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…
- 301
Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.
0,4/gün ort. +0 son gün — commit HTML 14 Haz 2026 güncellendi 22 Ağu 2026 - 302
面向电商视觉生产的 Agent 技能库:26 个可组合的 skill.md,覆盖平铺图 → 模特上身 → 裂变套图 → 详情页 → 主图视频 → 投前质检 → 平台合规校验。不锁后端,dLazy / OpenAI / Gemini / fal / Replicate / 火山方舟
0,8/gün ort. +1 son gün — commit JavaScript 17 Ağu 2026 güncellendi 4 gün önce - 303
DeepSeek V4 特化思维链引导规范:we need to 句式,任意 agent 客户端可接入(纯提示词层)
0,7/gün ort. +0 son gün — commit 15 Ağu 2026 güncellendi 10 Eyl 2026 - 304
Visualize your project's feature logic as a semantic flow graph — not call graphs, not import maps. AI writes the data, you see the story.
0,3/gün ort. +0 son gün — commit TypeScript 15 May 2026 güncellendi 17 Tem 2026 - 305
Screenplay breakdown & AI prompt-pack studio — import a script, get scenes, elements, bibles, shot lists & a timeline, then export self-exec
0,5/gün ort. +1 son gün — commit HTML 18 Tem 2026 güncellendi 05 Ağu 2026 - 306
AI academic PPT workflow skill for Codex / ChatGPT: paper-to-editable PowerPoint, planning table, mockup family, and PPTX generation.
0,4/gün ort. +1 son gün — commit Python 03 Haz 2026 güncellendi 07 Eyl 2026 - 307
Don Cheli — SDD Framework. The most comprehensive Specification-Driven Development framework for AI agents. 88+ commands, 51 skills, 15 reas
0,3/gün ort. +0 son gün — commit TypeScript 21 Mar 2026 güncellendi 10 Ağu 2026 - 308
A desktop workspace for crafting vivid AI personas and exploring what emerges when different personalities fuse.
0,4/gün ort. +0 son gün — commit Go 28 May 2026 güncellendi 2 gün önce - 309
AutoResearch + PromptFoo = AutoPrompter. Run it with Neo AI Engineer
0,2/gün ort. +0 son gün — commit Python 16 Mar 2026 güncellendi 16 Nis 2026 - 310
Vibe Coding 轻量项目实验室:Web 应用、桌面工具、Prompt 资料库与 Codex Skills
0,5/gün ort. +0 son gün — commit JavaScript 05 Tem 2026 güncellendi 9 gün önce - 311
Hybrid rule-based and context-aware LLM evaluation system for Chinese-to-Japanese game localization QA.
0,9/gün ort. +0 son gün — commit Python 04 Eyl 2026 güncellendi 21 gün önce - 312
ZCode+ 提示词增强:为 ZCode 桌面版注入一键式提示词增强按钮(CDP 注入,零依赖,支持自定义模板)
1/gün ort. +0 son gün — commit JavaScript 07 Eyl 2026 güncellendi 13 Eyl 2026 - 313
Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep
0,3/gün ort. +0 son gün — commit Python 26 Nis 2026 güncellendi 22 Tem 2026 - 314
Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT
0,3/gün ort. +0 son gün — commit JavaScript 11 May 2026 güncellendi 11 May 2026 - 315
Make AI-generated prose sound human. 29-pattern catalog + 8-rule operating system + 8-dimension scoring rubric. Works with Claude Code, Open
0,3/gün ort. +0 son gün — commit Shell 01 May 2026 güncellendi 28 May 2026 - 316
A Sovereign Agent Governance Protocol for Deep-Water Workflows
0,2/gün ort. +0 son gün — commit JavaScript 17 Mar 2026 güncellendi 07 May 2026 - 317
讓 AI 用台灣人的繁體中文講話,並把已寫好的文字清掉 AI 味。Claude Code、claude.ai、ChatGPT Codex 與一般聊天都能用。
0,7/gün ort. +1 son gün — commit Python 14 Ağu 2026 güncellendi 04 Eyl 2026 - 318
An opinionated ecosystem of rules, skills, and steerings to elevate Delphi development to a state-of-the-art level with Artificial Intellige
0,2/gün ort. +0 son gün — commit 20 Mar 2026 güncellendi 26 Mar 2026 - 319
Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t
0,5/gün ort. +0 son gün — commit HTML 17 Tem 2026 güncellendi 5 gün önce - 320
面向 AI Agent 的全流程长篇小说创作技能。从书名生成到千章完稿,配备三大自动系统(记忆系统/强约束/叙事质量管理)确保长篇连贯性。支持 AI 全自动和分步引导双模式。
0,3/gün ort. +0 son gün — commit PowerShell 10 May 2026 güncellendi bugün - 321
意图放大与 Goal Contract 协议,面向 Codex 和 Claude Code 的 goal Skill
0,4/gün ort. +0 son gün — commit JavaScript 19 Haz 2026 güncellendi 21 gün önce - 322
Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcrip
0,4/gün ort. +0 son gün — commit TypeScript 10 Haz 2026 güncellendi 06 Eki 2026 - 323
Make your AI think like Munger, Feynman, or Paul Graham — load real mental models, not personas.
0,3/gün ort. +0 son gün — commit 02 Nis 2026 güncellendi 09 Nis 2026 - 324
A Codex skill that keeps human outcomes and creative intent ahead of overengineering.
0,5/gün ort. +0 son gün — commit 23 Tem 2026 güncellendi 13 Ağu 2026 - 325
让 ComfyUI 像 WebUI 一样写提示词:中文翻译、Tag 自动补全、LoRA 管理、区域提示词控制,支持 Anima 与 SDXL 工作流。
0,3/gün ort. +0 son gün — commit JavaScript 23 May 2026 güncellendi dün - 326
DSH PUA — 为 DeepSeek Harness 提供 PUA 任务推进、角色风味、验收循环和运行状态卡片 · PUA task persistence, personas, verification loops, and live status cards for De
1/gün ort. +3 son gün — commit TypeScript 12 Eyl 2026 güncellendi dün - 327
Collection of Hermes Agent profiles — persona-driven AI agent configurations for orchestration, coding, and research.
0,4/gün ort. +0 son gün — commit Python 15 Haz 2026 güncellendi 14 Ağu 2026 - 328
A behavioral governance framework for GitHub Copilot agents — skills.md and instructions to make AI coding agents think like senior engineer
0,2/gün ort. +0 son gün — commit TypeScript 12 Mar 2026 güncellendi 07 Eyl 2026 - 329
Agent Skill that silently refines prompts for the currently running model
0,4/gün ort. +0 son gün — commit Python 05 Haz 2026 güncellendi 3 gün önce - 330
An agent skill for prose that sounds clear, specific, and human.
0,3/gün ort. +0 son gün — commit Python 27 May 2026 güncellendi 5 gün önce - 331
A pi extension that suggests the user's likely next prompt.
0,2/gün ort. +0 son gün — commit TypeScript 10 Mar 2026 güncellendi 23 gün önce - 332
Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project
0,4/gün ort. +0 son gün — commit Shell 05 Haz 2026 güncellendi 03 Eyl 2026 - 333
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
0,4/gün ort. +0 son gün — commit JavaScript 07 Tem 2026 güncellendi 2 gün önce - 334
电商主图与详情页视觉策划、参考反推和生产级生图提示词 Skill
0,8/gün ort. +1 son gün — commit 01 Eyl 2026 güncellendi 01 Eyl 2026 - 335
AI Image Generator is a powerful and user-friendly desktop application designed to help creators produce stunning, high-quality artwork, pho
0,2/gün ort. +0 son gün — commit 06 Nis 2026 güncellendi 06 Nis 2026 - 336
Claude skill for generating and beautifying resumes — 11 print-ready HTML templates, structured data pipeline, three entry flows (beautify /
0,4/gün ort. +0 son gün — commit HTML 29 Haz 2026 güncellendi 05 Tem 2026 - 337
For those who struggle with how Claude speaks to them. No more essays. No more slogans, metaphors, "it's not X, it's Y". This plugin makes C
1,2/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 29 gün önce - 338
Claude Skill | 中文学术论文知网AIGC降重 | 实战将AI率20.6%降至10.1% | A Claude Skill for rewriting CNKI AIGC-flagged Chinese academic paragraphs
0,3/gün ort. +0 son gün — commit 01 May 2026 güncellendi 01 May 2026 - 339
CRISP — The missing layer between vibe coding and building something people actually want.
0,2/gün ort. +0 son gün — commit Python 23 Mar 2026 güncellendi 18 Eyl 2026 - 340
基于上游 1.1.71 维护的 dsh-purge 社区兼容包:只负责 DeepSeek Harness 的版本与本地 Windows 运行问题兼容。
3/gün ort. +5 son gün — commit JavaScript 20 Eki 2026 güncellendi 5 gün önce - 341
The open engine behind Aedelgard: a persistent, self-hosted AI agent with a verbatim memory palace and a model-agnostic brain. Swap Claude,
0,3/gün ort. +0 son gün — commit Python 19 Nis 2026 güncellendi 27 gün önce - 342
Ecossistema de Engenharia de Estudos com IA Fundamentada (NotebookLM + Gemini Estudantes). Metodologia N.A.G. (Nucleo de Aprendizagem Guiada
1,1/gün ort. +2 son gün — commit 21 Eyl 2026 güncellendi 26 gün önce - 343
🎬 Director-grade Seedance 2.0 prompt OS for OpenClaw + Hermes agents — 28 skills, T2V/I2V/V2V/FLF2V, multi-clip sequences, zh/ja/ko support,
0,4/gün ort. +0 son gün — commit Python 08 Tem 2026 güncellendi 08 Tem 2026 - 344
A structured failure-analysis workflow that assumes your plan already failed and works backward to find every reason why. Based on Gary Klei
0,3/gün ort. +0 son gün — commit 03 May 2026 güncellendi 30 Haz 2026 - 345
The Agency — a roster of 200+ specialist AI agent personas (engineering, design, marketing, sales, security, GIS, game-dev & more) for Claud
0,4/gün ort. +2 son gün — commit Shell 05 Tem 2026 güncellendi 05 Tem 2026 - 346
AI-driven intelligent clipboard turns scattered content across applications into a searchable, editable AI context. It features a clean, ele
0,8/gün ort. +0 son gün — commit C# 01 Eyl 2026 güncellendi 13 Eyl 2026 - 347
小优AIGC(抖音小优与AIGC的奇妙冒险)的 AI 摄影剧组 skill —— 电影摄影级生图提示词生成器,可装入 Claude Code / Codex / Hermes
0,4/gün ort. +0 son gün — commit 15 Tem 2026 güncellendi 22 Tem 2026 - 348
A compact operating covenant for AI agents.
0,3/gün ort. +0 son gün — commit Python 30 Nis 2026 güncellendi 26 May 2026 - 349
AI Paper Reviewer: LLM-based tool for academic paper review
0,3/gün ort. +0 son gün — commit Python 01 Haz 2026 güncellendi dün - 350
Low-code templating for LLM prompts: Jinja2 templates, token accounting, and cache-aware truncation.
50/gün ort. +0 son gün 1 commit 1 yazar Python 05 Kas 2026 güncellendi dün