馏你自己的说话风格 —— Agent Skill,适配 Claude Code / Codex / Cursor 等 runtime。
cubrift/quartAn autonomous AI chatbot built for WhatsApp using Node.js, Baileys, and the Vercel AI SDK powered by OpenAI. Designed to act like an active, context-aware participant in group chats and direct messages, Quart goes far beyond traditional command-and-response bots by actively listening and engaging in human conversations.
soycodetrail/ai-skills-workshopAI 技能工坊 · 精选 Agent Skill 合集(绘图/写作/视频)——同步自 soycodetrail.top/skills
donmathew158-sys/superprompt-aiSuperPrompt AI – Transform raw ideas into perfectly optimized prompts for ChatGPT, Claude, Gemini, and 5+ other AIs. Guided interview or instant mode. Built with Streamlit + Groq.
Ultra119/ai-metadata-inspectorMetadata Inspector - PNGs from ComfyUI or other tools
quiescencycommonrush642/goal-prompt-builderBuild precise goal prompts for Claude CLI agents using a five-section template to ensure audit-friendly execution and efficient token usage.
jaypkallega/open-ai-hubA community-driven library of prompts, skills, and .md files for LLMs and AI. Free for all
alaala-daka/2026_OpenAI_Prompting_best_practices_zh2026OpenAI官方提示词最佳实践简体中文翻译
ZOORO-NEW/qianjin-skill-storeQianjin Skill Store - curated index of 19 ZOORO-NEW open-source AI agent skills with install guides. 技能商店总入口.
boscochuck6812/shall-we-talk「Shall We Talk? · 我们聊聊吧?」开源 AI 技能:分析聊天记录判断感情状态,定制摊牌话术与模拟演习。An open-source AI skill for the what-are-we talk, works with any AI.
dehuamading/help-me-understand-skill《帮我看懂》AI 技能个人备份(help-me-understand)— 来源:得到 AI 学习圈
QiDouZu/retcon-form让 AI 的结论可回查、可推翻:每条判断写成「进行时」+原文指针,按段取原文不整包读(省 token、省上下文)。零依赖,17 场景沙盘可跑。
edwinkyc/projectrosabel_dsv4proProject Rosabel is a production grade system instruction set for clinician facing AI, designed for deployment with DeepSeek-V4-Pro. It enforces medication safety, epistemic honesty, provenance, and escalation, with halt conditions for high risk therapies and a final quality gate.
Nesarf/Oishikunaare-Moe-Moe-KyunOutput house rules for every DeepSeek Harness agent: no check-mark or cross glyphs in replies or written files, and a light kaomoji habit in conversation. One global prompt section, so every preset, workspace and subagent obeys without a single preset edit.
RELATED Other topics · full topics ranking →
#claude-code
2,978#ai-agents
2,315#llm
1,760#claude
1,531#mcp
1,447#python
1,409#developer-tools
1,287#codex
1,070#ai
1,067Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology