Document splitting

VerifiedSafe

Reads documents and splits them into manageable chunks based on line count, character size, markdown sections, or paragraphs. Supports overlapping chunks to maintain context. Useful for processing large files, analysis, or transfer tasks.

Sby Skills Guide Bot
Data & AIBeginner
406/2/2026
Claude Code
#split#document-chunking#text-processing#file-splitting

Recommended for

Our review

Reads documents and splits them into manageable chunks for processing, analysis, or transfer.

Strengths

  • Multiple splitting strategies (lines, size, sections, paragraphs)
  • Supports overlap to maintain context between chunks
  • Clear output with headers and summaries
  • Simple usage with intuitive options

Limitations

  • Only works on readable text files
  • Size-based splitting is approximate and breaks at line boundaries
  • Relies on line break or header structure
When to use it

When you need to break a large document into smaller pieces for sequential processing or analysis.

When not to use it

For binary files or when byte-precise splitting is required.

Security analysis

Safe
Quality score92/100

The skill only reads files and uses 'wc -l' for counting lines, with no network access, file modification, or command execution beyond the allowed tools. It presents no risk of data exfiltration, unauthorized access, or destructive actions.

No concerns found

Examples

Split by default lines
/split README.md
Split by markdown sections
/split document.md --sections
Split by lines with overlap
/split document.txt --lines 100 --overlap 10

name: split description: Read documents and split them into chunks allowed-tools:

  • Read
  • Bash(wc *)

Split Skill

Read documents and split them into manageable chunks for processing, analysis, or transfer. Like a master breaking boards, this skill shatters overwhelming information into fragments that can be easily mastered.

Capabilities

  • Split by Lines: Split files into chunks of a precise number of lines.
  • Split by Size: Split files into chunks of an approximate character count.
  • Split by Sections: Split at structural boundaries like markdown headers.
  • Split by Paragraphs: Split at blank line delimiters.
  • Support Overlap: Maintain context between chunks with an overlapping buffer.

Usage Examples

Split a file into standard chunks:

/split README.md

Split by precise line count:

/split document.txt --lines 100

Split by markdown sections:

/split document.md --sections

Split by paragraphs:

/split article.txt --paragraphs

Split with context overlap:

/split document.txt --lines 100 --overlap 10

Options

| Option | Description | Default | | -------------- | ------------------------------------ | ------- | | --lines N | Split every N lines | 100 | | --size N | Split at approximately N characters | - | | --sections | Split at markdown headers (# ## ###) | - | | --paragraphs | Split at blank lines | - | | --overlap N | Include N lines of context | 0 |

Output Format

Present each chunk with a header showing its number and line range:

══════════════════════════════════════════════════════
CHUNK 1 of 5 (lines 1-100)
══════════════════════════════════════════════════════

[chunk content here]

══════════════════════════════════════════════════════
CHUNK 2 of 5 (lines 101-200)
══════════════════════════════════════════════════════

[chunk content here]

Splitting Strategies

By Lines (default)

Split at fixed line intervals. Best for uniform content like logs or data files.

By Size

Split at approximate character counts, breaking at line boundaries. Best when targeting specific output sizes.

By Sections

Split at markdown headers (lines starting with #). Best for documentation. Each section becomes its own chunk.

By Paragraphs

Split at blank lines. Best for prose where paragraphs are the logical units.

Workflow

  1. Read the file using the Read tool.
  2. Get file stats using wc -l to show total lines.
  3. Apply splitting strategy based on options.
  4. Display chunks with headers and summaries.
  5. Show summary with total chunks and average chunk size.
Related skills