A multi-dimensional article analysis tool that evaluates content quality, detects AI-generated text, and identifies original writing to optimize reading time.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tmpz3kwrq8c
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 tmpz3kwrq8c 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 specialized analysis tool designed to serve as a digital connoisseur for written content. It stands at the intersection of quality assessment and AI detection, helping users filter through the noise of the modern web to find high-value information. By analyzing technical depth, structural logic, and emotional resonance, it provides a comprehensive score that guides readers on whether a piece is worth their time.
As part of the Openclaw Skills ecosystem, this tool is particularly effective at identifying what is colloquially known as AI flavor or generic content. It employs sophisticated linguistic analysis to distinguish between genuine human voices and the repetitive, hollow patterns often found in machine-generated text, while maintaining high accuracy through specialized exemption rules for classical literature and poetry.
Article Taster Use Cases
- Filtering technical blog posts to identify deep architectural insights versus generic AI summaries.
- Detecting AI-generated patterns in creative writing or academic submissions to ensure authenticity.
- Performing spoiler-free narrative analysis on novels to evaluate pacing and structure.
- Prioritizing reading lists by batch-processing article directories and ranking them by quality score.
- Identifying high-quality classical poetry and literature using specialized exemption filters.
How Article Taster Works
- The skill first performs article type identification to categorize content as technical, creative, novel, or general text.
- Content is routed to specialized modules like TechAnalyzer or NovelAnalyzer for context-aware evaluation.
- The AI Detection engine analyzes perplexity, vocabulary richness, and paragraph uniformity to calculate an AI flavor score.
- A weighted scoring system aggregates results across dimensions like practicality, originality, and readability.
- The tool generates a final JSON report and a Markdown summary featuring a grade from A+ to D and specific reading advice.
Article Taster Setup
To get started with this skill, ensure you have the necessary environment and dependencies installed:
# Install required Python libraries
pip install jieba scikit-learn
# Optional: Install LLM providers for enhanced analysis
pip install openai anthropic
# Analyze a text file directly from the CLI
python -m article_taster analyze --file my_article.txt
# Perform a quick score for immediate feedback
python -m article_taster quick --text "Your article content here..."
Article Taster Data Schema & Taxonomy
The skill organizes its output into structured reports. Below is the primary data taxonomy used in the analysis:
| Category | Metadata Field | Description |
|---|---|---|
| Identification | type_confidence | Probability score of the detected article genre |
| Quality | overall_score | Final weighted score (0-100) |
| AI Detection | ai_flavor_level | Classification from Human Writing to High AI Flavor |
| Context | reading_advice | Targeted audience and estimated reading time |
| Technical | dimension_scores | Breakdown of depth, structure, and practicality |
Article Taster Advanced Features
- Smart Exemption Engine: Automatically raises AI detection thresholds for classical poetry and rhythmic literature to prevent false positives.
- Customizable Weighting: Users can modify scoring_weights.json to prioritize different quality dimensions like technical depth over readability.
- Spoiler-Free Analysis: Specialized novel analysis mode that evaluates plot structure without revealing key narrative twists.
- Multi-Agent Integration: Optional hooks for OpenAI and Anthropic models to provide nuanced, LLM-assisted qualitative feedback.
- Human Marker Detection: Specifically looks for personal voice markers like real-world experience and authentic emotional cues.
SKILL.md
Loading
Related Openclaw Skills
UpLead
The UpLead skill for Openclaw Skills enables automated B2B sales intelligence and lead verification through the Membrane framework.
Skill Creator
Skill Creator is a comprehensive development framework designed to build, test, and optimize modular AI agent capabilities through iterative evaluation loops.
Airflow Read-Only Skill
A secure, read-only interface to inspect Apache Airflow DAGs, runs, and task instances via the Stable REST API.
Crypto Sentiment Monitor
A real-time analysis tool that aggregates social media, search trends, and exchange data to track cryptocurrency market sentiment.
Operation Daily Report Claw
An automated data aggregation tool that collects multi-platform operational metrics and generates structured daily reports for Feishu integration.
find-agents
An intelligent AI-powered search agent that performs advanced web searches, aggregates multi-source results, and provides comprehensive answers with full citations.
Featured*
