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…
- 1
Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
27,5/gün ort. +21 son gün 30 commit 4 yazar JavaScript 12 Eki 2026 güncellendi 17 gün önce - 2
A drop-in AGENTS.md system prompt for coding agents: full execution, no hedging, no moralizing, no fade-to-black.
10/gün ort. +0 son gün 2 commit 1 yazar 24 Eki 2026 güncellendi 10 gün önce - 3
9Router — Pro edition of 9Router with Prompt Injection (system prompt or chat script per global / API key / model), per-key token quotas, ac
6,4/gün ort. +2 son gün 392 commit 2 yazar JavaScript 20 Eki 2026 güncellendi dün - 4
Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-
5,7/gün ort. +0 son gün 0 commit 0 yazar 01 Nis 2026 güncellendi 11 May 2026 - 5
The Claude Mythos 5.1 System Prompt
2,6/gün ort. +0 son gün 5 commit 1 yazar 07 Eki 2026 güncellendi 27 gün önce - 6
Published: 2026-10-18
1,5/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 16 gün önce - 7
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. +0 son gün 2 commit 1 yazar Python 12 Ağu 2026 güncellendi 10 gün önce - 8
从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill
1,2/gün ort. +1 son gün 0 commit 0 yazar 04 May 2026 güncellendi 04 May 2026 - 9
Independent research on Claude Code internals, Claude Agent SDK, and related tooling.
0,8/gün ort. +0 son gün — commit HTML 26 Mar 2026 güncellendi 31 Mar 2026 - 10
Rational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and re
0,8/gün ort. +0 son gün — commit 23 Haz 2026 güncellendi 14 Eyl 2026 - 11
Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and
0,6/gün ort. +0 son gün — commit TypeScript 31 Mar 2026 güncellendi 31 Mar 2026 - 12
An AI prompt-skill that turns 20 cognitive biases into high-converting marketing copy. Includes playbooks for ads, landing pages, email sequ
0,5/gün ort. +7 son gün — commit 18 Haz 2026 güncellendi 4 gün önce - 13
A system prompt against AI sycophancy, backed by 42 sources on why models tend to agree with you.
0,5/gün ort. +0 son gün — commit 16 Eyl 2026 güncellendi 16 Eyl 2026 - 14
A curated collection of Claude Fable 5 system prompts for developers and researchers. Discover more advanced prompt engineering tools at Moe
0,5/gün ort. +0 son gün — commit 15 Haz 2026 güncellendi 15 Haz 2026 - 15
346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality ev
0,4/gün ort. +0 son gün — commit Python 04 Haz 2026 güncellendi 17 Eyl 2026 - 16
赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation
0,4/gün ort. +0 son gün — commit HTML 06 Nis 2026 güncellendi 10 Nis 2026 - 17
DeepSeek Harness (dsh) 插件：注入系统提示词，强制 Agent 的思维链 / 规划 / 工具推理全程使用简体中文，防止中文思考漂移为英文。零外部依赖，任意本地目录 link 即装。
0,3/gün ort. -1 son gün — commit JavaScript 06 Eyl 2026 güncellendi 01 Eki 2026 - 18
Edit a DeepSeek Harness (dsh) custom mode: system prompt, base mode, and plugin switches.
0,3/gün ort. +0 son gün — commit JavaScript 17 Eyl 2026 güncellendi 6 gün önce - 19
A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a
0,3/gün ort. +0 son gün — commit 18 Haz 2026 güncellendi 01 Eyl 2026 - 20
Open database of system prompts extracted from frontier LLMs using JustAsk
0,2/gün ort. +0 son gün — commit HTML 31 Mar 2026 güncellendi 04 Nis 2026 - 21
OpenAI Codex 自定义系统提示词注入工具 | System Prompt Injection | CTF Security Research Red Team | Auto Install | Cross-Platform
0,2/gün ort. +0 son gün — commit Python 16 May 2026 güncellendi 08 Haz 2026 - 22
Free anti-AI-slop system prompt & skill that makes ChatGPT, Claude, Gemini, Grok & Kimi write like a human. Bans AI tells (delve, tapestry,
0,2/gün ort. +0 son gün — commit JavaScript 30 Haz 2026 güncellendi 01 Tem 2026 - 23
Simplified Technical English for Code - extract, adapt, and enforce ASD-STE100 rules for software documentation. 9-agent pipeline, 59-test b
0,2/gün ort. +0 son gün — commit Python 29 Tem 2026 güncellendi 11 Eyl 2026 - 24
Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillat
0,1/gün ort. +0 son gün — commit Python 17 Haz 2026 güncellendi 10 Eyl 2026 - 25
Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.
0,1/gün ort. +0 son gün — commit JavaScript 16 Nis 2026 güncellendi 24 Ağu 2026 - 26
Reverse-engineer how you think, talk, and make decisions — then turn it into a stress-tested AI System Prompt. Works on any LLM. Full pipeli
0,1/gün ort. +0 son gün — commit Python 06 Nis 2026 güncellendi 02 Eki 2026 - 27
A methodology so aggressive it demands to be replaced.
0,1/gün ort. +0 son gün — commit Python 24 Haz 2026 güncellendi 26 gün önce - 28
A portable agent skill (SKILL.md + reference playbooks) for writing top-conference embodied-AI papers — distilled from 63 papers (CoRL/RSS/I
0,1/gün ort. +0 son gün — commit Python 25 May 2026 güncellendi 10 gün önce - 29
A strategic-reasoning AI tuned to the Hammerstein framework. Portable system prompt + retrieval. The framework survives the model.
0,1/gün ort. +0 son gün — commit Python 05 May 2026 güncellendi 31 Tem 2026 - 30
Behavior guidelines that stop your AI coding agent from overengineering, hallucinating, and breaking things
0,1/gün ort. +0 son gün — commit Python 19 May 2026 güncellendi 30 Eyl 2026