Coverage Matrix Construction

Builds coverage matrices mapping required elements to threads and identifies gaps with severity classifications.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill coverage-matrix-construction-gozonerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Coverage Matrix Construction
Source: https://github.com/gozonerd/shadow-ai-assessment/tree/main/.claude/skills/dmis/task_type/TT-13_Coverage_Matrix_Construction
Command: npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill coverage-matrix-construction-gozonerd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Analysts running multi-pipeline document analysis need a quantitative way to verify that all required elements are actually covered by available evidence threads, and to pinpoint blind spots before synthesis proceeds. ## Core Features & Use Cases - Coverage Matrix Construction: Maps required elements against threads/sources with Addressed, Partial, or Missing indicators per cell. - Aggregation & Gap Analysis: Calculates per-element, per-thread, and overall coverage percentages, then classifies gaps by severity with remediation paths. - Output Validation: Ships a Python validator that checks YAML outputs against the TT-13 schema, including severity enums and coverage ranges. - Use Case: After running P1-P3 analysis pipelines, verify that all required dimensions (e.g., deployment history, adoption metrics) are covered across the specified thread counts (P1=15, P2=25, P3=5) and document any high-severity gaps requiring new source material. ## Quick Start Ask the AI to build a TT-13 coverage matrix from your required elements specification and thread inventory, then validate the resulting YAML output with the included script.

Frequently Asked Questions about Coverage Matrix Construction

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

FAQPage Schema
How do I build a coverage matrix for multi-source analysis?

Enumerate all required elements from your input specification, list available threads from raw processing, then score each element-thread cell as Addressed, Partial, or Missing. Aggregate coverage percentages per element and per thread, and document gaps with severity and remediation.

How to validate a coverage matrix YAML output in Python?

Run the included validate_output.py script with the output file path as argument. It checks for required fields like coverage_matrix, coverage_aggregation, and gap_analysis, verifies overall_coverage is between 0 and 1, and confirms gap severity values are Low, Medium, or High.

What coverage values are allowed in the matrix cells?

Each element-thread cell must be one of three indicators: Addressed, Partial, or Missing. These values feed the aggregation step that computes per-element, per-thread, and overall coverage percentages.

Why does output validation fail on gap severity values?

Validation fails when a gap entry uses a severity outside the allowed set of Low, Medium, or High, or when required keys like element or severity are missing. Check each gap object in gap_analysis.gaps against the schema.

What are the limitations of coverage matrix scoring?

Coverage scoring depends on accurate element extraction and honest depth assessment; marking elements covered without verifying relevance produces superficial results. It also cannot distinguish input specification errors from genuine processing gaps without careful review.