Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 151
Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.
1,5/gün ort. +1 son gün — commit Python 12 Ağu 2026 güncellendi 23 Ağu 2026 - 152
Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development
0,7/gün ort. +0 son gün — commit Shell 21 Nis 2026 güncellendi 26 Tem 2026 - 153
Goal-based planning and proof gate for AI coding agents
0,8/gün ort. -1 son gün — commit Shell 30 May 2026 güncellendi 24 Tem 2026 - 154
OpenCode skill suite for MiniMax H3 directing, routing, multishot planning, prompt generation, and review.
1,5/gün ort. +0 son gün — commit PowerShell 09 Ağu 2026 güncellendi 09 Ağu 2026 - 155
Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком
1,3/gün ort. +0 son gün — commit Python 30 Tem 2026 güncellendi 5 gün önce - 156
Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR)
1/gün ort. +0 son gün — commit Python 02 Tem 2026 güncellendi 28 gün önce - 157
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden
0,9/gün ort. -9 son gün — commit Python 15 Haz 2026 güncellendi 22 Eyl 2026 - 158
Best Prompt Engineering Tools for 2026 AI Workflow Optimization
1/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 159
让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them
0,8/gün ort. +0 son gün — commit 28 May 2026 güncellendi 25 Haz 2026 - 160
东方文化编辑海报 v2 Codex skill:Image 2 出图、中文标题精炼、真实文化物证、A/B/C 三联测试
1,1/gün ort. +0 son gün — commit 14 Tem 2026 güncellendi 06 Eyl 2026 - 161
Turn vague product or feature ideas into clear, checkable requirements before planning or coding—mapping rough descriptions to professional
1,6/gün ort. +0 son gün — commit Python 21 Ağu 2026 güncellendi dün - 162
DeepSeek-Harness (DSH) 插件:✨ 提示词一键增强(5 模式·模型链·记忆链)+ 💬 语音输入增强(热键·说完自动停·口水词清理·语音纠错)
1,4/gün ort. +1 son gün — commit JavaScript 13 Ağu 2026 güncellendi 2 gün önce - 163
Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control
0,9/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 164
Top 10 Claude Prompt Optimization Frameworks 2026
0,9/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 165
Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Cod
0,5/gün ort. +0 son gün — commit Vue 24 Mar 2026 güncellendi 4 gün önce - 166
Universal AI Agent Swarm & MCP Plugin with 178 specialized skills and 8 autonomous subagents for Antigravity, Claude Code, Cursor, Windsurf,
0,7/gün ort. +2 son gün — commit JavaScript 21 May 2026 güncellendi dün - 167
Production-Stage Visual Design & In-Codebase UI Engineering Suite
1,5/gün ort. +0 son gün — commit Python 18 Ağu 2026 güncellendi 14 gün önce - 168
🔍 Reverse engineer any codebase into a build prompt — architecture breakdown, ASCII blueprint, and AI-ready reconstruction prompt
0,9/gün ort. +0 son gün — commit TypeScript 25 Haz 2026 güncellendi 25 Haz 2026 - 169
Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.
0,7/gün ort. +0 son gün — commit Python 28 May 2026 güncellendi 29 Ağu 2026 - 170
✨ Stunning glassmorphism UI for Stable Diffusion and Anima prompt engineering. Intelligent conflict-free composition, live preview, NSFW saf
0,7/gün ort. +0 son gün — commit HTML 22 May 2026 güncellendi 16 Tem 2026 - 171
🐴 Prompt-first harness engineering for safer AI coding agent workflows.
0,7/gün ort. +0 son gün — commit Python 26 May 2026 güncellendi 18 Haz 2026 - 172
HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code
0,9/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 173
Claude Code skill & open-source wisdom companion (v6.6.0, Apache 2.0) for CLI, IDE, and web chat. One lens per turn, local SQLite vault, 350
0,5/gün ort. +0 son gün — commit Python 28 Mar 2026 güncellendi 5 gün önce - 174
An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly
0,7/gün ort. +0 son gün — commit HTML 27 May 2026 güncellendi 25 Ağu 2026 - 175
Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components
0,5/gün ort. +0 son gün — commit JavaScript 18 Mar 2026 güncellendi 9 gün önce - 176
An AI roleplay chat platform with the most advanced prompting system
0,8/gün ort. +0 son gün — commit 16 Haz 2026 güncellendi 8 gün önce - 177
CLAUDE.md / AGENTS.md 规则模板:放进项目根目录,让 Claude Code、Codex、Cursor 少返工(附前后对比)|Drop-in rules for AI coding agents
0,8/gün ort. +0 son gün — commit 25 Haz 2026 güncellendi 9 gün önce - 178
19 套可直接生图的视觉风格 Skills,为 gpt-image-2 编写。把文章、主题、产品或已有视觉资产编译成完整提示词。/ 19 visual-style prompt skills for gpt-image-2.
0,8/gün ort. +0 son gün — commit 18 Haz 2026 güncellendi 15 Ağu 2026 - 179
中文 AI 图片提示词库,覆盖女装、童装、电商主图、产品摄影、小红书封面和广告海报。
0,6/gün ort. +0 son gün — commit 15 May 2026 güncellendi 16 Tem 2026 - 180
Generate project-based guidance and interview Q&A docs with STAR speaking scripts. 基于真实项目生成导学与面经(含第一人称 STAR 法则口播答案)
0,6/gün ort. +0 son gün — commit Python 21 Nis 2026 güncellendi 2 gün önce - 181
Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explici
0,6/gün ort. +0 son gün — commit JavaScript 25 Nis 2026 güncellendi 13 Tem 2026 - 182
⚡ Unit tests for AI. Test prompts, compare models, save money.
0,5/gün ort. +0 son gün — commit Python 11 Nis 2026 güncellendi 22 May 2026 - 183
AI agent that turns your rough ideas into perfect image generation prompts. 7-component formula, 70+ creative techniques, 9 domain modes.
0,5/gün ort. +0 son gün — commit Python 25 Mar 2026 güncellendi 13 gün önce - 184
You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.
0,5/gün ort. +0 son gün — commit Python 16 Mar 2026 güncellendi 16 gün önce - 185
让 AI 像人一样说话、创作的规则集。Ruleset for making AI talk and write like a human.
1,2/gün ort. +2 son gün — commit Python 12 Ağu 2026 güncellendi 3 gün önce - 186
Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce
0,9/gün ort. +0 son gün — commit Python 06 Tem 2026 güncellendi 15 Tem 2026 - 187
把模糊视觉需求直接变成可落地生成的高质量设计图
0,5/gün ort. +0 son gün — commit Python 18 Nis 2026 güncellendi 20 Nis 2026 - 188
AI Agent 面试知识库:覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。
0,7/gün ort. +0 son gün — commit CSS 01 Haz 2026 güncellendi 09 Ağu 2026 - 189
Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal
0,9/gün ort. +0 son gün — commit Rust 14 Tem 2026 güncellendi 2 gün önce - 190
Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an
1,2/gün ort. +0 son gün — commit Python 13 Ağu 2026 güncellendi 26 Ağu 2026 - 191
Rational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and re
0,7/gün ort. +1 son gün — commit 23 Haz 2026 güncellendi 14 Eyl 2026 - 192
Study materials, code examples, and practice scenarios for Anthropic's Claude Certified Architect: Foundations (CCA-F) certification exam. C
0,4/gün ort. +0 son gün — commit Jupyter Notebook 16 Mar 2026 güncellendi 19 Eyl 2026 - 193
The most frequently used agent skills of Wade Foster, CEO of Zapier
0,9/gün ort. +0 son gün — commit 17 Tem 2026 güncellendi 21 Tem 2026 - 194
中文网文写作工具包 · Chinese web-novel writing toolkit (23 skills) — a Claude Code plugin, also works in ChatGPT / DeepSeek / Gemini
0,6/gün ort. +0 son gün — commit Python 05 Haz 2026 güncellendi 2 gün önce - 195
Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.
1,2/gün ort. +0 son gün — commit Batchfile 18 Ağu 2026 güncellendi 09 Eyl 2026 - 196
Route-first FPV AI video prompting skill for Seedance, Kling, Runway, Veo, GPT Image asset packs, numbered stops, and red-line path control.
0,6/gün ort. +0 son gün — commit 09 Haz 2026 güncellendi 10 Haz 2026 - 197
Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideat
0,6/gün ort. +0 son gün — commit Shell 09 Haz 2026 güncellendi 04 Ağu 2026 - 198
A muted, poetic paper-poster Agent Skill for low-saturation zine-style image generation.
0,8/gün ort. +0 son gün — commit 22 Tem 2026 güncellendi 22 Tem 2026 - 199
58 个跨境电商 · DTC 品牌出海 AI 技能库:Amazon 运营、SEO/GEO、广告归因、财务、联盟、红人、线下零售、VOC、众筹。事实均标来源与日期,内置证据闸——数据不足时说「数据不足」,而不是编一个数字。| 58 skills for cross-border e
0,4/gün ort. +1 son gün — commit Python 07 Nis 2026 güncellendi 01 Ağu 2026 - 200
SkillForge — AI Agent Skills Generator. A structured 4-step prompt system that forges production-grade Agent Skills from scratch.
0,4/gün ort. +0 son gün — commit TypeScript 10 Mar 2026 güncellendi 16 Tem 2026