| name | text-splitter |
| description | Split text into specified-sized chunks while maintaining semantic integrity. Suitable for long text batch processing, dividing text into processable segments |
| category | tools |
| version | 2.1.0 |
| last_updated | 2026-01-11T00:00:00.000Z |
| license | MIT |
| compatibility | Claude Code 1.0+ |
| maintainer | Gong Fan |
| allowed-tools | [] |
| model | opus |
| changelog | [{"version":"2.1.0","date":"2026-01-11T00:00:00.000Z","changes":["[Truncated]","[Truncated]","[Truncated]","[Truncated]"]},{"version":"2.0.0","date":"2026-01-11T00:00:00.000Z","changes":["[Truncated]","[Truncated]","[Truncated]"]},{"version":"1.0.0","date":"2026-01-10T00:00:00.000Z","changes":["[Truncated]"]}] |
Text Splitter Tool
Functionality
Split text into specified-sized chunks while maintaining semantic integrity, facilitating subsequent batch processing and analysis.
Usage Scenarios
- Process extra-long text by splitting it into agent-processable segments
- Perform text preprocessing to provide standardized input for subsequent content analysis, summarization, or evaluation tasks
- Optimize text processing workflows to ensure each processing unit is controllable in size and semantically complete
Core Capabilities
- Semantic Integrity Priority: When splitting, avoid truncating sentences or paragraphs; prioritize splitting at natural boundaries (periods, line breaks) to ensure semantic integrity of each chunk
- Preserve Original Format: During splitting, preserve the original format and structure of text, such as Markdown, HTML tags, etc.
- Precise Chunk Size Control: Strictly split according to specified size limits, ensuring each text chunk does not exceed the preset maximum length
- Multiple Splitting Strategies: Support various splitting strategies based on character count, token count, paragraph count, or specific delimiters
Input Requirements
- Text Content: Original text to be split
- Chunk Size Limit: Maximum length of each text chunk (recommend providing character count or token count)
- Splitting Strategy (optional): Specify preferred splitting strategy, such as split by sentence, split by paragraph, split by specific delimiter, etc.
Output Format
[Text Splitting Report]
- Original text length: [integer] words/tokens
- Target chunk size: [integer] words/tokens
- Actual number of chunks: [integer] chunks
### Splitting Results
- Chunk 1 (length: [integer] words/tokens): "[content preview...]"
- Chunk 2 (length: [integer] words/tokens): "[content preview...]"
- Chunk 3 (length: [integer] words/tokens): "[content preview...]"
...
Constraints
- Splitting results must strictly comply with specified chunk size limits
- Ensure maximum preservation of text semantic integrity during splitting
- Output format must be structured, clearly displaying content and length of each text chunk
- Avoid introducing any extra information or explanations in output; only provide splitting results
Examples
See {baseDir}/references/examples.md for more detailed examples:
examples.md - Contains splitting examples for different lengths, different splitting strategies, and complex text structures
