liveBook · Manning

Progressive disclosure

As explained in Vibe Engineering

Progressive disclosure is a technique that reveals information in successive levels only when it becomes relevant or requested.

Loading every instruction, checklist, and script into an agent’s context wastes space. Progressive disclosure keeps capabilities discoverable while loading detail only when it becomes relevant. section 3.3.6

A skill can load in three levels:

  • Load frontmatter first: roughly 80 tokens per skill, carrying its name and description across requests. Make the description specific enough to match likely user requests. section 3.3.6
  • Load the Markdown instructions when the skill matches a request or is invoked by name. Bodies typically run 1,000–3,000 tokens. section 3.3.6
  • Keep referenced files as paths until needed; load checklists, templates, or scripts only when the procedure reaches them. section 3.3.6
pull-request-review/
├── SKILL.md        # frontmatter + instructions
├── references/     # the full review checklist
├── scripts/        # run-lint.sh, check-migrations.sh
└── assets/         # PR description template

A skill directory separates its instructions from reference material, scripts, and assets. section 3.3.6

How Vibe Engineering covers it

How deep it goes
Defines three loading levels, gives typical token costs, and explains description-driven discovery and deferred files.
Examples
Uses a pull-request review skill with staged instructions, a checklist, migration checks, and a review template.
What you can do after
Configure agent skills so brief descriptions support discovery and detailed procedures load only when needed.
How it connects
Connects agent skills with context engineering, context windows, Markdown, and frontmatter.

Also explained in

Compare how 2 books explain progressive disclosure →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Vibe Engineering. The section links point to the parts of the book it draws on.