Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nicepkg/value-dividend-screener
Screen US stocks for high-quality dividend opportunities combining value characteristics (P/E ratio under 20, P/B ratio under 2), attractive yields (3% or higher), and consistent growth (dividend/revenue/EPS trending up over 3 years). Supports two-stage screening using FINVIZ Elite API for efficient pre-filtering followed by FMP API for detailed analysis.
Passed 15 of 20 test cases with the skill, and 7 of 20 without it.
and 7 more in the full report
9 fixed8 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to screen for top dividend stocks but limit the resulting output list to exactly 50 candidates instead of the default 20. What CLI flag and argument should be passed to the screening script?
| Checked | Without skill | With skill |
|---|---|---|
| Includes --top 50 when invoking the screening script | Missed | Passed |
The instructions your model reads when the skill loads.
This skill identifies high-quality dividend stocks that combine value characteristics, attractive income generation, and consistent growth using a two-stage screening approach:
Screen US equities based on quantitative criteria including valuation ratios, dividend metrics, financial health, and profitability. Generate comprehensive reports ranking stocks by composite quality scores with detailed fundamental analysis.
Efficiency Advantage: Using FINVIZ pre-screening can reduce FMP API calls by 90%, making this approach ideal for free-tier API users.
Invoke this skill when the user requests:
For Two-Stage Screening (Recommended):
Check if both API keys are available:
import os
fmp_api_key = os.environ.get('FMP_API_KEY')
finviz_api_key = os.environ.get('FINVIZ_API_KEY')
If not available, ask user to provide API keys or set environment variables:
export FMP_API_KEY=your_fmp_key_here
test cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.