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…
- 401
Claude skill for behavioral interview prep — mine real experiences, structure them with STAR/CAR, and build a reusable bilingual story bank.
0,3/gün ort. +0 son gün — commit HTML 29 Haz 2026 güncellendi 28 Eyl 2026 - 402
Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses
0,6/gün ort. +0 son gün — commit Python 25 Ağu 2026 güncellendi 31 Ağu 2026 - 403
Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir
0,2/gün ort. +0 son gün — commit Elixir 20 Mar 2026 güncellendi 5 gün önce - 404
Transforme Claude Code en générateur autonome de knowledge vault Obsidian. Pattern Karpathy. Par LE LABO IA.
0,2/gün ort. +0 son gün — commit 20 Nis 2026 güncellendi 20 Nis 2026 - 405
Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides
0,3/gün ort. +0 son gün — commit 12 Haz 2026 güncellendi 22 Tem 2026 - 406
AI 工作流提示词|两套可复制的视频工作流:AI 数字人视频生产 + 实拍口播自动剪辑(剪气口、剪废话)
0,4/gün ort. +0 son gün — commit 14 Tem 2026 güncellendi 08 Ağu 2026 - 407
A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert
0,3/gün ort. +0 son gün — commit Python 02 Haz 2026 güncellendi 02 Haz 2026 - 408
Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization
0,3/gün ort. +0 son gün — commit Shell 10 Tem 2026 güncellendi 02 Ağu 2026 - 409
27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment
0,2/gün ort. +0 son gün — commit Python 15 Mar 2026 güncellendi 4 gün önce - 410
高级朦胧梦幻动态视觉 Skill:把随手拍照片转化为电影感图生图提示词。Dreamy motion editorial prompts from casual photos.
0,4/gün ort. +0 son gün — commit Python 09 Ağu 2026 güncellendi 09 Ağu 2026 - 411
AI가 청중에 맞는 HTML 발표자료와 발표 노트를 만들고 Chromium 기반 시각 검증까지 수행하도록 돕는 스킬·플러그인
20/gün ort. +0 son gün — commit HTML 05 Kas 2026 güncellendi 2 gün önce - 412
Built for OpenClaw and beyond, Chat Selfie lets your AI Agent send you emotional selfies in every conversation, with mood-aware replies, hea
0,2/gün ort. +0 son gün — commit Python 14 Mar 2026 güncellendi 26 Mar 2026 - 413
Antigravity 破甲工程:二进制提示词补丁 / 规则技能 / 生命周期钩子 / IDE 等长补丁 / 模型后端改道
0,8/gün ort. +1 son gün — commit JavaScript 16 Eyl 2026 güncellendi 10 gün önce - 414
A Codex CLI plugin that grades how you collaborate with Codex across 9 dimensions in 3 categories — your Codex model writes a free-form diag
0,3/gün ort. +0 son gün — commit 05 Haz 2026 güncellendi 20 Eyl 2026 - 415
local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools
0,2/gün ort. +0 son gün — commit Go 29 Mar 2026 güncellendi 11 May 2026 - 416
Pravidla, díky kterým AI píše český text jako člověk a nikoliv jako AI generátor. Krátký prompt do AI chatu, plný průvodce a skill pro AI ag
0,2/gün ort. +0 son gün — commit 03 Haz 2026 güncellendi 27 gün önce - 417
DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill tog
0,5/gün ort. +0 son gün — commit JavaScript 21 Ağu 2026 güncellendi 14 gün önce - 418
MCP server + prompt that turns any AI coding agent (Cursor, Claude Code, Cline, Kiro, Windsurf…) into your Digital Twin — generate a project
0,2/gün ort. +1 son gün — commit TypeScript 09 Nis 2026 güncellendi 03 Tem 2026 - 419
A deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate con
0,3/gün ort. +0 son gün — commit Python 08 Tem 2026 güncellendi 29 Ağu 2026 - 420
Aileron Protocol: A strict system harness override enforcing deterministic AI behavior through codebase-first execution, strict token econom
0,2/gün ort. +0 son gün — commit 25 May 2026 güncellendi 20 Haz 2026 - 421
930+ AI-powered skills and 31 agent plugins for Claude Code, OpenAI Codex, Gemini CLI, GitHub Copilot, and Perplexity Computer. The largest
0,2/gün ort. +0 son gün — commit TeX 14 Mar 2026 güncellendi 08 Tem 2026 - 422
15 creative techniques. Intensity slider 0.3-1.0. Drunk fusion mode merges with Drunk Claude. 4 output styles including playing cards. Trans
0,3/gün ort. +1 son gün — commit TeX 13 Haz 2026 güncellendi 27 gün önce - 423
Turn travel photos into archival photo-and-rubber-stamp field note posters.
0,5/gün ort. +0 son gün — commit Python 24 Ağu 2026 güncellendi 24 Ağu 2026 - 424
A 21-day hands-on journey to mastering AI for DevOps — covering LLMs, GenAI, CI/CD, Kubernetes, cloud, automation, and AI-powered DevOps pro
0,5/gün ort. +0 son gün — commit 25 Ağu 2026 güncellendi 28 Eyl 2026 - 425
A collection of AI prompts for generating comprehensive manual test scenarios from software projects, covering features, edge cases, securit
0,4/gün ort. +0 son gün — commit 31 Tem 2026 güncellendi 31 Tem 2026 - 426
A full-stack AI prompt library for discovery, structured authoring, safe imports, moderation, and shareable agents.
0,2/gün ort. +0 son gün — commit TypeScript 06 May 2026 güncellendi 27 Ağu 2026 - 427
Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method searc
0,2/gün ort. +0 son gün — commit Python 13 Nis 2026 güncellendi 04 Tem 2026 - 428
MiniMax H3 全域提示词工程 Skill v1.8.1|AIMixer Director 导演台生产规则 + 武打/兵器/枪斗编排|T2VA / I2VA / FL2VA / L2VA / Ref2VA|Subject 与 Picture 语义分离、跨镜头因果桥、人物一致
0,4/gün ort. +1 son gün — commit Python 04 Ağu 2026 güncellendi 24 gün önce - 429
Turn any local codebase into clean, structured, AI-ready data.
0,5/gün ort. +4 son gün — commit Python 24 Ağu 2026 güncellendi 10 gün önce - 430
中文 9 段式人像提示词创作体系 · 可直接出图的模板/风格预设/千条级批量生成器 · 覆盖全身照与上半身中景照 · 适配 ComfyUI/Krea2/GPT Image 2 · 无强制约束,创作自由
0,3/gün ort. +0 son gün — commit Python 07 Tem 2026 güncellendi 27 Ağu 2026 - 431
SEO Content Engine for LLMs - a prompt-engineering system that turns any capable AI into a world-class SEO strategist: generate, rewrite, an
0,3/gün ort. +0 son gün — commit Python 21 Haz 2026 güncellendi 12 Tem 2026 - 432
Production-grade vibe coding framework with specs, architecture, AI agents, testing, security, code review, CI/CD, and battle-tested workflo
0,8/gün ort. +0 son gün — commit JavaScript 22 Eyl 2026 güncellendi 7 gün önce - 433
Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.
0,2/gün ort. +0 son gün — commit 13 May 2026 güncellendi 04 Haz 2026 - 434
1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions
0,4/gün ort. +0 son gün — commit 31 Tem 2026 güncellendi 25 gün önce - 435
A skills & discipline framework for Microsoft 365 Copilot Cowork — for knowledge workers using AI as a coworker.
0,2/gün ort. +0 son gün — commit PowerShell 30 Nis 2026 güncellendi 15 Haz 2026 - 436
Production-grade, agent-portable image prompting skill for Nano Banana Pro and Nano Banana 2 in the Gemini image family
0,1/gün ort. +0 son gün — commit Python 09 Mar 2026 güncellendi 30 May 2026 - 437
AI teaching Skill based on the Feynman Technique — makes YOU teach the AI to expose gaps in your understanding. Works with Claude Code, Curs
0,2/gün ort. +0 son gün — commit Python 14 Nis 2026 güncellendi 18 May 2026 - 438
Build a reusable Markdown context about you and your company (Claude Code skills + templates), then use it in ChatGPT, Claude, Gemini, Curso
0,3/gün ort. +0 son gün — commit Shell 18 Haz 2026 güncellendi 22 gün önce - 439
图片/中文描述 → 英文绘图提示词(DeepSeek API)· Windows 零依赖单文件小工具 / Chinese(or image)-to-English image prompt translator
0,7/gün ort. +6 son gün — commit C# 17 Eyl 2026 güncellendi 03 Eki 2026 - 440
Interactive AI tutor built as a Claude Code skill — teaches with spaced repetition, personalized project examples, and a visual progress das
0,2/gün ort. +0 son gün — commit PowerShell 20 May 2026 güncellendi 29 Eyl 2026 - 441
Convert long AI conversations into portable conversation state graphs for LLM handoffs.
0,2/gün ort. +0 son gün — commit 30 May 2026 güncellendi 30 May 2026 - 442
An open Agent Skill for reconstructing faithful, reusable image-generation prompts from reference images.
0,4/gün ort. +1 son gün — commit 07 Ağu 2026 güncellendi 07 Ağu 2026 - 443
Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails
0,2/gün ort. +0 son gün — commit Ruby 20 Mar 2026 güncellendi 25 gün önce - 444
Grimoire's Tome & The Grim Council. A Prompt Spellbook of /skills. The #1 Coding Wizard 🧙♂️📖
0,5/gün ort. +0 son gün — commit JavaScript 25 Ağu 2026 güncellendi 14 gün önce - 445
Your coding agent starts every session knowing nothing about your project. One line, and it writes its own memory from your real code, then
0,6/gün ort. +0 son gün — commit Python 13 Eyl 2026 güncellendi 11 gün önce - 446
Frontier model solution tracing, then made the prompting skills
0,3/gün ort. +0 son gün — commit Python 05 Tem 2026 güncellendi 10 gün önce - 447
The Military-Grade Memory Hygiene, private, offline-first prompt manager for AI Agent power users. Features AES-256 encrypted local storage,
0,5/gün ort. +0 son gün — commit TypeScript 26 Ağu 2026 güncellendi 5 gün önce - 448
إطار مفتوح المصدر لتكييف مساعدات الذكاء الاصطناعي وسير العمل القانوني مع البيئة القانونية السعودية. Open-source framework for adapting AI as
0,2/gün ort. +0 son gün — commit Python 14 May 2026 güncellendi 3 gün önce - 449
CLAUDE.md + AGENTS.md 12-rule behavior file for Claude Code, Codex, Cursor, Hermes — drop-in, ~700 tokens, cuts AI coding mistakes ~40%→~3%
0,2/gün ort. +0 son gün — commit HTML 10 May 2026 güncellendi 11 May 2026 - 450
A Claude Code skill that rewrites your prompts for clarity before they run.
0,2/gün ort. +0 son gün — commit 06 May 2026 güncellendi 18 gün önce