Intellectronica Agent Skills
Twenty-two standalone skills: Notion, Todoist, Tavily, Context7, image generation, converting documents to Markdown
- 299 ★ on the repository
- Last commit
- CC0-1.0
Broad access
Why this level
- The Notion, Todoist and Raindrop.io skills read, change and delete data in accounts on the owner's token
- The `gog-cli` skill covers Gmail, Drive, Docs, Calendar and Workspace administration, including sending mail
- Requests to Tavily, Upstash and image models go to external services together with the contents of notes and files
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/intellectronica-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The Notion, Todoist and Raindrop.io skills read, change and delete data in accounts on the owner's token
- The `gog-cli` skill covers Gmail, Drive, Docs, Calendar and Workspace administration, including sending mail
- Requests to Tavily, Upstash and image models go to external services together with the contents of notes and files
This is third-party code. Review the repository files before installing.
What it does
The intellectronica/agent-skills repository is a personal collection of 22 skills under the CC0 license, meant to be picked one at a time. Most skills connect an agent to an external service over REST or through a command-line tool: Notion, Todoist, Raindrop.io, Anki through `AnkiConnect`, Tavily search, current library documentation from Context7, keys and values in Upstash Redis, Google Workspace through `gogcli`. The media part: `gpt-image-1-5`, `nano-banana-pro` and `nano-banana-2` create and edit images with OpenAI and Google models, `ray-so-code-snippet` turns a code fragment into a picture, `beautiful-mermaid` renders Mermaid diagrams to SVG and PNG, `youtube-transcript` pulls a video's captions, and `markdown-converter` turns PDF, Word, Excel, PowerPoint and other formats into Markdown via `uvx markitdown`. The rest are small helpers: `promptify` rewrites a request into a detailed prompt, `here-be-git` sets up a git repository with agent instructions, `lorem-ipsum` outputs placeholder text, `mgrep-code-search` searches a large codebase by meaning, `copilot-sdk` advises on the GitHub Copilot SDK in five languages, `ultrathink` draws a colorful ANSI inscription.
Who it is for. People who keep tasks and notes in Notion, Todoist or Raindrop.io and want to attach separate skills to an agent instead of one big bundle.
Good fit when
- An agent must read a Notion page or add a Todoist task, and you would rather not set up an MCP server for it
- A PDF, an Excel sheet or a presentation is needed as Markdown for a model to analyse
- The model remembers an old version of a library API and you need current documentation from Context7
- A Mermaid diagram from an agent answer must become an SVG or PNG for an article
Not a fit when
- You want a ready MCP server for Notion or Google with shared authorisation: here calls go over REST and through CLI tools from the skill instructions
- You want to install all 22 skills at once: the author describes installing them one by one with the --skill flag
- Work happens without access to the OpenAI, Google and Tavily APIs: the image and search skills depend on those services' keys
Example request
Convert report.pdf to Markdown and list the second-level headingsLimitations
- The Notion, Todoist, Raindrop.io, Tavily, Upstash and Monologue skills need a token from their own service, image generation needs an OpenAI or Google key. The OpenAI and Google APIs are not directly available from Russia.
- The `gog-cli` skill manages Gmail, Drive and Calendar through `gogcli`, which must be installed and authorised separately.
- `markdown-converter` and some other skills run packages through `uvx`, so the uv manager is required.
- The repository's last commit was in April 2026.
How to disable. Remove a skill by deleting its folder from the agent's skills directory. A plugin installed through the marketplace is removed with claude plugin uninstall and a name such as markdown-converter@intellectronica-skills.
FAQ
How do I install one skill from Intellectronica Agent Skills?
With npx skills add intellectronica/agent-skills --skill `markdown-converter`, where the name after --skill is the skill you need. In Claude Code the marketplace also works: claude plugin marketplace add intellectronica/agent-skills, then claude plugin install markdown-converter@intellectronica-skills.
Which skills work without keys?
Local helpers such as `ultrathink`, `lorem-ipsum`, `here-be-git`, `promptify` and `markdown-converter` need no service token. Skills that call Notion, Todoist, Tavily, Upstash and image generation wait for a key in environment variables.
Which keys does image generation need?
`gpt-image-1-5` works with OpenAI's GPT Image 1.5, `nano-banana-pro` with Gemini 3 Pro Image, `nano-banana-2` with Gemini 3.1 Flash Image Preview, so OpenAI and Google keys are needed. `nano-banana-2` sets the aspect ratio and a resolution from 512 pixels to 4K.
What does `mgrep-code-search` do?
A natural-language query finds functions and modules by meaning. The skill is meant for repositories with more than 30 non-gitignored files or nested directories and complements grep and ripgrep.
How does the Todoist skill differ from the others in safety?
The `todoist-api` skill works through the `td` command-line tool and, by its description, requires confirmation before deleting. The Notion and Raindrop.io descriptions have no such condition, so state the confirmation in your request.
Discussion
No questions or reviews yet.
Related
Skillscafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository
A set of everyday agent skills: web search, browser automation, Gmail, Google Calendar and Drive, speech transcription and YouTube transcripts
A personal library of 25 skills: posters and storyboards, Google-style code review, lab report reading and scenario simulations
Five skills from one author: arXiv reports, technical diagrams, a report site, a design system library and agent guardrails
Seven skills for research, HTML explainers and source citation, installable all at once or one at a time through npx.
A library of more than 130 SKILL.md skills in 23 categories, from React and Kubernetes to invoices and restaurant menus
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Intellectronica Agent Skills (this card) | no | 299 | |
| AI Agent Skills | no | 1,156 | a CLI manager for installing skills; here the skills themselves, installed by the common skills tool |
| Mindrally skills collection | no | 297 | over two hundred skills with coding rules for frameworks; here twenty-two skills for external services and media |
README in short
The README names two ways to install, then gives a table of 22 skills: the name linked to its folder, a description of when the skill triggers and two ready install commands. Links to the author's training materials come before the table.
README badge
Original SKILL.md
--- name: markdown-converter description: 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. --- # Markdown Converter Convert files to Markdown using `uvx markitdown` — no installation required. ## Basic Usage ```bash # Convert to stdout uvx markitdown input.pdf # Save to file uvx markitdown input.pdf -o output.md uvx markitdown input.docx > output.md # From stdin cat input.pdf | uvx markitdown ``` ## Supported Formats - **Documents**: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls) - **Web/Data**: HTML, CSV, JSON, XML - **Media**: Images (EXIF + OCR), Audio (EXIF + transcription) - **Other**: ZIP (iterates contents), YouTube URLs, EPub ## Options ```bash -o OUTPUT # Output file -x EXTENSION # Hint file extension (for stdin) -m MIME_TYPE # Hint MIME type -c CHARSET # Hint charset (e.g., UTF-8) -d # Use Azure Document Intelligence -e ENDPOINT # Document Intelligence endpoint --use-plugins # Enable 3rd-party plugins --list-plugins # Show installed plugins ``` ## Examples