Installs into .claude/skills of the current project.
Are you the author of Auto Best Practice From Official?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/openamer-auto-best-practice-from-official)
---
name: auto-best-practice-from-official
description: LoRA · Hugging Face — We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition …;
auto_generated: true
created: 2026-09-09
source_insight: "Best practice from official docs: PEFT LoRA training best practices"
status: draft
fitness_score: 0
trials: 0
wins: 0
---
# Auto Best Practice From Official
## Trigger
Use when the agent encounters: LoRA · Hugging Face — We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model w
## Verification
- [ ] The skill produces the expected output for its domain
- [ ] No errors in execution
- [ ] Insight quality: actionable and specific
## Notes
Auto-generated from internet insight (Knowledge-to-Action pipeline).
Darwin will trial this skill; it gets promoted only if it wins arena fights.
