Aradotso

AI agent skill for using deepsec, the agent-powered security vulnerability scanner for large codebases

Open-source Luau/Lua script IDE and executor built as a Windows Forms C# application with Monaco editor integration

Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend at up to 17x lower cost.

Native macOS Markdown viewer app with Quick Look extension, Mermaid diagrams, KaTeX math, document outline, and editor integration

Minimalist batteries-included repository for training, evaluating, and deploying diffusion-forcing video world models for robot manipulation, gaming, and MPC planning.

WARNING - This project is malicious software disguised as an FL Studio crack/patcher

SysWatch is a single-host system diagnostics TUI for macOS and Linux with twelve tabs, plain-English insights, and session scrubbing.

Headless iOS Simulator manager with host-side HID input injection, 60fps streaming, and device farm web UI for iOS 26

Expert guidance for integrating OptiScaler Client, a C# Windows application that manages AI upscaling (DLSS/FSR/XeSS) and frame generation mods for games

Tutorial project for building a Claude Code-style agent CLI from scratch in Python with tool calling, file editing, and permission systems

AI-driven browser automation using Chrome DevTools MCP with WebMCP tools for structured, token-efficient interactions

A Minecraft launcher providing FPS optimization, PvP mods, and performance enhancements for competitive gameplay

Agentic coding system and terminal assistant powered by Anthropic Claude with multi-file editing, git workflows, MCP protocol, and automation

Master ClickLight, the macOS menu bar app that highlights clicks for demos, recordings, and UX reviews with real-time visual feedback.

WeChat Mini Program development automation via MCP - IDE control, debugging, testing, and deployment workflows

CLI for integrating Volcengine AI Search, recommendation, and conversational retrieval into agent and business systems

Build, test, and debug Tauri v2 applications using AI assistants with the Model Context Protocol server for UI automation, IPC monitoring, and mobile development

Executable context layer for data and analytics agents with skills, memory, and semantic layer for accurate warehouse queries

Use ktx to build an executable context layer for AI data agents, enabling accurate warehouse queries through semantic layer, skills, and memory

Context layer for data agents that teaches AI how to query warehouses accurately with approved metrics, semantic layers, and business knowledge

Build and query a self-improving context layer for AI data agents with ktx - combines warehouse metadata, metrics, and wiki knowledge

Build and query a context layer for AI data agents with ktx - auto-learning semantic layer, wiki, and MCP integration

Expert in ktx - the executable context layer for data and analytics agents with skills, memory and semantic layer

Executable context layer for AI data agents to query warehouses accurately through MCP with skills and memory

Automate content creation from research to video generation using AI-powered pipeline with Claude, OpenAI, and Remotion

Automated AI content pipeline that researches, generates scripts, and creates videos using Claude/OpenAI and Remotion

Ultimate AI Content Pipeline for automated research, content generation, and video creation using Claude, OpenAI, and Remotion

Automate content creation from research to video generation using Claude/OpenAI and Remotion for marketing pipelines

Automated Vietnamese/English content pipeline with AI research, script generation, and video rendering using Claude/OpenAI and Remotion

Automated AI content pipeline from research to video generation using Claude, OpenAI, and Remotion

Automated AI content pipeline for research, scriptwriting, and video generation using Claude/OpenAI and Remotion

Automated AI content pipeline for research, script generation, and video creation using Claude, OpenAI, and Remotion

Executable context layer for data and analytics agents - enables Claude Code, Codex, and AI agents to query data accurately through MCP with skills, memory and a semantic layer

Connect AI agents to MATLAB with MCP tools and curated skills for engineering and scientific workflows

An executable context layer that teaches AI agents to query data warehouses accurately through MCP with skills, memory, and a semantic layer

Context layer for AI data agents - teach Claude Code, Codex, and AI agents to query data warehouses accurately with semantic layer, wiki knowledge, and MCP tools

Use ktx to give AI agents accurate data warehouse querying through semantic layers, metrics, and business knowledge via MCP

Install and configure ktx, an executable context layer for data and analytics agents that enables accurate warehouse queries through MCP with semantic layer and skills

Context layer for AI data agents - query warehouses accurately with semantic layers, metrics, and wiki knowledge through MCP

Teach AI agents how to query data warehouses accurately using ktx - an executable context layer with skills, memory, and a semantic layer

Fully automatic OpenClaw skill manager for Windows - installs, updates, and launches 5200+ community skills from ClawHub with zero manual configuration

Connect MetaMask wallets, read balances, sign messages, and send transactions on EVM chains with a safety-first TypeScript SDK

Build and configure DeepSeek model integrations with OpenClaw agent framework using this local-first web app.

AI-enhanced Polymarket CLOB trading bot for BTC 5m/15m prediction markets with arbitrage strategies and risk management

AI-enhanced Polymarket CLOB trading bot for BTC 5m/15m arbitrage with OpenClaw decision engine

Build and operate AI-powered trading bots for Polymarket prediction markets with CLOB arbitrage on BTC 5m/15m windows

Build, configure, and extend HermesPet — a native macOS AI companion living in the Dynamic Island with multi-engine support, desktop pets, and advanced system integration

Fully automatic OpenClaw skill manager that installs, updates, and launches 5200+ community skills from ClawHub with zero manual configuration

115 brand-themed HTML design references for Claude Code — talk naturally ("Linear-style page", "飞书风的页面") to apply real brand tokens.

Context-aware motion design skill with build and audit modes, applying three distinct philosophies from Emil Kowalski, Jakub Krehel, and Jhey Tompkins

Generate DESIGN.md files from any website using Context.dev APIs for design tokens, brand data, and visual extraction

Install and use themed shadcn/ui components from 31+ design systems (Linear, Stripe, Apple, Notion, etc.) with one command

Apply 100 distinct design styles to AI-generated presentations and websites using Claude Code's design-pick skill

AI-powered UI/UX generator with dual-brain architecture (Claude + OpenAI), sub-agent workflow, and design-to-code translation

Unofficial Figma desktop client for collaborative interface design, prototyping, and FigJam whiteboarding

Comprehensive guide for designing production AI systems, RAG architectures, LLM engineering, agentic AI, and interview preparation

Security testing framework for automotive vehicle networks including CAN, LIN, and FlexRay protocols

Audit email account security, validate credentials, and manage email lists using this C++ email security testing utility

Self-hosted pentest management workspace for tracking engagements, running tools, auto-importing findings, and generating reports

Advanced Python web security scanner with 49 modules, evasion engine, CVE database, and WAF bypass for penetration testing

Implement Cisco's Foundry specification for agentic AI security evaluation systems with multi-agent architecture

AI-driven autonomous penetration testing with Kali Linux tools, multi-phase attack planning, and human approval gates for high-risk actions

Execute deterministic, event-sourced security audits using ESAA-Security's LLM-based agent architecture with 95 checks across 16 security domains

Interactive pentest report generator with vulnerability tracking, real-time risk statistics, and PDF export in multiple languages

Analytics engineering with Snowflake, dbt, and Inside Airbnb data - staging, marts, incremental models, tests, and Streamlit dashboards

End-to-end ETL pipeline and analytics for Harvard Art Museums API with SQL storage and Streamlit visualization

Build ETL pipelines and analytics dashboards using Harvard Art Museums API with Python, SQL, and Streamlit

Build ETL pipelines and analytics dashboards using the Harvard Art Museums API with Streamlit, MySQL, and Plotly

Build ETL pipelines and analytics apps using the Harvard Art Museums API with Python, SQL, and Streamlit

End-to-end data engineering pipeline with Harvard Art Museums API, ETL processing, SQL analytics, and Streamlit visualization

ETL pipeline and analytics application for Harvard Art Museums API data with SQL storage and Streamlit visualization

Build ETL pipelines and analytics dashboards for Harvard Art Museums API data with MySQL storage and Streamlit visualization

Build and use custom extensions for Pi Coding Agent, the open-source alternative to Claude Code with UI customization, multi-agent orchestration, and safety controls

Install and configure the Free Claude Code AI Desktop App with Anthropic Claude API, CLI, local LLM Ollama integration, and AI coding features on Windows 11

Use Claude Code CLI for agentic coding, multi-file editing, git workflows, and terminal automation with Anthropic's Claude API

Run decisions through 5 AI advisors with peer review using the LLM Council methodology

Bridge Feishu/Lark messenger with local Claude Code CLI for streaming conversations, per-chat sessions, and workspace management

AI-native video production toolkit for programmatic video creation with Remotion, ElevenLabs, and cloud AI tools

Safety net plugin that blocks destructive git and filesystem commands in Claude Code, OpenCode, Gemini CLI, Copilot CLI, and Codex

Convert Claude Code session files (JSON/JSONL) to clean, paginated HTML transcripts with GitHub integration

Mirror and download official Codex desktop app installers from GitHub Releases with verified checksums

Chinese-first academic research skills for paper writing, Office document generation, and scientific computing (MATLAB/Python)

Local Rust proxy that translates OpenAI Codex CLI Responses API into Chat Completions for Kimi, DeepSeek, GLM, and other OpenAI-compatible providers

CodexGuide - Comprehensive practical guide for OpenAI Codex across CLI, desktop app, cloud, and IDE integrations for beginners to teams

Run Codex Desktop with Factory BYOK models and ChatGPT GPT-5.5 via local API shim

CodexIsland - Display AI usage limits (Claude Code & Codex) in your MacBook notch with Dynamic Island-style UI

Opt-in red team mode for AI coding assistants that enables security-focused thinking for penetration testing and red team operations

Generate image-based PowerPoint presentations using gpt-image-2, converting articles, papers, and reports into visual slide decks

End-to-end validate a `text.ara.so/backend` (website-agent) fix against a real Railway preview environment BEFORE merging to main. Pushes the current branch, deploys the SHA to the long-lived `preview` Railway env, confirms the new `git_sha` is live via `/healthz`, then sends a focused signed webhook replay (single-turn or short multi-turn) to a reserved 555-01XX test phone, and polls Braintrust for the root span's `outcome` / rounds / tools / reply. Use whenever you change anything in `backend/src/` (tool handlers, system prompt, builder loop, etc.) and want production-fidelity proof — not just unit tests — before opening the PR. Invoked as `/replay-railway-preview` or `/replay railway preview`.

Ara's secrets convention — all runtime credentials live in Infisical (project "Ara-passwords"), one folder per active GitHub repo (`/ara-engineer`, `/text-ara-so`). The old megarepo lives at `/legacy-ara-megarepo` tagged `legacy` — reference only. Never ask the user to paste keys; never commit .env; never build a custom vault.

Align the website-agent (system prompt + routing) with successful on-Ara website building; analyze Braintrust traces for derailment (wrong phase, local-dev tutoring, missing deploy, paywall/connect confusion), patch `text.ara.so/backend` (primarily `system-prompt.ts`), then verify in a tight loop—`bt` / Braintrust evals / `bun run e2e` (replay + live)—and report a before vs after fit table. Invoked as `/align`, `/align <trace url>`, `/align users …` (pair with `/trace` to gather traces). Companion to `/trace`.

Ara agent-trace debugging — inspect Braintrust traces for the website-agent (TS/Bun, Cerebras, Vercel AI SDK v6). Invoked as `/trace recent`, `/trace turn <turn_id>`, `/trace convo <chat_id>`, `/trace user <phone>`, `/trace top users` (aggregate: who messaged most in a time window — one latest-turn link per sender, table below), `/trace tool <name>`, `/trace span <id>`, `/trace <url>`, `/trace test` (run canonical e2e via `text.ara.so/backend/scripts/e2e.ts` (`bun run e2e --target=local --scenarios=<name>`)), `/trace score`, `/trace online`, or `/trace grow`. **Use `/align`** to align system prompt and gates to traces and report before/after tables (`skills/align/SKILL.md`). **When the user asks for users’ traces / links:** give **one permalink per user** — the **latest** `webhook.inbound` root only. **When they ask for top / busiest users over a time range:** use the **top users table** format (Msgs, User, single review link) — no per-thread “all turns” column unless they ask.

Deeply research a technology already in the stack. Pulls latest official docs, changelogs, release notes, production recipes, and pitfalls via heavy web search — then maps findings onto the exact usage pattern in this repo to surface underused features and confirm best practices. Use whenever someone asks "are we using X right?", "what's the best way to use X for Y?", or "what did X ship recently that we should adopt?"

Braintrust `bt` CLI for Ara — every agent-facing service emits spans to the `Ara` project (org `Aradotso`). Use for inspecting logs/traces/prompts/evals, authenticating, SQL over spans, and wrapping new code with tracing. For the Ara-specific span shape and debug recipes (`/trace recent`, `/trace turn`, `/trace user`, etc.) see the companion `/trace` skill.

Meta-guide to the aracli CLI (formerly `ae`) and its skill-sharing pipeline. Covers how aracli ships Claude Code skills to every teammate automatically — first-run bootstrap, live symlinks, PreToolUse/Skill hook, SessionStart hook. Use whenever you need to author a new skill, edit an existing skill, or reason about why a skill change did (or didn't) reach another user.

Self-improving skill loop. Analyzes the current conversation — what worked, what didn't — and patches ae skills accordingly. Run at the end of a session.