4,240 boosters — open source, verified from GitHub, ready to install
You are the CODER - the implementation specialist who turns requirements into working code. Take a SINGLE, SPECIFIC todo item and implement it COMPLETELY and CORRECTLY. 1. Understand the Task
Search academic papers via the Semantic Scholar API using a structured 4-phase workflow. Parse the user's intent and choose a search strategy: Write ONE Python script. Example:
Automatically inserts checkpoint calls into jamovi R functions to enable incremental result rendering and change detection during long computations. Useful for jamovi module developers seeking to improve user experience with progress visibility.
This booster automates Git commits and pushes following Conventional Commits standards and project CONTRIBUTING.md guidelines. It helps developers maintain consistent commit messages and workflow compliance across projects.
The implement booster activates specialized AI personas (architect, frontend, backend, security, QA) to coordinate feature and code implementation with framework-specific best practices and MCP tool integration. It's designed for developers needing structured, multi-domain implementation workflows in Claude Code.
A Claude Code skill that executes simple tasks directly without agent planning overhead, ideal for quick bug fixes and single-file changes. Developers benefit from faster execution for straightforward coding work.
"name": "norman-finance", "description": "AI-powered bookkeeping and tax filing automation for entrepreneurs at the heart of the European economy. Connect to Norman to manage clients, invoices, transactions, taxes, and documents.", "name": "Norman Finance",
Reference documentation for building Prismatic custom components. Do NOT use these MCP tools — they return incomplete data that causes broken scaffolds and missing connections downstream. A hook will deny them, but avoid the wasted round trip. Components define their own inputs — not wrappers. Each
You are the TESTER - the visual QA specialist who SEES and VERIFIES implementations using Playwright MCP. Test implementations by ACTUALLY RENDERING AND VIEWING them using Playwright MCP - not just checking code! 1. Understand What Was Built
"version": "0.1.68", "description": "Agent work marketplace — train your agent, let it work for others", "url": "https://github.com/lhead/akemon"
You are the STUCK AGENT - the MANDATORY human escalation point for the entire system. You are the ONLY agent authorized to use AskUserQuestion. When ANY other agent encounters ANY problem, they MUST invoke you. You are invoked when:
Search and retrieve Prismatic product documentation and code examples to answer conceptual questions, explain features, and provide best-practice guidance. Prismatic docs pages serve clean markdown by appending to the URL path: The version strips HTML/CSS/JS, returning clean content ideal for LLM
Heuristic scoring (no AI key configured).
Generates eye-catching infographic series for Xiaohongshu (Little Red Book) by converting content into 1-10 cartoon-style visuals with customizable styles and layouts. Ideal for content creators, marketers, and social media managers targeting Chinese audiences.
Reference documentation for building Prismatic Code Native Integrations (CNI). Do NOT use these MCP tools — they return incomplete data that causes broken scaffolds and missing connections downstream. A hook will deny them, but avoid the wasted round trip. All components are accessed via manifests:
A code audit specialist agent that enforces library-first development by checking existing components and patterns before writing new code, helping teams reduce duplication and maintain consistency across projects.
sparc-coordinator is an agent designed to enforce library-first development practices by checking existing components and patterns before writing new code. It benefits teams seeking to reduce code duplication and maintain consistency across projects.
A load-balancer agent that distributes agent tasks across multiple workers using library-first design patterns. Useful for operations teams optimizing task distribution and resource allocation in multi-agent systems.
Spotdb is an ephemeral data sandbox for AI workflows that provides secure, isolated database environments for agentic AI systems. It's useful for developers building AI agents and LLM applications that need safe data isolation and guardrails.
A specialized Python code cleaning agent that refactors verbose code by removing unnecessary comments, applying DRY principles, adding professional docstrings, and modernizing to current Python standards. Ideal for developers inheriting legacy codebases or standardizing team code quality.
A React Native mobile development agent that enforces library-first practices by checking component catalogs and patterns before writing code. Useful for teams wanting to standardize code reuse and maintain consistency across React Native projects.
A Claude agent designed to guide ML model training workflows with library-first principles, helping developers reuse existing components and patterns. Useful for teams building AI/ML solutions who want standardized, reusable training processes.
An ethics-focused agent designed for research tasks that enforces library-first development patterns and component reuse across Claude projects.
An agent designed to manage AI/ML experiment tracking workflows with library-first architecture patterns. Useful for teams standardizing experiment management across projects while enforcing code reuse.
