Enhance AI Agent Skill Import Options (GitHub URL, Zip Size, Binary)

Feature Requests
1

Enhance AI Agent Skill Import Options (GitHub URL, Zip Size, Binary)

What’s the feature?

Please expand the options for importing new skills to AI Agents. Currently, I face three specific blockers when trying to import NotebookLM-related skills (URL: GitHub - teng-lin/notebooklm-py: Unofficial Python API and agentic skill for Google NotebookLM. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw. · GitHub).
To make the system more flexible, I request any of the following improvements:

  1. Support standard GitHub .git URL formats.
  2. Increase the ZIP file upload limit to at least 15MB (currently failing at 13MB+).
  3. Allow the import of skills containing binary data without throwing errors.

Your use case

I want to add advanced external skills (such as NotebookLM integration) to my Teable AI Agent to expand its capabilities. Allowing these import formats will enable users to easily deploy complex Python-based skills from GitHub or local packages.

2

Hi @Yuichi ,

Thanks for sharing the details.

For the GitHub URL, please remove the trailing .git and use the standard repository URL instead:

For this specific NotebookLM skill, the main limitation is not the repository URL format. It relies on a CLI login state and authentication credentials that may not persist reliably in a cloud-based agent runtime, so it is generally better suited to a locally running agent.

The current Skill ZIP upload limit is 5 MB, which we consider sufficient for lightweight Skill instructions and scripts. Larger dependencies should generally be installed at runtime rather than included in the uploaded package. Please continue sharing other cases that genuinely require a larger upload, and we’ll evaluate whether the current limit remains appropriate.

We also do not plan to allow executable binaries, native binaries, or precompiled dependencies at this stage due to security risks.