content-scanner

Scan text content for quality issues using deterministic rules and LLM semantic analysis.

Updated Apr 4, 2026
One-click install
npx skills add https://github.com/keji94/content-scanner --skill content-scanner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: content-scanner
Source: https://github.com/keji94/content-scanner/tree/main
Command: npx skills add https://github.com/keji94/content-scanner --skill content-scanner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, jieba, and includes scripts (resource) components.

What problem does it solve?

Many writers and editors need an automated way to evaluate text quality, detect rule violations, and receive actionable feedback without manually reviewing every paragraph.

Core Features & Use Cases

  • Deterministic Rule Engine: Fast, zero‑cost checks using Python scripts for common style and consistency issues.
  • LLM Semantic Review: Per‑paragraph AI analysis that catches subtle narrative problems and logical contradictions.
  • Fix‑Loop Orchestration: Automatic re‑scanning after suggested edits to ensure convergence toward a high score.

Quick Start

Invoke the scanner with the command scan <content_path> workspace=<workspace_path> to receive a graded quality report.

Frequently Asked Questions about content-scanner

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

FAQPage Schema
How do I automate content quality scanning for a novel or tutorial document?

Content quality scanning can be automated by invoking the scanner with a content path and a configured workspace, generating a graded report that evaluates narrative consistency and style issues.

How does LLM semantic analysis detect logical contradictions in text content?

LLM semantic analysis reviews text content paragraph by paragraph to identify subtle narrative problems and logical contradictions that deterministic rule engines might miss.

Do I need Python 3.10 to run the deterministic rule engine for text quality checks?

Yes, Python 3.10 or higher is required to run the deterministic rule engine scripts and execute the zero-cost style and consistency checks for text content.

Can I apply custom rule configurations when scanning general content for quality issues?

Yes, you can apply custom rules by specifying a workspace path containing rule and context configurations tailored for novel, tutorial, or general content.

What is the best way to ensure text content reaches a high quality score after rule violations are found?

The fix-loop orchestration automatically re-scans text content after suggested edits are applied, ensuring the document converges toward a high quality score.

Why does the content scanner require jieba and pyyaml dependencies?

The content scanner requires jieba for text segmentation and pyyaml to parse workspace rule and context configuration files during the quality analysis process.