generate-qa-scorecard

Generates a 7-dimension QA scorecard with letter grades and priority actions for Claude Code plugins.

1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/JaviMontano/mao-plugin-qa --skill generate-qa-scorecard-javimontano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: generate-qa-scorecard
Source: https://github.com/JaviMontano/mao-plugin-qa/tree/main/skills/generate-qa-scorecard
Command: npx skills add https://github.com/JaviMontano/mao-plugin-qa --skill generate-qa-scorecard-javimontano

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? After running validation and audit checks on a Claude Code plugin, teams are left with scattered findings and no clear overall verdict. This Skill aggregates those findings into a single executive scorecard with a letter grade, numeric score, and ranked improvement actions. ## Core Features & Use Cases - 7-Dimension Scoring: Evaluates Structure Conformance, Manifest Quality, Component Standards, Hook Safety, Reference Integrity, Security Posture, and Content Quality with strict PASS/WARN/FAIL rules. - Letter Grade Mapping: Converts numeric scores (out of 70) into A-F grades using fixed percentage thresholds, with proportional recalculation when dimensions are N/A. - Priority Actions: Ranks the top 3 most impactful fixes by severity, including expected score improvement for each. - Use Case: After running validate-structure, validate-manifest, and audit-security on a plugin, invoke this Skill to produce a compact Markdown table showing per-dimension status, finding counts, total score, grade, and the three fixes that will raise the grade fastest. ## Quick Start Generate a QA scorecard for my plugin using the findings from the validation and audit skills we just ran.

Frequently Asked Questions about generate-qa-scorecard

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

FAQPage Schema
How do I generate a QA scorecard for a Claude Code plugin?▼

Run the validation and audit skills first (validate-structure, validate-manifest, validate-components, validate-hooks, validate-cross-refs, audit-security, audit-content-quality), then invoke this Skill. It maps findings to 7 dimensions, assigns PASS/WARN/FAIL status, and outputs a graded Markdown table.

How is the plugin letter grade calculated?▼

Each dimension scores 10 points for PASS, 6 for WARN, and 2 for FAIL, with a maximum of 70. The total maps to letter grades: A is 63-70, B is 56-62, C is 49-55, D is 42-48, and F is below 42. N/A dimensions are excluded and thresholds recalculate proportionally.

What happens if some quality dimensions were not evaluated?▼

Unevaluated dimensions are marked N/A with a justification note and excluded from the score denominator. The grade thresholds recalculate proportionally against the reduced maximum, and the scorecard explicitly notes the reduced evaluation scope.

Does the scorecard skill modify my plugin files?▼

No, the Skill is strictly read-only. It aggregates findings from other validation and audit skills into a report but never modifies any plugin files. Fixes must be applied separately based on the priority actions it recommends.

What are the limitations of the PASS/WARN/FAIL scoring model?▼

All dimensions are weighted equally, so a security FAIL scores the same as a content quality FAIL. A dimension with 1 critical finding scores identically to one with 20. The priority actions section provides the nuance the numeric score cannot.