isda

Analyze text into five strata and generate compressibility metrics.

3|Updated May 17, 2025
One-click install
npx skills add https://github.com/vincitamore/misc --skill isda
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: isda
Source: https://github.com/vincitamore/misc/tree/main/isda
Command: npx skills add https://github.com/vincitamore/misc --skill isda

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Irreducible Semantic Density Analysis (ISDA) provides a principled way to assess how much of a text is genuinely necessary to convey its core contribution, by decomposing content into five strata and quantifying compressibility.

Core Features & Use Cases

  • Decompose text into five strata: Structural Skeleton, Retrievable Knowledge, Derived Inferences, Curatorial Decisions, and Generative Novelty, to reveal where meaning resides.
  • Produce quantitative metrics (e.g., Raw Length, SCR, ND, RI, CBAT) and a detailed stratum ledger to guide editing, rewriting, and quality assurance.
  • Use cases include evaluating editorial efficiency, measuring originality, and guiding condensation or expansion of long-form content.

Quick Start

Provide a sample text to analyze with a five-strata breakdown and a full metric report.

Frequently Asked Questions about isda

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I measure the semantic density and compressibility of a text?

To measure semantic density, you can analyze the text using a five-strata framework that decomposes content into structural, retrievable, derived, curatorial, and novel layers to estimate how much is genuinely necessary to convey the core contribution.

What is the five-strata framework for analyzing text content?

The five-strata framework analyzes text by breaking it down into Structural Skeleton, Retrievable Knowledge, Derived Inferences, Curatorial Decisions, and Generative Novelty to reveal where meaning resides and quantify compressibility.

How do I identify unnecessary length and guide edits in long-form content?

You can identify unnecessary length and guide edits by applying the five-strata analysis to produce quantitative metrics like SCR, ND, RI, and CBAT, which generate a detailed stratum ledger for evaluating editorial efficiency.

Can I measure the originality of written content using semantic analysis?

Yes, you can measure originality by isolating the Generative Novelty stratum within the text, which evaluates the layer of generative novelty against other content layers to quantify original contributions.

Does semantic density analysis work for evaluating editorial efficiency across various text lengths?

Yes, semantic density analysis evaluates different layers of content across various text lengths to assess editorial efficiency, measuring the irreducible semantic density to determine if condensation or expansion is needed.