Chunk textbook into chapters

VerifiedSafe

Split a textbook PDF into per-chapter files using its embedded or recovered outline.

Sby Skills Guide Bot
Data & AIIntermediate
207/24/2026
Claude Code
#textbook#pdf#chunking#chapters#arcane

Recommended for

Our review

This skill splits a textbook PDF into per-chapter PDF files using the document's embedded or recovered outline.

Strengths

  • Automates splitting large textbooks into manageable parts
  • Leverages existing or recovered outline for accurate boundaries
  • Provides a dry-run preview before actual splitting
  • Handles error cases like scanned documents or missing outlines

Limitations

  • Requires the PDF to be text-based (not scanned)
  • Depends on presence or recovery of an outline
  • Only works with the Arcane CLI tool
When to use it

Use this skill when you have a textbook PDF in an Arcane project and want to split it into separate chapter files.

When not to use it

Do not use it for scanned PDFs (without OCR) or if you don't have access to the Arcane tool.

Security analysis

Safe
Quality score88/100

The skill only invokes the 'arcane' tool for PDF analysis and chunking, with no destructive commands, external data exfiltration, or obfuscation. All operations are deterministic and confined to the project scope.

No concerns found

Examples

Chunk textbook by chapters
Chunk the textbook PDF in my Arcane project 'physics101' into chapter files.
Split with specific depth
Split the PDF 'biology_textbook.pdf' into chapters using depth 2 to include section headings.
Force re-chunk existing source
Re-chunk the math textbook in the project 'math' with --force because the old chunks are wrong.

Skill: chunk-textbook

Split a textbook PDF into per-chapter files using its embedded or recovered outline.

When to use

The user has a textbook PDF in an Arcane project and wants it split into one PDF per chapter. Run this skill when they say "chunk", "split into chapters", or "split by chapter".

Steps Claude must follow

  1. Ask for the project name and source title if not provided.

  2. Probe the PDF to confirm it is text-based:

    arcane analyze probe "<pdf-path>" --json
    
    • If document_kind is Scanned → stop and tell the user outline recovery is required first.
  3. Inspect the existing outline:

    arcane analyze outline "<pdf-path>" --depth 2
    
    • If no outlines → tell the user to run recover-outline-heuristic or recover-outline-bridge first, then return here.
  4. Dry-run to preview chapter boundaries:

    arcane chunk "<project>" --depth 1 --dry-run
    

    Show the user the boundary table and ask: "Does this look correct? Should I proceed?"

  5. Execute chunking (only after user confirms):

    arcane chunk "<project>" --depth 1
    

    If source already chunked and --force was not requested, inform the user and offer to re-chunk with --force.

  6. Verify output:

    arcane list-chunks "<project>"
    

    Report the chunk count and list the files.

  7. Fill in template.md and present the summary to the user.

Flags to mention

  • --depth 2 — includes section-level headings
  • --source "Title" — chunk only one specific source
  • --force — overwrite existing chunks

Error handling

| Problem | Action | |---------|--------| | No outlines found | Direct to recover-outline-heuristic or recover-outline-bridge | | Source is scanned | Stop; explain OCR is not supported | | Wrong boundaries | Suggest --depth 2 or running analyze offset first |

Related skills