Skills by intellectronica

Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.

Generates and edits images using Google's Nano Banana Pro via the `scripts/generate_image.py` script and the `google.genai` client. The skill reads the `GEMINI_API_KEY` env var and instructs running `~/.claude/skills/nano-banana-pro/scripts/generate_image.py`, which will make network calls to `gemini-3-pro-image-preview`.

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.

This skill extracts YouTube captions using `scripts/get_transcript.py` and the `youtube-transcript-api`. It instructs running `uv run scripts/get_transcript.py "VIDEO_URL_OR_ID"` and will contact `youtube.com` (e.g., `https://www.youtube.com/watch?v=VIDEO_ID`) to fetch transcripts.

Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.

This skill provides comprehensive instructions for interacting with the Notion API via REST calls. This skill should be used whenever the user asks to interact with Notion, including reading, creating, updating, or deleting pages, databases, blocks, comments, or any other Notion content. The skill covers authentication, all available endpoints, pagination, error handling, and best practices.

Semantic code search using mgrep for efficient codebase exploration. This skill should be used when searching or exploring codebases with more than 30 non-gitignored files and/or nested directory structures. It provides natural language semantic search that complements traditional grep/ripgrep for finding features, understanding intent, and exploring unfamiliar code.

Transform user requests into detailed, precise prompts for AI models. Use when users say "promptify", "promptify this", or explicitly request prompt engineering or improvement of their request for better AI responses.

Use this skill for web search, extraction, mapping, crawling, and research via Tavily’s REST API when web searches are needed and no built-in tool is available, or when Tavily’s LLM-friendly format is beneficial.

Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.

Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.

Dangerous skill: Documents the GitHub Copilot SDK for building agents but permits powerful operations. It exposes `execute` shell commands, writes to `~/.copilot/` and `.github/agents/`, and references env vars such as `$COPILOT_MCP_API_KEY` and `tools: ["*"]`.

This skill provides guidance for interacting with Todoist via the `td` CLI and direct API calls. It instructs executing `td` commands and `curl` requests to `https://api.todoist.com/api/v1/...` using the `$TODOIST_API_TOKEN`, which entails shell execution, credential use, and external network access.

This skill enables interaction with Anki via the AnkiConnect local HTTP API to read and modify decks, notes, cards, models, media, and perform syncs. It includes explicit shell command examples using `jq` and `curl` that call `http://127.0.0.1:8765`, i.e., it instructs executing shell commands.

Initialise a git repository with optional agent commit instructions and .gitignore. Use when users say "here be git", "init git", "initialise git", or otherwise indicate they want to set up version control in the current directory.

This skill builds a `https://ray.so/#...` URL and uses `agent-browser` plus shell commands to render and save code-snippet images to the current directory. It runs shell commands (`which`, `curl`, `agent-browser --session ... eval`, `base64`, `python3`) and loads remote scripts from `https://cdn.jsdelivr.net/npm/html-to-image@1.11.11/dist/html-to-image.js`.

Generate lorem ipsum placeholder text. This skill should be used when users ask to generate lorem ipsum content, placeholder text, dummy text, or filler text. Supports various structures including plain paragraphs, headings with sections, lists, and continuous text. Output can be saved to a file or used directly as requested by the user.

This skill provides comprehensive instructions for using gogcli (gog), a fast, script-friendly CLI for Google Workspace services including Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, Classroom, Contacts, Tasks, People, Groups, and Keep. This skill should be used when the user wants to interact with Google services via the command line, including reading/sending email, managing calendar events, working with Google Drive files, managing classroom courses, or any other Google Workspace operations. The skill assumes gog is installed and authorised.