claude-ml-intern-skill
Autonomous ML research, training, verification, and Hub publishing
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install claude-ml-intern-skill?โผ
Run `npx skills add AlexWortega/claude-ml-intern-skill --all -g -y` in your terminal to install the skill globally.
What does ml-intern actually do?โผ
It takes a single ML instruction, then autonomously researches the paper, writes the code, trains the model, verifies the results, and publishes the checkpoint to Hugging Face.
How does it avoid fake training results?โผ
Every run must pass six self-verification checks, including generation sanity and loss plausibility, so a low loss number alone never counts as success.
Does it work with agents other than Claude Code?โผ
Yes. It also installs into OpenAI Codex CLI, and any agent that can read the SKILL.md instructions file can run the same workflow.
Can I get notified when training finishes?โผ
Yes. Add your Telegram or Slack tokens to the .env file and you will receive alerts at every milestone, from plan ready to published.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core