aie-skills-installer

To detect ML workflow skills, scan project files like pyproject.toml, requirements.txt, and notebooks to map technology signals to curated skill recommendations, ensuring each match has concrete evidence before installation.

The best way to selectively install recommended skills is to analyze the repository's dependency files and source imports, present an evidence-backed match table for user confirmation, and run install.sh to perform the validated selective installations.

Yes, you can use repository analysis for Docker-based ML projects by scanning Dockerfiles, dependency files, and notebooks to detect technology signals and recommend relevant skills like docker-gpu-setup based on concrete project evidence.

You need to confirm skill recommendations before installation to prevent unnecessary skills from being added, ensuring only evidence-backed matches relevant to your project's detected signals are selectively installed via the install.sh script.

Yes, the installer supports scanning Jupyter notebooks for technology signals alongside README files, dependency files, and source imports to build a comprehensive technology profile and recommend matching skills.

To verify selective skill installations, run install.sh after user confirmation and check the returned JSON output, which provides verification details for each selectively installed skill based on the detected repository signals.