Rule-based Markdown chunks derived from huzey/claude-skills (source file: claude-skills.gpt_summary.parquet).
--include-heading-path-in-text: true
--include-frontmatter-unit: true
--primary-level-strategy: highest
--max-primary-level: 3
--max-chars: 4000
--min-chars: 800
--tldr: true (synthetic TL;DR chunk at chunk_index_in_doc=0)
These columns are copied from the source dataset… See the full description on the dataset page:
https://huggingface.co/datasets/huzey/claude-skills-chunk.
