Skip to content
TakoAPI
Back to skills

nlp-toolkit

by raghulpasupathi

Search & Research
459Downloads reported by clawskills.sh
1Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Advanced NLP with perplexity scoring, burstiness analysis, and entropy calculation.

Description

What This Skill Does

Analyzes text using statistical NLP measures to estimate whether it was written by a human or generated by AI. Computes perplexity, burstiness, and Shannon entropy scores, then combines them into a confidence rating.

Runs entirely client-side with no external API calls, so text is never sent to a third-party detection service.

When to Use It

  • Screening submitted essays for AI authorship
  • Flagging AI-generated support tickets before human review
  • Auditing content pipelines for model-generated text
  • Comparing writing samples before and after AI tool adoption
  • Spot-checking blog drafts for undisclosed AI use

Example Workflow

INPUT

User asks: Is this 200-word paragraph AI-generated?

AGENT
  1. 1

    Pass the text to analyzeText with default thresholds

  2. 2

    Calculate perplexity from unique-to-total word ratio

  3. 3

    Measure burstiness as coefficient of variation across sentence lengths

  4. 4

    Compute Shannon entropy over character frequency distribution

  5. 5

    Combine three scores into a single confidence percentage

OUTPUT

{ isAI: true, confidence: 78, metrics: { perplexity: 32.4, burstiness: 0.21, entropy: 4.1 }, explanation: 'Low perplexity and uniform burstiness suggest AI generation' }

Installation

clawhub install raghulpasupathi/nlp-toolkit

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links