intellectronica agent-skills
COMMUNITYLABSCO SUMMARY
The 22 span services that have nothing to do with each other: Anki flashcards, Google Workspace through the gog CLI, Notion, Todoist, Raindrop.io bookmarks, Upstash Redis, Monologue's personal notes API, web search and crawling through Tavily, YouTube transcripts, Mermaid diagram rendering, document-to-Markdown conversion via markitdown, semantic code search via mgrep, ray.so code-screenshot images, and two separate image-generation wrappers for GPT Image 1.5 and Google's Nano Banana models. A few are process helpers instead: here-be-git initialises a repository, promptify rewrites a request into a more detailed prompt, and copilot-sdk is a reference for building on the GitHub Copilot SDK across five languages.
This is for someone who already uses several of these specific tools and wants a ready skill instead of writing one against each API's docs from scratch. Use none of Notion, Todoist, Raindrop, Anki, or the image APIs, and most of the 22 simply won't come up: only three — context7, promptify and ultrathink — run on the conversation alone with nothing to configure first, and the rest split between needing an account or API key already set up and needing a local tool already installed.
READ THE FULL ANALYSIS
The readme sells something too. Above the actual skill table it promotes two paid workshops, "Mastering Agent Skills" and "Introduction to Agent Skills", hosted at the author's own agentic-ventures.com.
ALSO IN THIS PACKAGE
anki-connect
This skill is for interacting with Anki through AnkiConnect, and should be used whenever a user asks to interact with Anki, including to read or modify decks, notes, cards, models, media, or sync operations.
beautiful-mermaid
Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.
context7
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.
copilot-sdk
This skill helps with GitHub Copilot SDK work across Node.js/TypeScript, Python, Go, .NET, and Java. It covers setup, authentication, permissions, streaming events, custom tools, custom agents, MCP servers, hooks, skills, and session persistence.
gog-cli
Use this skill whenever the user wants to operate Google Workspace from the command line with gog/gogcli, including Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Apps Script, Chat, Classroom, Contacts, Tasks, People, Groups, Admin, Keep, auth, configuration, scripting, or agent-safe Google automation. Prefer this skill for Google account/file/mail/calendar work when the user mentions gog, gogcli, Google CLI, Gmail search/send, Calendar events, Drive files, Docs/Sheets/Slides editing, Forms, Apps Script, Workspace admin, or command-line Google automation.
gpt-image-1-5
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.
here-be-git
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.
lorem-ipsum
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.
markdown-converter
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.
mgrep-code-search
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.
monologue-notes-api
Use this skill when the user wants to read or search their Monologue notes through the Monologue Notes REST API. It covers authentication with the MONOLOGUE_API_KEY environment variable, safe token handling, listing notes, fetching a single note, pagination, filters, and error handling.
nano-banana-2
Generate and edit images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) API. This skill should be used when the user asks to create or modify images, especially when they need fast iteration, explicit aspect-ratio control, or resolution control from 512px to 4K.
nano-banana-pro
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images.
notion-api
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.
promptify
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.
raindrop-api
This skill provides comprehensive instructions for interacting with the Raindrop.io bookmarks service via its REST API using curl and jq. It covers authentication, CRUD operations for collections, raindrops (bookmarks), tags, highlights, filters, import/export, and backups.
ray-so-code-snippet
Generate beautiful code snippet images using ray.so. This skill should be used when the user asks to create a code image, code screenshot, code snippet image, or wants to make their code look pretty for sharing.
tavily
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.
todoist-api
This skill provides instructions for interacting with Todoist using the td CLI tool. It covers CRUD operations for tasks/projects/sections/labels/comments, and requires confirmation before destructive actions.
ultrathink
Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.
upstash-redis-kv
Read and write to Upstash Redis-compatible key-value store via REST API. Use when there is a need to save or retrieve key-value data, use Redis features (caching, counters, lists, sets, hashes, sorted sets, etc.) for the current interaction, or when the user explicitly asks to use Upstash or Redis.
youtube-transcript
Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar).
WHAT'S INSIDE
22 showing · 22 totalNothing else to set up — install it and go.
anki-connect
Anki is a flashcard app for studying; this lets you run your collection by conversation rather than by clicking, and nothing gets changed or deleted until you say yes.
beautiful-mermaid
Mermaid is a way of describing a diagram in plain text, and this turns that text into an actual picture you can drop into a document or a slide.
context7
Programming libraries change faster than an AI's memory of them, so this fetches a library's current documentation and code examples from the Context7 service before answering.
copilot-sdk
GitHub Copilot's coding agent, wired into software you are building yourself rather than used at the terminal — the same agent, reachable from Node.js, Python, Go, .NET or Java.
gog-cli
gog is a command-line tool for a Google account — mail, calendar, files, documents — which lets an assistant work on them directly, and can be restricted so it never sends or deletes anything without your say-so.
gpt-image-1-5
OpenAI's GPT Image 1.5, put behind a single command: describe a picture, or point at one you already have and say what to change, and the finished PNG lands in the folder you are working in.
here-be-git
Turns a plain folder into a git project that keeps a history of every change, then asks whether the assistant should commit your work automatically and which files to leave out.
lorem-ipsum
Lorem ipsum is the nonsense Latin filler that stands in for real words while a page is being designed; this turns out as much of it as you need, in whatever shape the mock-up calls for.
markdown-converter
Takes a file an assistant cannot read directly and turns it into plain text, keeping the headings, tables and lists so the structure survives the trip.
mgrep-code-search
Search a codebase by describing what you want in ordinary words — 'where do we check passwords?' — rather than having to guess the exact term whoever wrote it used.
monologue-notes-api
Monologue is a notes app that keeps a transcript with every note; this reaches the notes in your own account so they can be searched and read back in a conversation.
nano-banana-2
Google's Nano Banana 2 is the fast one of its image models, built for trying an idea several ways before committing; this puts it behind a single command, for new pictures and for edits to ones you already have.
nano-banana-pro
Google's Nano Banana Pro image model, one command away — give it a sentence and it paints the picture, or give it a photo and tell it what should be different.
notion-api
Notion is a workspace for notes, documents and tables; this lets an assistant work inside yours, and it asks first before changing or deleting anything.
promptify
Rewrites a rough, spoken-style request into exact, spelled-out instructions for an AI model, so it is not left guessing what you meant.
raindrop-api
Raindrop.io is a bookmarking service; this puts your saved links, folders and tags within reach of an assistant, which asks before it deletes or moves anything in bulk.
ray-so-code-snippet
Code pasted into a slide or a post looks terrible. This turns a snippet into a picture of it instead — coloured, framed, in whichever style you pick — and saves the image where you are working.
tavily
A way for an assistant with no web access of its own to go and look: search, pull the readable text out of pages you name, walk a whole site, or run a longer investigation and come back with a written answer and its sources.
todoist-api
Run your Todoist list by asking rather than clicking — add a task with its due date in one line, see what is due today, tidy up projects and labels — and it checks with you before deleting or ticking anything off.
ultrathink
Prints the word ultrathink across the terminal in big coloured block letters. That is the entire skill.
upstash-redis-kv
Somewhere to park a piece of data and pick it up later — a counter, a cached answer, a queue, a leaderboard — so what was worked out in one session is still there for the next one.
youtube-transcript
Pulls the spoken words out of a YouTube video as text you can read or search, either as flowing paragraphs or with a timestamp on every line so you can point at the moment something was said.
HOW TO GET IT
npx skills add intellectronica/agent-skillsnpx skills add intellectronica/agent-skills --skill <name> --full-depthPick the skill name from the Skills tab — each entry there installs independently.
/plugin marketplace add intellectronica/agent-skills/plugin install anki-connect@intellectronica-skills/plugin install beautiful-mermaid@intellectronica-skills/plugin install context7@intellectronica-skillsTyped inside the agent's own prompt, not in a terminal. The marketplace lists 22 plugins; three are shown. Every one installs the same way, with its own name before @intellectronica-skills.