From mdsel
Markdown selective reader. Run `mdsel <file>` via bash to get a table of contents (headings + structure) in a fraction of the tokens — use it for overviews, navigation, or when you only need specific sections. Also supports fuzzy search by keyword. Only use read when you need full file content or plan to edit. Triggers: markdown, .md, README, documentation, docs, overview, table of contents
How this skill is triggered — by the user, by Claude, or both
Slash command
/mdsel:mdselThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`mdsel` is a markdown selective reader with three modes:
mdsel is a markdown selective reader with three modes:
mdsel README.md (no selector) → get the TOCmdsel "h2.4,h3.6" README.md — grab specific sectionsmdsel "installation" README.md — fuzzy-find by keyword0-based indexing. Always index before selecting.
NEVER use the * wildcard selector. If you need the entire document, use the Read tool instead — that's what it's for. The purpose of mdsel is selective reading to save tokens.
Use the Read tool for markdown files when:
* or root — just use Read)Offers UI/UX design guidance for web and mobile with 50+ styles, 161 color palettes, 57 font pairings, and 99 UX guidelines across 10 stacks. Use for designing pages, components, color systems, or reviewing UI code.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub dabstractor/mdsel-skill --plugin mdsel