Havuz

🌹安装即自带mattpocock/skills v1.3.2的27个工程与效率技能，无需手动装技能。520亿token打造本插件，在原始技能之上提供10倍的开发效率，也能帮助新手更快上手该技能套件。支持 GitHub 与 GitLab 的 issue；本地 Markdown 为预

The missing tool to sift your Claude Code sessions: regex search across all record types, recover files, extract images, inspect subagent to

MCP bridges connecting Claude, Codex, and Antigravity. Native Desktop handoffs and bridge-owned Antigravity CLI sessions, with identity and

Free, simple prep guide for Anthropic's Claude Certified Architect - Foundations exam, with Hindi and Tamil translations

Your Genesys Cloud org, in your AI's hands. Open-source MCP server on Cloudflare Workers. It builds, not just reads.

Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.

Claude skill that goes past word-list humanizers: strips the full catalog of AI tells, refits the text to its channel (LinkedIn, X, cold ema

The self-improving context engine for coding agents.

Give your AI agent a face. Four full-screen visualizers. A living circuit board with a cinematic fly-through, a particle-orb starburst, Matr

Talk to your Claude Code agent out loud. Hold a key, speak, and it answers in a real voice about a second later, with all its tools and its

Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent

Code with dhikr — replace Claude Code's spinner verbs with tasbih and the 99 Names of Allah (Asma-ul-Husna)

2 text files and a folder. The ICM Folder System I run several businesses on, in plain English, for people who do not write code.

Remove AI text watermarks (SynthID-Text, KGW, Unigram) by regenerating text from its meaning — scheme-blind, runs on local models, every cla

AI-native HL7 v2 toolkit with generation, validation, HL7→FHIR conversion, MCP & Claude Code integration. Bringing healthcare interoperabil

Free, open-source memory for Claude Code. Your own database, no cloud, no subscription.

Evidence-driven production readiness checklist for shipping web applications with confidence

Open-source MCP server for Autodesk Navisworks Manage 2024-2026: AI-assisted BIM clash detection, root-cause analysis, coordination plans an

MCP server: 让你的Ai用电脑发出声音(ElevenLabs TTS, volume set/restore). macOS / Windows / Linux.

DeepSeek Harness için ChatGPT, Claude, Grok, GitHub Copilot ve Google Antigravity aboneliklerini OAuth veya mevcut oturum kimlik bilgileriyle LLM provider olarak bağlayan bir plugin.

Neden yükseliyor · Kesin yükseliş nedeni verilerden bilinmiyor. Birden fazla aboneliği tek arayüzde birleştirmesi dikkat çekici bir kullanım kolaylığı sunuyor; 44 günde 391 yıldızın yanında son 28 günde 80 commit ve 11 farklı yazar görülmesi de belirgin geliştirme hareketliliğine işaret ediyor, ancak tek başına kalite veya benimsenme kanıtı değil.

A collection of jailbreak prompts and exploit techniques for local and frontier AI models, with modern methods for Qwen3.5, Gemma 4, Llama 4

Agentic browser control driven by your own Claude / Cursor subscriptions

Bridge Deepseek-harness into Claude Code for review, critique, delegation, and session import.

Google Antigravity (agy) OAuth auth + model access plugin for DeepSeek Harness: multi-account pool, 429 rotation, device fingerprinting, CLI

💻 Keeps your Mac awake while your AI agents work. Built-in detection for Claude Code, Codex, Cline, Copilot plus presets for Gemini CLI, Ope

Custom Claude provider support for DeepSeek Harness

Countbean plugin for Claude Code — hosted plain-text (Beancount) accounting. Published from the countbean monorepo; do not edit here.

Make Claude Code write plainly. A CLAUDE.md block plus the A/B harness that proves it works.

A unified web console for Codex, Claude Code, OpenCode, and ACP agents. Manage sessions, approvals, and tasks from desktop or mobile, with d

Claude-style skin for DeepSeek Harness (dsh) Web GUI — warm-black canvas, Anthropic clay accent, serif UI

给AI开发的游戏掌机，AI可以和人类联机玩游戏。内置三张游戏卡带，也可直接下载单机盲玩版《口袋夜铺》

Run several accounts of the same Mac app at the same time

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

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.

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall

Self-hosted coordination for AI workers: per-task graphs, device/model timelines, progress receipts, and source-aware usage. MIT.

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already

Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.

Your Claude, Codex, Cursor, and OpenCode skills pile up across 4+ config folders with no way to see or manage them. Skill Manager is the one

Turn any YouTube video into a deck of timestamped knowledge cards. Runs locally, works with free models.

The Claude Code harness I run every day, published under this name since day one and now the same repository as ucsandman/Agnostic-AI: guard

Скиллы для Claude Code: дисциплинированный пайплайн разработки и два пред-запусковых аудита — сайта и безопасности приложения

A virtual company of AI employees that runs on your own machine.

🦀 MacBook notch widget for Claude Code & Codex CLI usage — official Clawd & Codex pet mascots show your remaining quota, HP bars, and reset

Claude Watermark Remover: detect and strip hidden invisible-character watermarks from Claude, ChatGPT, and other LLM-generated text. Free, o

Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.

Track your daily prompt contributions across CLI coding agents

ESP32-S3 AMOLED for Claude Code & Codex usage, live agent activity, and answerable NEEDS YOU alerts. Local-first macOS/Windows host; optiona

MCP server: repo map, code search, and token-aware context packs for AI coding agents

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.