claude-code
Production workflows for frontend, backend, code analysis, and review
All Skills in This Repository (27)
Pure Emerald Level Indicatorsrelease
Coordinate plugin version bumps, marketplace.json updates, and git tagging.
Claudish Integration Skill
Query Claudish for OpenRouter model recommendations in JSON.
claudish-usage
Routes Cubist CLI tasks through sub-agents to prevent context window pollution.
tester-detective
Audit test coverage in TypeScript/JavaScript codebases using AST callers analysis.
claudemem-search
Analyze codebases with tree-sitter AST parsing and PageRank symbol ranking.
search-interceptor
Intercept bulk file operations to recommend semantic search before execution.
debugger-detective
Trace AST call chains to locate root causes of code defects.
developer-detective
Traces data flow and function call relationships via AST analysis to locate implementations and assess impacts.
architect-detective
Analyze codebases with AST analysis and PageRank to map architectural layers.
code-search-selector
Apply semantic search before reading files during codebase audits.
ultrathink-detective
Audit codebases via AST commands to reveal architecture, implementation, and testing health issues.
cross-plugin-detective
Map agent roles to detective skills across plugins using claudemem search.
Frequently Asked Questions
FAQPage SchemaHow to install MAG Claude Plugins?βΌ
Run `npx skills add MadAppGang/claude-code --all -g -y` in your terminal to install all plugins and skills globally.
What plugins are included in this marketplace?βΌ
It includes plugins for frontend React development, Bun backend APIs, semantic code analysis, multi-agent orchestration, SEO, video editing, image generation, and a universal dev assistant with 46 skills.
How does semantic code search work here?βΌ
The code-analysis plugin uses claudemem to index your codebase with AST parsing and PageRank ranking, letting the agent find implementations, trace callers, and detect test gaps without reading every file.
Can it review code with multiple models?βΌ
Yes. The orchestration and frontend plugins run parallel reviews using external models like Grok, GPT-5, and Gemini via OpenRouter, then consolidate findings into a single consensus report.
Do I need coding experience to use these plugins?βΌ
Basic development knowledge helps since these target real codebases, but the agents handle implementation details, validation, and testing automatically from plain-English feature requests.
Related Repositories in Software Engineering
View All in Software Engineeringβopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core