Havuz

Graftcode, farklı dil ve runtime’lardaki metotları Gateway üzerinden uzaktaki istemcilere yerel dependency gibi kullandırmayı amaçlayan bir geliştirme katmanıdır.

Neden yükseliyor · 87 günlük bir repoda 930 yıldız dikkat çekici bir başlangıç; son 28 günde 6 commit ve 4 farklı yazar da projenin yalnızca tek kişinin güncellediği bir demo olmadığını gösteriyor. Ancak bu veriler benimsenme veya README’deki geniş uyumluluk iddialarının doğrulandığını tek başına kanıtlamıyor.

让 AI 编程助手先查本机工具、按项目声明选对版本；查询严格只读，MCP 维护需显式确认。Windows 工具发现 + 零依赖 Node MCP。

Agent Skill that analyzes your repo and generates the AI-ready configuration coding agents need — AGENTS.md, copilot-instructions, CI, issue

Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates JSON and CSS custom propertie

Curated developer tools, AST analyzers, and automated verification workflows.

Flisk: your whole app, running on your computer with one command

Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and c

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flag

🧪 Serious APIs, curious projects. A playground for hackers, makers and developers experimenting with @Openapi®

Shorter replies with Claude Code. Save output token spend.

A Claude Code status line with a reactive character plus cost, git, and usage widgets. Zero token spend, local-first, MIT.

Prettier for localization, automatically convert React and Next.js apps into multilingual applications FAST.

Engineering knowledge infrastructure for AI coding agents.

Paste your code and get brutally roasted by AI — then refactored into something actually worth shipping.

A behavioral governance framework for GitHub Copilot agents — skills.md and instructions to make AI coding agents think like senior engineer

Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, an

Answers you can judge and act on without reading code — Claude Code plugins that keep implementation detail below a marked line. Off by defa

デバッグ能力を「鍛える」と「測る」を1つにしたBtoB向けの仕組み。AIは答えではなく段階的な問いを返し、業務を止めずに技術力が育つ。到達度・正答率・成長率を5軸で可視化し、人事評価の客観的な根拠として使える。

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

AI commit messages that are actually atomic — and work with your existing tools, no API key needed.

A cross-tool field guide to how I build with AI, with practical workflows and portable skills from research to maintenance.

Prismatic — a highly customizable, zero-dependency status line for Claude Code. Truecolor gradient model pills, a color-coded context bar, a