article-reporting

name	article-reporting
description	Reporting Kura experiment results for notes, Scrapbox, blog posts, X/Twitter, or comparison summaries. Use when summarizing training parameters, dataset size, generated comparison images, observed quality, caveats, and reproducible run IDs.

Article Reporting

Use this skill to turn Kura experiments into concise public or private writeups.

Include

• Run IDs and backend.
• Base model and architecture.
• GPU/runtime when relevant.
• Dataset count and role summary.
• Rank/alpha/LR/batch/steps/save interval.
• Selected checkpoints and LoRA strength.
• Prompt set and seed policy for comparisons.
• Clear caveats: dataset quality, overfit signs, non-controlled variables.

Avoid

• Overclaiming from one dataset.
• Publishing secrets, local private paths, or gated model access details.
• Treating qualitative image preference as a benchmark.