Havuz

Obsidian vault’ını farklı CLI agent’lar arasında paylaşılan, Markdown tabanlı kalıcı hafıza ve bilgi yönetimi alanına dönüştüren bir Python projesi.

Neden yükseliyor · 187 günlük yaşına kıyasla 4.617 yıldız ve son 28 günde 131 commit ile dikkat çekiyor; aynı dönemde 12 farklı yazarın katkısı da projenin yalnızca tek geliştiricinin son dönemdeki commit’lerinden ibaret olmadığını gösteriyor. Birden fazla agent’ı kullanıcının kendi Obsidian vault’ındaki ortak hafızaya bağlama vaadi de güncel bir ihtiyaca hitap ediyor.

GPT Image 2/2.5 için prompt galerisi, agent skills ve görsel üretme/düzenleme odaklı bir CLI sunuyor.

Neden yükseliyor · 158 günde 5.568 yıldıza ulaşması görünürlüğünün yüksek olduğunu gösteriyor; geniş prompt galerisiyle CLI ve agent skills'i bir araya getirmesi de keşfedilebilir, doğrudan denenebilir bir paket sunuyor. Ancak yıldızlar kalite veya düzenli benimseme kanıtı değil; son 28 gündeki 13 commit ve 2 farklı yazar daha sınırlı geliştirme tablosuna işaret ediyor.

Appllama'nın agent skills paketi, mobil uygulama tasarımını araştırma yönergeleri ve Expo / React Native geliştirme iş akışlarıyla AI agent'lara yaptırmayı amaçlıyor.

Neden yükseliyor · Agent'lara mobil uygulama geliştirme becerisi kazandırma vaadi ve birden fazla agent ortamına tek komutla kurulum, güncel ilgiyle örtüşüyor. 45 günde 2106 yıldız dikkat çekici; ancak son 28 gündeki 2 commit ve 1 farklı yazar, bu ilginin sürekli geliştirme veya geniş katkıcı tabanıyla desteklendiğine dair sınırlı kanıt sunuyor.

Turn complex codebases into clear, navigable architecture diagrams with Claude Code.

Design visual, review-gated agent loops for Claude Code before you run them.

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with revie

Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.

Hyperliquid trading desk for AI agents: 7 roles, 17 skills and keyless market tools. Research first; execution requires your API wallet and

JeecgBoot Skills — AI 驱动 · 一句话生成全套工件! 在 Claude Code 中，用一句话生成 代码 · 表单 · 流程 · 报表 · 图表 · 大屏 · 仪表盘。 覆盖 JeecgBoot 低代码平台 与 JimuReport 积木报表 两大产品的企业

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, c

情圣 · Claude Code 中文恋爱教练技能 · 微信/探探/Soul/Bumble/青藤之恋聊天截图分析 · 高情商回复生成 · 7阶段关系推进

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS/Swift). Security

AI-powered GA4 + GTM event tracking — automates site analysis, event schema, GTM sync, preview verification, and publishing. Works with Curs

Air traffic control discipline for agent output. Written for a reader with ADHD.

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini

Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown kno

Lightweight Codex/Claude/Antigravity loop harness with strict evidence gates.

🖼️ AI agent skill for Claude Code & Codex — turns raw app screenshots into store-ready App Store & Google Play marketing images: device fram

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

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

Hand off tasks to Devin — a plugin/skill for Claude Code, Codex, Cursor, and any coding agent

Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdo

Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, a

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。

Claude Code skill for AI persona panels, virtual customer research, and concept testing.

Candid reviews of Claude Code skills. File:line citations. Ranked actions. No filler.

A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.

VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a statef

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

One-command installer for all AI Marketing Hub tools: Claude SEO, Claude Blog, Skill Forge, WP MCP Ultimate

CRISP — The missing layer between vibe coding and building something people actually want.

Claude Code skill: Kimi types, Claude thinks & verifies — route implementation work-orders to the Kimi Code CLI (k3). A port of @steipete's

Claude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once and kept current —

Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic sco

Interactive data-flow diagrams your AI agent can write. One SKILL.md — install in Claude Code, Cursor, Codex, and 11+ other clients via `npx

Strips the AI tells out of prose, code, and academic writing. 152 patterns from real AI-vs-human analysis, two-pass rewrite, three-tier scor

One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings

Claude Code skill: Generate design.md, design-guidelines.md & design-components.md from any design references — images, PDFs, links, screens

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref

"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with

A massive, self-updating local archive of AI tools — 11,000+ agent skills, 240+ MCP servers, 2,200+ IDE rules (Cursor/Cline), and 30+ system

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method searc

Claude Code skill: Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a supreme judge delivers the verdict

A Claude Code skill that rewrites your prompts for clarity before they run.

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

Build production marketing sites with Claude Code — an Astro + Cloudflare Workers template, a WordPress→Astro migration playbook, and 36 sil

Browse every recent Claude Code session across all your projects and jump back into any of them. Shows project path, summary, git branch, mo

Publish HTML frontend games to the AI Game MCP platform.