bull-research

Generate structured investment bull cases from JSON financial data.

Updated Jun 19, 2026

Search Tags:#finance #stock analysis #technical analysis #investing #fundamental analysis #bullish

Ready to run

npx skills add https://github.com/a-chris/auto-search-finance --skill bull-research-a-chris

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bull-research
Source: https://github.com/a-chris/auto-search-finance/tree/main/skills/bull-research
Command: npx skills add https://github.com/a-chris/auto-search-finance --skill bull-research-a-chris

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of cognitive bias and information overload in financial research by providing a structured, optimistic framework to identify and validate investment opportunities.

Core Features & Use Cases

Structured Bull Case Generation: Synthesizes technical, fundamental, and sentiment data into a rigorous investment thesis.
Multi-Agent Coordination: Acts as a specialized sub-agent within a larger research pipeline to provide the optimistic perspective.
Use Case: When the main research agent identifies a potential watchlist candidate, this Skill evaluates the ticker to determine if it represents a high-conviction buying opportunity based on technical setups and fundamental strength.

Quick Start

Invoke the bull-research agent by passing the pre-collected financial data file to the orchestrator for a specific ticker analysis.

Frequently Asked Questions about bull-research

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

FAQPage Schema

How do I generate a structured investment bull case from pre-collected stock data?▼

Generating a structured investment bull case requires passing pre-collected JSON data inputs into an automated financial research pipeline. The agent synthesizes technical indicators, fundamental metrics, and market sentiment to output a standardized high-conviction verdict.

Can I use technical and fundamental analysis to score stock conviction without external API calls?▼

Yes, you can score stock conviction without external API calls by feeding pre-collected JSON data to the evaluation agent. It assesses technical setups and fundamental strength internally to determine if a ticker represents a high-conviction buying opportunity.

What is automated multi-perspective stock evaluation in a financial research pipeline?▼

Automated multi-perspective stock evaluation is a process where a specialized sub-agent analyzes technical, fundamental, and sentiment data. It acts within a larger research pipeline to provide an optimistic perspective and validate watchlist candidates.

Do I need to pre-collect JSON data inputs before running automated stock analysis?▼

Yes, you must pre-collect JSON data inputs before running automated stock analysis. The evaluation agent requires these pre-assembled financial metrics to generate a structured investment thesis and conviction score without making external API calls.

Best way to validate watchlist candidates for high-conviction buying opportunities?▼

The best way to validate watchlist candidates is using a structured optimistic framework that evaluates technical setups and fundamental strength. This approach mitigates cognitive bias and information overload by synthesizing market sentiment data into a rigorous investment thesis.

Limitations of generating stock bull cases without real-time market sentiment data?▼

A limitation of generating stock bull cases without real-time data is the reliance on pre-collected JSON inputs. Because the agent makes no external API calls, the accuracy of the automated conviction scoring depends entirely on the freshness of your supplied market sentiment and technical metrics.