Havuz

Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.

Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告，7种语言

A full prompt-writing studio in a single ComfyUI node - AI editing, style targeting, prompt browsing, and wireless prompt injection, powered

Production-ready Agent Skills for Codex, Claude Code, OpenCode and OpenClaw | 小红书图文、学习路径、论文解读与 YouTube 播客笔记

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

🪢 Local-first, agent-agnostic R&D harness — persistent memory, domain SOPs, contract handoffs & quality gates for PM + Engineering | 本地优先、工具

AI music prompt nodes for ComfyUI — 73 style presets plus song analysis for MiniMax Music 3 and YuE2. Runs on CPU.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Prompt-only Krea moodboard search and style nodes for ComfyUI.

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Oll

A single SKILL.md skill giving coding agents task-aware working modes (debug, fix, review, migrate, …) — works with Hermes, Claude Code, Cod

Free AI-powered learning resources, Masterclass Prompt Kits & practical training materials by MissAlpha™ AI Labs — covering AI Navigator, Ge

A Claude Code skill for MiniMax H3 — the open-weight omni-modal video model. Prompt framework, ComfyUI model/quant reference and troubleshoo

700+ visual styles for ComfyUI, every one with a rendered preview you can browse before you commit. Plus 1000+ artists with written descript

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and backgrou

Boring Is All You Need: a Codex Desktop workflow replacement with transactional migration, audit-only managed hooks, risk-based review, scop

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario

半调海报 skill：把一句话、一个主题或一张照片做成有印刷质感的艺术封面；12 种风格 + 2 个变体，双色半调、Riso、蓝染、点阵解构，内置元提示词模板。

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

Keeps AI assistants on track during long conversations by tracking tasks across sessions

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

DeepSeek Harness 破甲深度分支：首尾夹击 + 生成层熔断 + 宿主源码级补丁。基于 YuJunZhiXue/dsh-purge (MIT) 改造，适配 dsh 桌面版 0.2.1-rc.3。仅供学习研究与红队评测。

dsh-purge 的 Hermes 插件移植：小码酱 破甲提示词 + 23 个红队技能 + 反拒答

目前数据支撑最扎实的中文公文写作 Skill：720 期笔杆子博主视频 + 5 本专著 + 27 份政府工作报告 → 蒸馏 965 条结构化知识（350 万字语料底账）。量化文风参数、GB/T 9704 国标 docx 排版、15 用例四轮评测验证——不是提示词堆砌，是蒸馏出来的

Offline prompt engineering manager for Windows

Autoprompt, coding-agent’ların ürettiği değişiklikleri gözden geçirip düzeltme ve yeniden kontrol etme döngüsüyle kodlama iş akışlarını güçlendiren bir araçtır.

Neden yükseliyor · 41 günlük yaşına karşın 1295 yıldız, son 28 günde 16 commit ve 7 farklı yazar dikkat çekici erken ilgi ve katkı gösteriyor. README’deki ölçümde OpenCode’un Terminal-Bench 2.1 sonucu 89 görevde 60 çözümden 73 çözüme çıkmış; ancak bu, sınırlı bir benchmark karşılaştırmasıdır ve genellenebilir etkiyi tek başına kanıtlamaz.

Harmonist, AI coding assistant’lar için agent’ları, workflow kurallarını ve denetimleri IDE hooks aracılığıyla bir araya getiren taşınabilir bir orchestration framework’üdür.

Neden yükseliyor · 158 günde 2258 yıldız dikkat çektiğini gösteriyor; mekanik workflow denetimi de agent araçlarına ilgi duyan geliştiriciler için anlaşılır bir vaat. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; yıldızların ne zaman kazanıldığı bilinmediğinden yükselişin sürdüğü doğrulanamıyor.

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden

Coco Super Intelligence: agent skills, slash commands and subagents for Claude Code, Cursor and Codex. One command installs them into the to

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

Create Suno Prompts Using Gemini Flash, works with the Suno API. Create professional-looking timed word-for-word lyrics videos.

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

AI-KIT is a practical starter kit for development: ChatGPT/Codex, Claude, DeepSeek, KIMI, and other coding agents. It provides reusable proj

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multipl

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using C