fundamental-stock-analysis_skill

This skill performs fundamentals-based stock analysis and peer ranking, scoring quality, balance-sheet safety, cash flow, and valuation to guide pick selection.
  • Python

2.5k

GitHub Stars

3

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill fundamental-stock-analysis

  • _meta.json487 B
  • README.md1.8 KB
  • SKILL.md1.6 KB

Overview

This skill performs fundamental equity analysis and peer ranking using a structured scoring playbook covering quality, balance-sheet safety, cash flow, valuation, sector adjustments, and confidence modifiers. It is designed to analyze one or more tickers, compare peers, and produce a decisive fundamentals-based verdict with explicit confidence and data caveats. The output separates business quality, balance-sheet safety, and valuation and never fabricates missing metrics.

How this skill works

I follow a fixed playbook: parse inputs, collect market and financial data, run a quick screen, apply standardized scoring across defined categories, and produce ratings and a ranked peer selection. For multi-ticker requests I analyze each ticker individually, then apply peer-ranking logic and invalidation triggers to choose a best pick. I always report a confidence level and flag stale or conflicting data, marking unavailable metrics as NA.

When to use it

  • You want a systematic fundamentals-based verdict on one or several stock tickers.
  • You need a ranked comparison of peers and a single best pick backed by objective rules.
  • You require separate assessment of business quality, balance-sheet safety, and valuation.
  • You want explicit confidence and clear calls when data is stale, conflicting, or missing.

Best practices

  • Provide tickers and an explicit peer list when possible to speed accurate comparisons.
  • Specify a target analysis date if you need a snapshot other than the latest available data.
  • Expect NA for missing metrics; supplement with primary filings if precise figures are critical.
  • Use the score breakdown to validate subjective judgments before making investment decisions.

Example use cases

  • Analyze AAPL and MSFT, then rank them and recommend which to prioritize based on playbook scores.
  • Screen a small peer group in a given sector to choose the best fundamentals-based pick.
  • Request a fundamentals verdict with an explicit confidence level for inclusion in a research note.
  • Ask for separate commentary on business quality, balance-sheet safety, and valuation for a single ticker.

FAQ

Confidence is derived from data freshness, completeness, and consistency across sources; stale or conflicting inputs lower confidence.

What happens if a metric is missing?

Missing metrics are marked NA and the scoring adjusts using available data and confidence modifiers; no fabrication occurs.

Can the playbook be customized?

The core playbook is fixed for reproducibility; provide inputs such as peers or analysis date to influence context without changing scoring rules.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational