book-chapter-generator_skill

This skill designs an optimal chapter structure for intelligent textbooks by aligning concepts with dependencies and taxonomy.
  • Python

1

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill vishalsachdev/claude-skills --skill book-chapter-generator

  • SKILL.md15.9 KB

Overview

This skill generates a structured chapter outline for intelligent textbooks by analyzing the course description, learning graph, and concept taxonomy. It produces an optimal chapter count (6-20), assigns every concept exactly once, and creates titles and one-sentence summaries for each chapter. The design enforces dependency constraints and balances concept distribution to support a clear pedagogical progression.

How this skill works

The skill reads the course description, the learning-graph.json, and an optional concept taxonomy to extract concepts, dependencies, and clusters. It validates the learning graph (DAG, unique IDs, valid references), detects foundational and advanced concepts, and computes an assignment that respects all prerequisite relationships. It then proposes chapter counts, chapter titles, per-chapter concept lists, and single-sentence summaries for user approval before generating directory and index files.

When to use it

  • After creating the learning graph (learning-graph.json exists) and finalizing the course description
  • When you need a chapter-level structure before writing chapter content
  • When concept dependencies must be preserved across chapters
  • When you need balanced distribution of ~200 concepts into 6–20 chapters
  • Before running automated chapter content generation tools

Best practices

  • Ensure learning-graph.json is a valid DAG with unique concept IDs before running the skill
  • Provide a clear course description and taxonomy to guide meaningful chapter groupings
  • Aim for 10–15 chapters for ~200 concepts; target 10–20 concepts per chapter on average
  • Keep chapter titles concise (Title Case, <200 characters) and summaries to one sentence (20–40 words)
  • Iterate on the proposed design: review challenges, request specific moves, then revalidate dependencies

Example use cases

  • Designing a 12-chapter undergraduate textbook from a 200-concept learning graph
  • Splitting a large taxonomy category into multiple chapters to avoid overly dense chapters
  • Creating chapter outlines that ensure advanced topics appear after all prerequisites
  • Generating MkDocs-ready chapter directories and index.md files after user approval
  • Preparing a chapter scaffold for automated content generation tools

FAQ

Course description (/docs/course-description.md) and /docs/learning-graph/learning-graph.json; concept-taxonomy.md is optional but recommended.

How does the skill ensure dependencies are respected?

It validates the graph as a DAG, uses topological ordering, and assigns concepts so no concept precedes its prerequisites.

Can I change the number of chapters?

Yes. The proposal asks for approval and supports iterative edits: you can request a different chapter count or move specific concepts.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational