From document-to-markdown
Use when you need to split a long Markdown document into logical sections
How this skill is triggered — by the user, by Claude, or both
Slash command
/document-to-markdown:chunk-markdownThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Split a Markdown document into semantically meaningful chunks based on heading hierarchy and content classification. Produces numbered files and a manifest index.
Split a Markdown document into semantically meaningful chunks based on heading hierarchy and content classification. Produces numbered files and a manifest index.
--depth (optional; defaults to 2, i.e., split at ##)--min-tokens (optional; defaults to 200)--max-tokens (optional; defaults to 8000)--min-tokens with adjacent sections.--max-tokens at lower heading levels if possible.chunks/ next to the input Markdown.chunks/NN-slug.md, where NN is zero-padded sequence and slug is derived from the heading (kebab-case, sanitized).chunks/index.toon manifest with one entry per chunk, fields: slug, title, kind (e.g., "chapter", "appendix", "glossary"), tokens, source_lines (start line and end line in original file).chunks/ directory created next to input Markdownchunks/index.toon manifest file with metadata per chunkCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin document-to-markdown