intellectronica/agent-skills▌

Render Mermaid diagrams as SVG and PNG images with theme customization. \n \n Supports five diagram types: flowchart, sequence, state, class, and entity-relationship diagrams \n Produces both vector SVG (scalable) and high-resolution PNG (4K viewport) outputs in a single workflow \n Includes 13 built-in themes (default, Dracula, Tokyo Night, Nord, GitHub, Catppuccin, Solarized, One Dark, Zinc Dark) \n Requires agent-browser skill for PNG capture; uses Bun, Node, or Deno for SVG rendering \n Prov

Text-to-image generation and image-to-image editing via Google's Gemini 3 Pro Image API. \n \n Supports both new image generation from text prompts and editing of existing images with instruction-based modifications \n Configurable output resolution: 1K (default), 2K, or 4K for high-resolution results \n Automatically detects API key from --api-key argument or GEMINI_API_KEY environment variable \n Saves PNG output to the user's current working directory with timestamped filenames \n

Comprehensive REST API reference for reading, creating, updating, and deleting Notion content. \n \n Covers all core endpoints: pages, blocks, databases, data sources, users, and comments with curl examples and required headers \n Includes authentication via API key, rate limiting (3 req/sec average), request size limits, and pagination patterns \n Provides error handling reference (400, 401, 403, 404, 429, 500+ status codes) and exponential backoff strategy for rate limits \n Requires confirmat

Displays colorful ANSI art of the word \"ultrathink\" in the terminal. \n \n Renders a large, multi-colored ASCII art banner using ANSI escape codes with cycling rainbow colors \n Triggered when the user says \"ultrathink\" or invokes the /ultrathink command \n Produces clean output with no additional text or commentary \n

Retrieve current documentation for software libraries and frameworks via the Context7 API. \n \n Two-step workflow: search for a library by name and topic, then fetch documentation using the returned library ID \n Supports documentation retrieval across hundreds of libraries (React, Next.js, FastAPI, Axios, and others) with plain-text or JSON response formats \n Query parameters accept specific topics for relevance ranking; results include library descriptions and snippet counts \n No API key re

A fast, script-friendly CLI for Google Workspace services with JSON-first output and multi-account support.

Convert documents, spreadsheets, presentations, images, audio, and web content to Markdown for LLM processing. \n \n Supports 15+ formats including PDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, images with OCR, audio with transcription, ZIP archives, YouTube URLs, and EPub \n Preserves document structure including headings, tables, lists, and links in the converted Markdown output \n Optional Azure Document Intelligence integration ( -d flag) for improved extraction on complex or scanned P

Provide a curl-based interface to Tavily’s REST API for web search, extraction, mapping, crawling, and optional research. Return structured results suitable for LLM workflows and multi-step investigations.

Generate beautiful code snippet images using ray.so and save them locally.

This skill enables interaction with the Raindrop.io bookmarks service through its REST API. Use curl and jq for direct REST calls.

Enable reliable interaction with Anki through the AnkiConnect local HTTP API. Use this skill to translate user requests into AnkiConnect actions, craft JSON requests, run them via curl/jq (or equivalent tools), and interpret results safely.

Transform user requests into detailed, precise prompts optimised for AI model consumption.

mgrep is a semantic search tool that enables natural language queries across code, text, PDFs, and images. It is particularly effective for exploring larger or complex codebases where traditional pattern matching falls short.

Extract transcripts from YouTube videos with optional timestamps. \n \n Accepts multiple URL formats (youtube.com/watch?v=, youtu.be/, embed links, or raw video IDs) and outputs plain text or timestamped format \n Fetches auto-generated or manually added captions, whichever is available; requires captions to be enabled on the video \n Outputs to a file named VIDEO_ID-transcript.txt by default, or to a user-specified file path \n When timestamps are omitted, reorganizes caption segments into comp

Initialise a git repository with optional configuration for agent workflows.

The GitHub Copilot SDK is a multi-platform agent runtime that embeds Copilot's agentic workflows into applications. It exposes the same engine behind Copilot CLI, enabling programmatic invocation without requiring custom orchestration development.

Generate new images or edit existing ones using OpenAI's GPT Image 1.5 model.

Procedural guidance for Todoist task management via the td CLI tool. \n \n Supports full CRUD operations on tasks, projects, sections, labels, and comments with natural language quick-add parsing (e.g., td add \"Buy milk tomorrow p1 #Shopping\" ) \n Requires user confirmation before destructive actions (delete, complete, update, archive); read-only operations execute directly \n Provides filtering by project, label, priority, due date, assignee, and custom Todoist queries; output as JSON, newlin

Generate lorem ipsum placeholder text using the bundled generator script. Always use the script to generate content rather than writing lorem ipsum directly.

Generate new images or edit existing images with Nano Banana 2 (gemini-3.1-flash-image-preview).