claude-code-plugins

GitLab CLI for merge requests, issues, CI/CD pipelines, repositories, and more. Use when working with GitLab to list/view MRs, check CI status, browse issues, or any GitLab API operation. Triggered by requests involving GitLab data, merge requests, CI pipelines, or GitLab project management.

Judgment rules for how to shape commits, plan branches, and respond to review — not git mechanics. Use when staging changes, writing commit messages, splitting/reordering commits, planning a branch's structure, addressing review feedback, or deciding how to merge.

This skill should be used when the user asks to "search the web", "look up online", "find recent information", "search for", "what's the latest on", or needs web search results. Provides access to a private SearXNG metasearch engine instance via the `searxng` CLI. Prefer this over WebSearch when available.

CLI for querying RabbitMQ instances (vhosts, queues, exchanges, bindings). Use when inspecting RabbitMQ, listing queues, checking exchange bindings, viewing queue details, or exploring RabbitMQ topology. Triggered by requests involving RabbitMQ data, queue inspection, exchange listing, or message broker exploration.

Use Gemini CLI in non-interactive mode for tasks requiring massive context windows (1M tokens). Best delegated to subagents for iterative analysis and summarization. Invoke when analyzing large codebases, requesting deep analysis, getting second opinions on complex problems, or when Claude's context limits are insufficient. Triggers include phrases like "use gemini", "analyze with gemini", "get second opinion", "deep analysis of codebase", or when processing files exceeding Claude's context capacity. IMPORTANT - Always delegate to a subagent using the Task tool for better iteration and result summarization.

CLI for querying Metabase (cards/questions, dashboards, collections, databases, search). Use when working with Metabase to search entities, browse collections, run saved questions, export/import dashboards, explore database metadata, or resolve Metabase URLs. Triggered by requests involving Metabase data, dashboard queries, saved questions, collection browsing, or Metabase automation.

CLI for querying Google Workspace and consumer Google services (Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, Tasks, Forms, Chat, People, Apps Script). Use when working with Google services to search email, manage calendar events, upload/download Drive files, read/write Sheets, send emails, manage contacts or tasks, or any Google API operation from the terminal. Triggered by requests involving Google data, Gmail, Google Calendar, Google Drive, Google Docs, Google Sheets, or Google Tasks.

Migrate Python projects from Poetry, pipx, or pip/requirements.txt to uv. Converts pyproject.toml from Poetry format to PEP 621 standard, handles dependency groups, scripts, extras, build backends, and generates uv.lock. Use when user asks to: (1) migrate/convert from Poetry to uv, (2) replace pipx with uv tool, (3) modernize Python project packaging, (4) convert requirements.txt to uv, (5) switch to uv, or mentions "poetry to uv" or "migrate to uv".

Conducts comprehensive, autonomous deep research on specific topics using Google's Gemini Deep Research API. Initiates long-running background research tasks that synthesize multiple sources into detailed reports. Use when users request deep analysis, comprehensive research, or multi-source synthesis on complex topics. Triggered by phrases like "research", "deep dive", "comprehensive analysis", or when simple fact lookups are insufficient.

CLI for converting files to Markdown using Microsoft's markitdown. Use when converting PDF, DOCX, PPTX, XLSX, HTML, images, audio, or other file formats to Markdown for text analysis or LLM processing. Triggered by requests involving file-to-markdown conversion, document text extraction, or preparing files for LLM input.