7 plugins, each analyzed from its own files.
A skill that teaches efficient CLI-based code and file search strategies, covering ripgrep, ast-grep, fd, rga, tokei, and scc with guidance on tool selection and best practices. It provides pattern recipes and search strategies for finding text patterns and structural code matches in codebases of any size.
This skill fetches live library documentation from the Context7 REST API for 50+ popular libraries like React, Next.js, Vue, and Express, triggered by natural language queries about documentation. It provides current, topic-specific documentation without the persistent context overhead of an MCP server.
This agent fetches and retrieves documentation from Context7 for specific libraries and frameworks like React, Express.js, and MongoDB. It enables users to access accurate, up-to-date reference materials directly within their development workflow.
pg-aiguide provides AI coding assistants with curated PostgreSQL best practices through semantic search over official documentation and AI-optimized skills that improve schema quality. It works as an Agent Skill, MCP server, or Claude Code plugin to help AI tools generate more robust, performant PostgreSQL code with better constraints, indexes, and modern features.
This plugin analyzes your Claude Code chat history to identify coding patterns, development gaps, and skill areas, then generates a personalized growth report with curated learning resources from HackerNews. It works entirely with local data and requires no external API keys or third-party services.
This plugin provides 3 agents and 7 skills for research, documentation lookup, utility routing, and skill authoring, along with instruction review and agent configuration auditing capabilities. It enables developers to audit reasoning processes and review agent configurations without requiring external API keys or services.
The explore plugin helps Claude understand a topic by reading a planning document and systematically exploring related files, with a workflow of Plan, then Execute. It works better when framed as preparation for discussion rather than for specific task completion.