skills.rest
ddunnock
ddunnockCOMMUNITY
Explore all skills by this author β†’
WebsiteGitHub

trade-study-analysis

Perform DAU 9-Step Trade Study analyses grounded in documented sources.

10|5|Updated Jan 2, 2026
Search Tags:#source-grounded#normalization#weighting#sensitivity-analysis#decision-analysis#trade-study
One-click install
npx skills add https://github.com/ddunnock/claude-plugins --skill trade-study-analysis
Or copy as Structured Prompt for Agentβ–Ό
Please help me install this Agent Skill.
Skill: trade-study-analysis
Source: https://github.com/ddunnock/claude-plugins/tree/main/skills/trade-study-analysis
Command: npx skills add https://github.com/ddunnock/claude-plugins --skill trade-study-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

πŸ’‘ This Skill requires numpy, pandas, matplotlib, seaborn, scipy, and includes scripts (resource) components.

What problem does it solve?

This Skill enables engineers to perform formal trade studies by grounding decisions in documented sources, reducing ambiguity and ungrounded conclusions.

Core Features & Use Cases

  • Structured problem framing: Define problems, identify root causes, and scope evaluation criteria to ensure defensible decisions.
  • Data-grounded evaluation: Collect, validate, and normalize data from alternatives and datasheets with explicit sources.
  • Weighted scoring & sensitivity: Apply weights, perform normalization, run sensitivity analyses, and generate professional reports with visuals.

Quick Start

  • Prepare problem context, sources, and alternatives, then kick off the DAU 9-Step Trade Study workflow.
  • Use the included scripts to register sources, collect data, compute scores, and generate a final report.
  • Example command: python tools/init_plugin.py skill trade-study-analysis --path skills

Frequently Asked Questions about trade-study-analysis

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

FAQPage Schema
How do I perform a DAU 9-Step trade study with weighted scoring and sensitivity analysis?β–Ό

Perform a DAU 9-Step trade study by defining the problem, collecting alternative data from documented sources, normalizing values, applying weighted scoring, running sensitivity analysis, and generating a final report using included Python scripts.

What is source-grounded decision analysis for engineering trade studies?β–Ό

Source-grounded decision analysis reduces ambiguity by requiring documented sources for all data used in the trade study. It validates evaluation criteria and scoring against actual datasheets and alternatives to ensure defensible engineering conclusions.

Can I use numpy and pandas for data normalization in engineering trade studies?β–Ό

Yes, numpy and pandas handle data normalization and weighting. The trade study workflow uses these dependencies alongside scipy and matplotlib to compute scores, run sensitivity analyses, and generate visual reports.

How do I prepare input data and datasheets before starting a trade study workflow?β–Ό

Prepare input data by defining problem context, identifying alternatives, and structuring documented sources into a sources.json file. This grounds the data collection phase before running scripts for normalization and scoring.

Does this trade study workflow support root-cause analysis and problem framing?β–Ό

Yes, the trade study workflow supports structured problem framing and root-cause analysis. It scopes evaluation criteria early in the DAU 9-Step process to ensure engineering decisions are properly bounded.

Related Skills

Explore More Data & Analytics Skills→
TheTesseractAITheTesseractAI

design-exploration

Analyze source code and context to generate distinct design variation hypotheses.

Community
Advanced
sereinmonosereinmono

δΈ“δΈšεˆ†ζ΅ζˆη»©ε―θ§†εŒ–εˆ†ζžοΌˆι€šη”¨η‰ˆοΌ‰

Analyze and visualize professional distribution scores from Excel data.

Community
Advanced
santoosaraujosantoosaraujo

options-advanced

Model volatility surfaces and manage multi-dimensional Greeks for options trading.

Community
Advanced
jshsakurajshsakura
22

data-researcher

Gather and synthesize evidence from datasets, metrics, and data pipelines.

Community
Advanced