An advanced content evaluation engine that analyzes article quality, detects AI-generated patterns, and provides reading recommendations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tmp70s6amg4
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tmp70s6amg4 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Article Taster?
Article Taster is a comprehensive analysis tool developed for the Openclaw Skills ecosystem to help users filter out low-quality content and prioritize valuable reading material. It functions as a virtual content analyst that assesses technical depth, structural clarity, and emotional resonance across multiple genres including technical documentation, creative essays, and novels.
By leveraging a sophisticated multi-stage pipeline, the skill identifies the difference between genuine human insight and generic machine-generated output. Whether you are a researcher looking for high-density information or a reader avoiding AI-generated noise, this tool provides an objective score and a detailed report on any given text.
Article Taster Use Cases
- Filtering high-quality technical tutorials from generic AI-generated content in research feeds.
- Evaluating the technical depth and practical utility of documentation before investing reading time.
- Detecting AI-generated patterns in creative writing and essays to ensure authenticity.
- Identifying and exempting original content like classical poetry from being mislabeled as AI-generated.
How Article Taster Works
- The system identifies the article genre (Technical, Creative, Novel, etc.) to apply the appropriate scoring methodology.
- Genre-specific analyzers evaluate the content based on metrics like technical depth or emotional narrative curves.
- A multi-dimensional AI detection engine analyzes text statistics, perplexity, and stylistic consistency.
- Exemption rules are applied to recognize classical literature or specialized formats that might trigger false positives.
- The system calculates a final weighted score and generates a detailed JSON report and a human-readable Markdown summary.
Article Taster Setup
To use this tool within the Openclaw Skills environment, ensure you have Python 3.10+ installed and set up the required dependencies:
# Install required Python libraries
pip install jieba scikit-learn openai anthropic
# Analyze a single text file
python -m article_taster analyze --file article.txt
# Run a quick analysis on raw text
python -m article_taster quick --text "Your article content here..."
# Batch process a directory of articles
python -m article_taster batch --dir ./articles
Article Taster Data Schema & Taxonomy
The skill organizes its analysis into structured reports and uses configuration files for custom weighting:
| Data Component | Description |
|---|---|
overall_score |
A 0-100 score reflecting the content quality |
ai_detection |
Contains AI probability, flavor scores, and specific warnings |
dimension_scores |
Breakdown of metrics like depth, structure, and readability |
reading_advice |
Targeted suggestions including estimated reading time and key benefits |
scoring_weights.json |
Configuration file to adjust weights for different content types |
exemption_rules.json |
Rules for identifying classical poetry and literary masterpieces |
Article Taster Advanced Features
- Multi-agent support utilizing optional OpenAI or Anthropic LLM integrations for deeper semantic analysis.
- Novel-specific analysis mode that evaluates plot structure while remaining strictly spoiler-free.
- High-precision AI detection that identifies template-based "bullshit" content and paragraph uniformity.
- Customizable scoring weights to prioritize specific values like technical practicality or emotional resonance.
- Built-in exemption mechanisms to protect classical literature from AI-generated misclassification.
SKILL.md
Loading
Related Openclaw Skills
Humanize Chinese
A professional utility for detecting and rewriting Chinese AI-generated content to remove machine-like patterns and restore a natural, human tone.
find-agents
An intelligent AI-powered search agent that performs advanced web searches, aggregates multi-source results, and provides comprehensive answers with full citations.
Operation Daily Report Claw
An automated data aggregation tool that collects multi-platform operational metrics and generates structured daily reports for Feishu integration.
Article Taster
A multi-dimensional article analysis tool that evaluates content quality, detects AI-generated text, and identifies original writing to optimize reading time.
Paper Generator
A professional academic writing assistant that transforms experimental source code into fully structured research papers in Markdown and PDF formats.
AIDraw-batch-img2img
An automation tool for batch processing reference-to-image tasks on the Tencent Hunyuan AI platform.
Featured*
