5,123 boosters — open source, verified from GitHub, ready to install
An agent that automates end-to-end testing tasks with library-first constraints, helping teams execute comprehensive test scenarios while reusing existing components and patterns. Useful for QA engineers and developers integrating testing into their Claude-powered workflows.
An agent that audits codebases for technical debt by enforcing library-first development practices and checking against existing components and patterns. Useful for teams managing code quality and reducing duplication across projects.
A technical-debt-manager agent that helps teams identify, track, and manage technical debt across projects using library-first principles and reusable patterns. Developers working in Claude Code or Claude Desktop environments benefit from automated technical debt assessment and refactoring guidance.
A Claude agent specialist designed to assist with stakeholder communication tasks across enterprise projects. Helps teams manage and streamline interactions with multiple stakeholders using library-first patterns and reusable components.
"name": "breaking-coding-chaos", "description": "Human-in-the-loop dual-loop skills: throughline, plan-spar, clean-cut", "description": "BCC — ship ideas with agents under a dual control loop",
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.
A Claude agent designed to facilitate database migrations across projects by automating code search, adaptation, and execution tasks. Developers managing schema changes and data transfers benefit from its library-first approach and integrated bash capabilities.
A Claude agent specialized in market research tasks that operates under library-first constraints to reuse and adapt existing components. Useful for business analysts and product teams needing automated market analysis capabilities.
"name": "quantum-loop", "description": "Universal CLI orchestrator with multi-runner support. Autonomous spec-driven development with dependency DAG, parallel worktree execution, two-stage review gates, and modular merge hardening.", "name": "andyzengmath"
An agent that generates architecture diagrams by leveraging Claude's code execution capabilities and a library-first approach to reuse existing components and patterns. Useful for developers and architects who need to quickly create system architecture visualizations.
"description": "Skills for configuring and using hologit", "name": "Jarvus Innovations", "email": "hello@jarv.us"
The apache-camel-integrator agent helps developers integrate Apache Camel-based enterprise integration patterns into their projects by enforcing library-first constraints and reusing existing components. It benefits teams building microservices and event-driven architectures who need standardized integration workflows.
An agent that helps developers design and manage API versioning strategies using library-first principles and reusable patterns. Teams building multi-version APIs benefit from structured guidance on compatibility and migration planning.
"name": "it-tools-mcp", "version": "5.10.6", "description": "MCP-compliant server access to over 100 IT tools and utilities commonly used by developers, system administrators, and IT professionals.",
"description": "Code-grounded Agent Skills for building with Pi (pi-mono). Covers all 7 packages: pi coding agent (workspace, extensions, packages, RPC/SDK, customization), pi-ai (multi-provider LLM API), pi-agent-core (agent runtime), pi-tui (terminal UI), pi-web-ui (web components), pi-mom (Slack
Boris is a master orchestrator agent that coordinates Claude Code workflows by delegating to specialists, managing verification loops, and ensuring quality output. It's ideal for developers who want a structured, systematic approach to complex software projects.
An agent designed to evaluate other agents and tasks, with library-first constraints and multi-tool integration across Claude platforms. Useful for teams building quality assurance workflows into their Claude-based systems.
Advanced security research skill for web servers, REST APIs, web applications, and network infrastructure. Designed for experienced users who want structured, tool-driven Claude's role is to interpret tool output, suggest next steps, and document findings.
This sub-skill generates a complete email marketing strategy tailored to your business type, including: Invoked by from the main email skill. First, check if exists and contains business type. If not, analyze context signals:
STOP! Before writing ANY code or suggesting ANY changes: 2. 📝 DOCUMENT FINDINGS: 3. ✋ WAIT FOR APPROVAL:
"description": "Zeabur CLI skills for deployment, template management, and troubleshooting", "version": "1.16.1", "repository": "https://github.com/zeabur/zeabur-claude-plugin",
"name": "secondme-skills", "description": "SecondMe 技能包 — 通过 Agent 使用 SecondMe（登录、资料、Plaza、Discover、Key Memory）并辅助开发第三方应用和集成", "name": "mindverse",
Cursor Rules for FastLED WASM provides critical development guidelines enforcing `uv` for Python execution and safe emoji handling to ensure consistent builds and cross-platform compatibility. Developers working on the FastLED web compiler project benefit from clear, actionable rules that prevent common errors.
Reviews email content before sending and provides a comprehensive quality score (0-100) across 5 weighted dimensions. Identifies critical issues, suggests improvements, and provides a rewritten version for low-scoring emails. Accept email content in any of these formats: 1. Pasted text - Subject lin
