72 boosters for "dex" — open source, verified from GitHub, ready to install
Get Shit Done (GSD) is a meta-prompting and context engineering system that helps developers coordinate AI-assisted workflows across multiple platforms while preventing quality degradation from context window bloat. Developers building with Claude, OpenCode, Gemini, and Codex benefit from its structured Plan→Execute→Verify→Complete pipeline.
Database Optimizer is an expert agent for PostgreSQL, MySQL, Supabase, and PlanetScale that helps developers design scalable schemas, write efficient queries, and troubleshoot performance issues using EXPLAIN ANALYZE and indexing strategies. Developers building database-backed applications benefit from expert guidance on optimization without hiring a DBA.
LSP/Index Engineer orchestrates Language Server Protocol clients to build unified code intelligence systems with semantic indexing. Developers working with multi-language codebases benefit from streamlined LSP client management and cross-language code visibility.
A specialized SEO agent that helps businesses optimize their online presence for Baidu search rankings and the Chinese market ecosystem, including ICP compliance and mobile-first strategies. Ideal for marketing teams, agencies, and companies targeting Chinese audiences.
notion-meeting-intelligence helps teams prepare professional meeting materials by pulling Notion context, researching via Codex, and generating tailored agendas and pre-reads for specific attendees and meeting types. It's ideal for managers, coordinators, and team leads who need to streamline meeting prep workflows.
skill-installer automates the discovery and installation of Codex skills from curated repositories and GitHub sources, streamlining the setup process for developers building AI-assisted coding workflows.
A meta-guide that helps users create or update specialized skills to extend Codex's capabilities with domain-specific knowledge and workflows. Developers and AI agents building custom extensions benefit from this structured approach to skill development.
A skill for iteratively developing and testing web-based games in HTML/JavaScript using Playwright automation and screenshot inspection. Developers building browser games benefit from this structured test-driven development loop.
This skill enables users to generate and edit images directly within Claude Code using the OpenAI Image API, supporting use cases from product mockups to concept art. Developers and designers benefit by automating image creation workflows without leaving their coding environment.
A skill for building and scaffolding ChatGPT Apps SDK applications that combine MCP servers with widget UIs, using a docs-first workflow. Developers building ChatGPT extensions and integrations benefit from structured guidance on tool design, UI registration, and SDK compliance.
Create a real CLI that future Codex threads can run by command name from any working directory. This skill is for durable tools, not one-off scripts. If a short script in the current repo solves the task, write the script there instead. Name the target tool, its source, and the first real jobs it sh
This skill automates the process of adding, extracting, and managing evaluation results in Hugging Face model cards, supporting multiple data sources including Artificial Analysis API and custom evaluations with vLLM/lighteval. It's valuable for ML practitioners and model maintainers who need to track and display model performance metrics.
"name": "understand-anything", "description": "AI-powered codebase understanding — analyze, visualize, and explain any project", "homepage": "https://github.com/Lum1104/Understand-Anything",
Context Mode is an MCP server that dramatically reduces Claude's context window consumption through sandboxed code execution and intelligent full-text search, enabling developers to work with larger codebases and knowledge bases without hitting token limits.
A Bash CLI wrapper for the EODHD financial data API designed for OpenClaw agents, with built-in secrets management and secure deployment practices. Useful for developers building open-source integrations that need stateless API access without credential exposure.
Openmemory JS is a local persistent memory store for LLM applications that enables long-term context retention across Claude Desktop, GitHub Copilot, and other AI platforms. Developers building AI agents and applications benefit from enhanced memory management without external dependencies.
Claude Code Workflow is a JSON-driven multi-agent development framework that orchestrates AI-powered CLI workflows across multiple LLM providers (Gemini, Qwen, Codex) for automated code development tasks. It benefits developers and teams seeking to automate complex development workflows with intelligent context management and multi-agent coordination.
"name": "hamel-review", "name": "Hamel Husain" "description": "Automated code review loop plugin for Claude Code"
wraps your coding agent (Claude Code, Codex, OpenCode) in composable workflows: review loops, repeat passes, parallel races, and task-list orchestration. Operators compose left to right. Loop operators wrap everything to their left. Custom review/gate prompts (positional shorthand):
"description": "Open-source cross-agent memory layer for coding agents across Cursor, Claude Code, Codex, Windsurf, Gemini CLI, Copilot, Kiro, OpenCode, Antigravity, and Trae via MCP.", "sideEffects": false, "memorix": "./dist/cli/index.js"
Blazing fast Rust CLI tool that turns 55+ websites into CLI interfaces, reusing Chrome's login state. Zero credentials needed. Single 4.7MB binary, zero runtime dependencies. 1. 账号安全：自动化行为可能触发平台风控 3. 最佳实践：执行前向用户展示将发布的内容，等待确认
Provides complete specifications and role templates for 37 specialized agent types in a dynamic multi-agent system, enabling developers to build scalable, parallel AI workflows. Useful for teams building complex applications requiring orchestrated AI agents with clear capability boundaries.
Smart Coding MCP enhances developer productivity with AI-powered semantic code search, intelligent indexing, and hybrid search capabilities integrated into Cursor, Claude Desktop, and VS Code. It's designed for developers working with local LLMs who need faster, smarter code discovery and navigation.
Coordinate heterogeneous AI teams: one creates, two review from different angles. Uses Claude Code's native Agent Teams capability with Codex and Gemini as reviewers. Different AI models have fundamentally different review tendencies. They don't just find different bugs — they look at completely dif
