novel-research

Aggregates and analyzes fanqienovel ranking data to recommend novel topics.

Updated May 8, 2026

Search Tags:#analysis #recommendation #novel #market-analysis #ranking-data #tomato #fanqienovel

Ready to run

npx skills add https://github.com/Ynyqy/ZAgent --skill novel-research-ynyqy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: novel-research
Source: https://github.com/Ynyqy/ZAgent/tree/main/zagent/workspace/skills/novel-research
Command: npx skills add https://github.com/Ynyqy/ZAgent --skill novel-research-ynyqy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydantic, requests.

What problem does it solve?

This Skill provides structured market analysis for novel authors by leveraging Tomato fanqienovel ranking data to guide topic selection, trend detection, and pitch creation.

Core Features & Use Cases

Fetch and compare male/female rankings from Tomato data to understand category share and shifts.
Analyze market trends and generate topic recommendations for writing, editing, and publishing strategy.
Output clear, actionable reports and creative direction for drafts and pitches.

Quick Start

Run a market scan for都市高武 to get top rankings and trend insights

Frequently Asked Questions about novel-research

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

FAQPage Schema

How do I analyze Tomato novel ranking data to guide topic selection?▼

Analyzing Tomato novel ranking data for topic selection involves fetching male and female rankings, comparing category shares, and detecting market shifts. This skill automates that data retrieval and outputs structured creative recommendations to guide your novel pitches.

What is the best way to track fanqienovel market trends for new writing topics?▼

Tracking fanqienovel market trends requires aggregating male and female ranking data to observe category share shifts over time. This skill processes ranking data to identify trending categories and returns actionable insights and creative direction for novel topics.

Can I get structured JSON outputs from Tomato ranking data for downstream LLM drafting?▼

Yes, you can get structured JSON outputs from Tomato ranking data for downstream LLM drafting. This skill formats market analysis, category trends, and creative recommendations into JSON-suited outputs, enabling seamless integration with LLM-assisted novel writing workflows.

Does this novel market analysis tool require specific dependencies like pydantic and requests?▼

Yes, this novel market analysis tool requires pydantic and requests dependencies to function. Pydantic handles data validation for the retrieved fanqienovel ranking data, while requests manages the on-demand API retrieval of male and female category rankings.

How do I compare male and female novel rankings to find category market gaps?▼

Comparing male and female novel rankings to find market gaps requires aggregating both datasets and analyzing their category shares. This skill fetches both rankings simultaneously, analyzes the proportional distribution, and highlights trending categories to reveal underserved novel topics.