stock-analysis

Synthesize company fundamentals, technical indicators, and market context into a risk-aware investment conclusion.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/nowonbun/nowonbun-harness --skill stock-analysis-nowonbun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stock-analysis
Source: https://github.com/nowonbun/nowonbun-harness/tree/main/codex-skills/stock-management_stock-analysis
Command: npx skills add https://github.com/nowonbun/nowonbun-harness --skill stock-analysis-nowonbun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a structured, evidence-based framework for analyzing individual stocks so analysts and AI agents produce clear, source-cited conclusions that separate technical and fundamental signals and explicitly report risks and uncertainties. It enforces transparency about assumptions, avoids presenting analysis as guaranteed returns, and sets rules for scope, evidence, and output format.

Core Features & Use Cases

  • Structured Analysis Workflow: Define analysis purpose and time horizon up front, collect evidence, separate technical and fundamental analyses, and summarize trends, volume/volatility, comparisons, and key risks.
  • Evidence and Methods Rules: Require source citations or calculation basis for all numeric claims, mark unverified assumptions, and demand clear distinction between technical and fundamental findings.
  • Output and Verification: Present the conclusion first, support it with bullet-pointed evidence, list major risks separately, and end with practical next steps or missing-data checks.
  • Use Case: Produce an investment review for a mid-term buy decision that includes valuation ratios with sources, chart-based trend summary, sector-relative context, and a ranked list of company-specific and macro risks.

Quick Start

Ask the skill to analyze Company XYZ for a mid-term investment review, separate technical and fundamental findings, cite sources for all figures, and list the top three risks with recommended next steps.

Frequently Asked Questions about stock-analysis

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

FAQPage Schema
How do I perform evidence-based stock analysis that separates technical and fundamental signals?

Evidence-based stock analysis requires defining your purpose and time horizon upfront, then collecting source-cited data to evaluate technical indicators and company fundamentals separately before synthesizing a risk-aware investment conclusion.

What is the best way to structure a stock investment review with clear risk reporting?

A structured stock investment review presents the conclusion first, supports it with bullet-pointed evidence including valuation ratios and chart-based trends, then lists major company-specific and macro risks separately with recommended next steps.

Can I use fundamental and technical analysis together for a mid-term trade assessment?

You can combine fundamental and technical analysis for a mid-term trade assessment by explicitly distinguishing between the two signal types, citing sources for all numeric claims, and documenting sector-relative context alongside volatility metrics.

How do I cite sources and verify calculations in a financial analysis report?

Financial analysis source verification requires citing the calculation basis for every numeric claim, explicitly marking any unverified assumptions, and ensuring clear distinction between technical chart findings and fundamental valuation data.

Does stock analysis work for comparing multiple companies across different time horizons?

Stock analysis supports comparative research across short-, mid-, or long-term horizons by requiring an explicit time horizon statement, synthesizing market context, and ranking key risks to produce clear, risk-aware conclusions for each evaluated company.

What limitations exist when analyzing stocks with missing financial data or unverified assumptions?

When analyzing stocks with missing data, the framework requires marking unverified assumptions explicitly and ending with practical missing-data checks, ensuring conclusions remain transparent rather than presenting analysis as guaranteed returns.