# Skill Forge

- **Event:** [OpenEnv Hackathon SF](https://cerebralvalley.ai/e/openenv-hackathon-sf)
- **When:** Mar 7 at 9:00 AM – Mar 8 at 12:00 AM (PST)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Kabalan Gaspard](https://cerebralvalley.ai/u/kg36), [Lifei Chen](https://cerebralvalley.ai/u/Leefey)
- **GitHub:** https://github.com/clfhaha1234/Skill-Forge
- **Website:** https://github.com/clfhaha1234/Skill-Forge/blob/main/colab_training.ipynb
- **Demo video:** https://youtu.be/6soVlEyb4J4
- **Hugging Face:** https://huggingface.co/spaces/kgast/openenv-hackathon-tesserae
- **Gallery:** https://cerebralvalley.ai/e/openenv-hackathon-sf/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/openenv-hackathon-sf/hackathon/gallery/15

A self-improving environment where LLM agents rewrite their own skill instructions through a generate → evaluate → optimize loop.
Instead of fine-tuning weights, we optimize human-readable skill files, making improvements interpretable, transferable, and composable.

Outputs are automatically scored against gold standards (Patronus Judge MM + Gemini Vision), and the agent updates its own rules with zero human feedback.

MVP: consulting slide generation improved 33 → 94 in one iteration. The same loop generalizes to any document task by swapping skill files and evaluators.

---

Markdown version of https://cerebralvalley.ai/e/openenv-hackathon-sf/hackathon/gallery/15. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt