Havuz

"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

💀 Find the agent skills you never use. Local-first analytics for Claude Code & Codex skills.

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.

Leaked Claude Code source tree, documented: every file under claude/src with generated summaries, exports, dependency hints, and syntax-high

Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secrets detection, IaC +

Claude Code skill that finds and rates other instances of a bug you just fixed, then presents options to fix them after explicit user approv

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

Save 87% token usage for Claude Code. Zero install. 8 rules covering input+output+context. 6 months verified.

Tandem lets you connect and control any coding agent—including Claude, Codex, or Hermes—across different devices. It allows all your agents

A cross-platform, file-based persistent memory and prompt bridge for Claude Code, claude.ai, and Antigravity IDE. Synchronizes project passp

AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review,

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

Design enforcement system, not a code generator. Two independent layers (Taste Guardian + Blind Spot ESLint). 7-phase design pipeline. Zero

Claude Code execution playbook with 3 pilot modes: cost-first (Haiku), quality-first (Sonnet), ceiling-elevation (Opus). Quantitative escala

Knack CLI: agent-friendly skill operations. Self-host on GitHub or use Knack Cloud.

Production-grade Agent Skill for TypeScript, React & Next.js — decision guides, hard rules, and debugging playbooks for AI coding agents (Cl

Bionic reading for Claude Code: bolds the leading part of each word in Claude's streamed replies so your eyes move faster. Zero dependencies

A live local HTML report Claude keeps updated as it works — status board, running narrative, screenshots, newest-first log, live-reload. No

A Claude Code / Claude.ai Skill that turns any codebase into something deployable with docker compose up and shippable through CI/CD, harden

PinPin Visual Identity — a Claude Code skill encoding a battle-tested design aesthetic methodology. 5 core principles (restraint, grayscale

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve

Two-pass code audit skill for Claude Code: adversarial Opus deep review + Codex second opinion

El árbol de decisión para saber qué construir en Claude Code: una skill, un subagente, un hook, un servidor MCP, un plugin, una rutina, una

加密环境文件操作 MCP 工具。当 Node.js 是加密软件白名单进程时，通过 fs 模块自动解密读写文件明文，替代 AI Agent 内置文件工具，适用于任何支持 MCP 协议的 Agent。

多平台文章统一发布 Skill — 支持 CSDN、51CTO、博客园、掘金一键分发

Turn a UI screen recording into design data, code edits, or a runnable React scaffold. A Claude Code skill.

Open-source Claude Code skills - reusable, drop-in agent workflows for weekly reviews, resume audits, and more.

Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.

Telegram bot development skill for Claude Code and OpenCode: checks the live Bot API docs and the installed library (aiogram, grammY, python

A Claude Code skill that turns Claude into a vSphere administrator using govc. Inventory, reports, snapshot audits, root-cause analysis, and

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

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

Publish HTML frontend games to the AI Game MCP platform.

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

A Claude Code skill that shows you where your folder structure sends an agent before you trust it with the task.

Claude Code plugin: stops Claude before your usage limit and saves a checked handoff note, so a new chat picks up where it left off.

Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, bench

One prompt to modernize React + Tailwind UIs. A Claude Code Skill.

Deterministic content-readiness lint.

A Claude Code skill that turns your pipeline into an animated metro map, replayed from what a real run recorded. Retries as loop arcs, paral

Agent skill that conducts an interactive architectural walkthrough and verification quiz over a codebase.