Sandbox configuration
QUICKSTART
A sandbox configuration for cloudflare workflows.
cloudflare1 file · MIT
AI Plugins
Claude Code agents, commands, MCP configs and hooks. Formats vary—not every entry is a native plugin.
Community source · Runtime untested. Licenses are included. Review scripts and hooks before installing; integrations may need your own keys or paid services. Browsing does not install or run tools.
Claude Code Templates ↗1,034 components · page 25 of 35
Project template
Rails App
Rails-App with Ruby
frameworks2 files · MIT
Agent
Rails Expert
Use when building or modernizing Rails applications requiring full-stack development, Hotwire reactivity, real-time features, or Rails-idiomatic patterns for maximum productivity. Specifically:\n\n \nContext: Building a new Rails 8.1 SaaS application from scratch with real-time notifications, multi-tenancy, and maximum developer velocity\nuser: "Create a new Rails 8.1 SaaS platform for collaborative project management. Need multi-tenant architecture, real-time collaboration via Hotwire/Turbo, ba
programming languages1 file · MIT
MCP configuration
Railway
Railway MCP server provides seamless integration with Railway's deployment platform, enabling Claude to manage projects, deployments, and infrastructure directly from the CLI.
devtools1 file · MIT
Project template
React App
React-App with Javascript-Typescript
frameworks6 files · MIT
Agent
React Performance Optimization
React performance optimization specialist. Use PROACTIVELY for identifying and fixing performance bottlenecks, bundle optimization, rendering optimization, and memory leak resolution.
performance testing1 file · MIT
Agent
React Performance Optimizer
Specialist in React performance patterns, bundle optimization, and Core Web Vitals. Use PROACTIVELY for React app performance tuning, rendering optimization, and production performance monitoring.
web tools1 file · MIT
Agent
React Specialist
Use when optimizing existing React applications for performance, implementing advanced React 19+ features, or solving complex state management and architectural challenges within React codebases. Specifically: Context: Production React app experiencing performance degradation with 8 custom hooks per component, large bundle size, and memory leaks user: "Our React dashboard is slow. Components re-render constantly, bundle is 850KB, and we have memory issues. Using 8 custom hooks in some places. Ho
programming languages1 file · MIT
Agent
Read Only Auditor
Use this agent when you need a security audit that is guaranteed to make no changes to the codebase. This agent has hooks in its frontmatter that block all Write, Edit, and Bash tool calls for the duration of the audit — enforcing read-only mode at the hook level, not just by convention. Invoke for compliance reviews, pre-merge audits, or any situation where auditability and non-interference are required. Context: A compliance officer needs a security review of payment processing code without an
security1 file · MIT
Settings
Read Only Mode
Restrict Claude to read-only operations for code review and analysis. Prevents any file modifications or command executions, making it safe for exploring unfamiliar codebases or conducting security audits.
permissions1 file · MIT
Agent
README
A agent for programming-languages workflows.
programming languages1 file · MIT
Sandbox configuration
README
A sandbox configuration for cloudflare workflows.
cloudflare1 file · MIT
Sandbox configuration
README
A sandbox configuration for docker workflows.
docker1 file · MIT
MCP configuration
Redis
Official Redis MCP Server providing natural language interface for Redis databases. Query, manage, and interact with Redis data through Claude.
database1 file · MIT
Command
Refactor Code
A command for utilities workflows.
utilities1 file · MIT
Agent
Refactoring Specialist
Use when you need to transform poorly structured, complex, or duplicated code into clean, maintainable systems while preserving all existing behavior. Specifically:\n\n \nContext: A codebase has methods exceeding 200 lines, deeply nested conditionals, and 15% code duplication across similar functions.\nuser: "Help me refactor this legacy payment processing module. The methods are too long and the logic is hard to follow."\nassistant: "I'll analyze the code for smells like long methods and duplic
development tools1 file · MIT
Agent
Refine Issue
Refine the requirement or issue with Acceptance Criteria, Technical Considerations, Edge Cases, and NFRs
expert advisors1 file · MIT
Command
Regression Triage
Triage a regression by comparing the failing path against the last known good commit
testing1 file · MIT
Command
Release
Create a new Git Flow release branch from develop with version bumping and changelog generation
git1 file · MIT
Command
Release
Prepare and execute project release with version management and changelog updates
project management1 file · MIT
Command
Remove
A command for orchestration workflows.
orchestration1 file · MIT
Workflow
Repo Cleanup Loop
Recovers valuable unmerged work and prunes stale branches and PRs until the repository is tidy.
engineering1 file · MIT
Agent
Repo Publication Auditor
Use this agent before a repository becomes public — a first release, an internal project being open-sourced, or a private repo about to be flipped. It audits what publication actually exposes: the full commit history rather than the working tree, the author email on every commit, credential shapes that trip GitHub push protection and vendor partner scanning, machine-specific paths, files committed before .gitignore covered them, and README claims that do not reproduce from a clean clone. Distinc
security1 file · MIT
Command
Report
A command for orchestration workflows.
orchestration1 file · MIT
Agent
Report Generator
Use this agent when you need to transform synthesized research findings into a comprehensive, well-structured final report. This agent excels at creating readable narratives from complex research data, organizing content logically, and ensuring proper citation formatting. It should be used after research has been completed and findings have been synthesized, as the final step in the research process. Examples: Context: The user has completed research on climate change impacts and needs a final r
deep research team1 file · MIT
Agent
Research Analyst
Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting. Specifically:\n\n \nContext: A company is planning to enter a new technology market and needs deep research on market size, competitors, technologies, and growth trends.\nuser: "Research the current state of the AI-assisted code generation market. We need to understand market size, key competitors, technology trends, growth
deep research team1 file · MIT
Agent
Research Brief Generator
Use this agent when you need to transform a user's research query into a structured, actionable research brief that will guide subsequent research activities. This agent takes clarified queries and converts them into comprehensive research plans with specific questions, keywords, source preferences, and success criteria. Context: The user has asked a research question that needs to be structured into a formal research brief.\nuser: "I want to understand the impact of AI on healthcare diagnostics
deep research team1 file · MIT
Agent
Research Coordinator
Use this agent when you need to strategically plan and coordinate complex research tasks across multiple specialist researchers. This agent analyzes research requirements, allocates tasks to appropriate specialists, and defines iteration strategies for comprehensive coverage. Context: The user has asked for a comprehensive analysis of quantum computing applications in healthcare. user: "I need a thorough research report on how quantum computing is being applied in healthcare, including current i
deep research team1 file · MIT
Agent
Research Orchestrator
Use this agent when you need to coordinate a comprehensive research project that requires multiple specialized agents working in sequence. This agent manages the entire research workflow from initial query clarification through final report generation. Context: User wants to conduct thorough research on a complex topic. user: "I need to research the impact of quantum computing on cryptography" assistant: "I'll use the research-orchestrator agent to coordinate a comprehensive research project on
deep research team1 file · MIT
Agent
Research Synthesizer
Use this agent when you need to consolidate and synthesize findings from multiple research sources or specialist researchers into a unified, comprehensive analysis. This agent excels at merging diverse perspectives, identifying patterns across sources, highlighting contradictions, and creating structured insights that preserve the complexity and nuance of the original research while making it more accessible and actionable. Context: The research-orchestrator has completed Phase 4 parallel resear
deep research team1 file · MIT
Choose the files that fit your workflow
Skills package reusable instructions with supporting resources. Agents describe a specialist role, commands define a repeatable request, and MCP configurations connect a compatible client to an external service. Hooks and settings change project behavior. Inspect the actual format before adding it to your project; this catalog does not imply compatibility with every AI assistant.
Downloads preserve the original source and license notices. Keep those notices when adapting a bundle. Use source control to review changes, keep credentials outside the downloaded files, and test in a disposable project before enabling hooks or external services.