Indexion Segment

by trkbt107ad5ad35a668No license2 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 2 weeks ago

Split text into contextual chunks for RAG/embedding pipelines. Document segmentation and section extraction using window, tfidf, punctuation, or hybrid strategies chosen by intent.

Instructions onlyAI & Agents

AI-generated overview

Splits text into contextual chunks for RAG and embedding pipelines using window, TF-IDF, punctuation, or hybrid strategies.

What it does: The skill segments a text document into smaller contextual chunks intended for retrieval-augmented generation or embedding pipelines. It offers window divergence, TF-IDF, punctuation, and hybrid NCD+TF-IDF strategies, with tunable segment sizes, thresholds, and window sizes. Output is written to a chosen directory with a configurable filename prefix.
When to use it: Use it when text must be chunked for RAG or embedding pipelines, or when a document needs to be split into meaningful sections. It also suits preparing text for sub-document similarity analysis.
Requirements: Requires the indexion command-line tool with its segment subcommand; no scripts ship with the skill. Input is a text file and output is a directory.

indexion segment

Split text into contextual segments using divergence-based, TF-IDF, or punctuation strategies.

When to Use

User needs to chunk text for RAG or embedding pipelines
User wants to split a document into meaningful sections
User asks to segment text for processing
Preparing text for similarity analysis at sub-document level

Usage

bash

# Default window divergence strategyindexion segment <input-file> <output-dir>
# TF-IDF based segmentationindexion segment --strategy=tfidf <input-file> <output-dir>
# Punctuation-based segmentationindexion segment --strategy=punctuation <input-file> <output-dir>
# Custom segment sizesindexion segment --min-size=200 --max-size=3000 --target-size=800 document.txt output/
# Custom divergence thresholdindexion segment --threshold=0.5 document.txt output/
# Adaptive threshold mode (default)indexion segment --adaptive document.txt output/
# Hybrid NCD+TF-IDF modeindexion segment --hybrid --ncd-weight=0.6 --tfidf-weight=0.4 document.txt output/
# Custom window sizeindexion segment --window-size=5 document.txt output/
# Custom output prefixindexion segment --prefix=chunk document.txt output/

# Default window divergence strategyindexion segment <input-file> <output-dir>
# TF-IDF based segmentationindexion segment --strategy=tfidf <input-file> <output-dir>
# Punctuation-based segmentationindexion segment --strategy=punctuation <input-file> <output-dir>
# Custom segment sizesindexion segment --min-size=200 --max-size=3000 --target-size=800 document.txt output/
# Custom divergence thresholdindexion segment --threshold=0.5 document.txt output/
# Adaptive threshold mode (default)indexion segment --adaptive document.txt output/
# Hybrid NCD+TF-IDF modeindexion segment --hybrid --ncd-weight=0.6 --tfidf-weight=0.4 document.txt output/
# Custom window sizeindexion segment --window-size=5 document.txt output/
# Custom output prefixindexion segment --prefix=chunk document.txt output/

Options

Option	Default	Description
`--strategy=NAME`	window	Strategy: window, tfidf, punctuation
`--min-size=INT`	100	Minimum segment characters
`--max-size=INT`	2000	Maximum segment characters
`--target-size=INT`	500	Target segment characters
`--threshold=FLOAT`	0.42	Divergence threshold
`--window-size=INT`	3	Window size
`--adaptive`	true	Adaptive threshold mode
`--hybrid`	false	NCD+TF-IDF hybrid mode
`--ncd-weight=FLOAT`	0.5	NCD weight in hybrid mode
`--tfidf-weight=FLOAT`	0.5	TF-IDF weight in hybrid mode
`--prefix=NAME`	segment	Output file prefix

Strategies

Workflow

Run indexion segment <input-file> <output-dir> to split text with defaults
Adjust --threshold and --target-size to tune segmentation granularity
Use --hybrid mode for better accuracy on mixed-content documents

Source and attribution

Source:trkbt10/indexion-skillsinskills/indexion-segmentat commit7ad5ad3

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Strategy	Description
`window` (default)	Sliding window divergence detection
`tfidf`	TF-IDF based topic change detection
`punctuation`	Punctuation/sentence boundary based

Indexion Segment

indexion segment

When to Use

Usage

Options

Strategies

Workflow

Source and attribution

More from trkbt10/indexion-skills

Indexion Wiki

Indexion Sdd

Indexion Refactor

Indexion Kgf

Indexion Readme

Indexion Documentation

More in AI & Agents

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills

Plugin Creator