431 boosters for "lit" — open source, verified from GitHub, ready to install
"name": "takahirom-claude-code-marketplace", "name": "claude-code-quality-gate", "source": "./plugins/claude-code-quality-gate",
"description": "127-agent automated development system with Agent Teams, quality gates, Bug Council diagnostics, and autonomous execution", "name": "Multi-Agent Development Team" "homepage": "https://github.com/michael-harris/devteam",
Guides developers in creating well-structured, efficient Claude skills with proper naming conventions, progressive disclosure, and model-specific testing. Ideal for skill authors and teams building Claude integrations.
"id": "ai.haymon/database", "description": "Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite", "url": "https://github.com/haymon-ai/database",
"name": "open-academic-paper-machine", "description": "Open Academic Paper Machine — Autonomous academic paper production system with idea evaluation gate and paper-vs-code audit. NEW in v6.4: /audit-paper command and audit-engine skill — static audit of a paper's empirical claims (datasets, models,
"name": "agent-recorder", "description": "Local-first flight recorder for Claude Code - captures MCP tool calls, subagents, and skills without recording prompts or chain-of-thought", "name": "Edyta Kucharska"
Local Voice MCP enables Claude Desktop and Claude Code to generate speech using local text-to-speech models, allowing developers to add voice capabilities without external API dependencies. This benefits developers building voice-enabled AI applications who need privacy-preserving, self-hosted speech synthesis.
"name": "cadre-devkit-claude", "description": "Cadre team development kit for Claude Code - security hooks, workflow automation, and productivity tools", "name": "Cadre Team"
"name": "claude-rock", "id": "claude-rock", "name": "Truong Vu",
This skill enables Claude to search a user's local Zotero library and discover related papers via Semantic Scholar, ideal for researchers and academics managing literature collections. It requires a local Zotero instance and works exclusively in Claude Code environments.
Hyperstaker-ui Cursor Rules is a comprehensive set of development guidelines for building the Hyperstaker platform, enforcing standards across TypeScript, Next.js 14, React 18, and Web3 libraries (Wagmi, Viem) to ensure consistent, performant code.
"name": "codereview", "description": "Comprehensive code review skills with an orchestrator for triage/routing and 11 specialist sub-skills for security, correctness, API, data, concurrency, performance, observability, testing, style, and configuration analysis.", "name": "Zainan Victor Zhou",
"name": "design-engineering", "description": "Design engineering for AI agents — animation timing, transitions, typography, color, components, layout, accessibility, anti-patterns. Plus a SOUL.md identity layer and six workflow subagents (ui-reviewer, motion-auditor, anti-pattern-scanner, agentation
A migration guide for transitioning from deprecated hardcoded agents to a dynamic ConfigurableAgent system in a Rust-based agentic chatbot server. Developers maintaining or upgrading agent-based systems benefit from clear configuration patterns and best practices for multi-provider LLM setups.
"name": "brainlayer", "name": "Etan Heyman", "url": "https://github.com/EtanHey"
"description": "Dogdoing (刀盾狗/我的刀盾) - A loyal shield-dog that participates in every task, splitting work as a subagent. Cheers with Wow-wow-wow when idle! | 一只永远不会缺席的工作犬，每个任务都插上一爪，没活就旺旺旺喝彩！", "repository": "https://github.com/hellowind777/dogdoing", "keywords": ["dogdoing", "shield-dog", "刀盾狗", "我的刀
"name": "kkweon-blog-tools", "description": "Custom utilities for blog post development and optimization",
"name": "wicked-garden", "description": "AI-Native SDLC \u2014 the complete software development lifecycle as a single Claude Code plugin. 14 domains covering code intelligence, delivery metrics, persistent memory, workflow orchestration, brainstorming, on-demand personas, and 80 specialist agents a
Quinn is a technical product management agent that automates progress monitoring, work validation, and proactive status reporting to keep stakeholders informed without manual requests. Teams building multi-agent systems benefit from delegating coordination and quality oversight tasks.
Heuristic scoring (no AI key configured).
WPT-diff is intended as a web-platform-tests runner for testing API interceptor compatibility, though the booster itself appears to be a legal warning rather than functional prompt content.
A lightweight, open-source WYSIWYG web editor designed for Windsurf that enables developers to quickly add rich text editing capabilities to their projects with customizable formatting tools, keyboard shortcuts, and modular architecture.
This booster lets developers quickly swap their OpenCLAW agent's personality by selecting pre-built characters from the G*BOY universe, complete with customizable tone, values, and visual avatars. It's useful for teams wanting to experiment with different agent personas without manual configuration.
Editor is an AI writing coach that transforms rough drafts into polished content by optimizing clarity, readability, and voice consistency. Ideal for content creators, marketers, and developers who need to elevate their written output.
