skills.rest
peopleforrester
peopleforresterCOMMUNITY
Explore all skills by this author →
Website𝕏@peopleforresterGitHub

eval-harness

Evaluate code quality across projects using a structured rubric.

3|Updated Jan 29, 2026
Search Tags:#automation#evidence#code-quality#scoring#assessment#rubric#evaluate
One-click install
npx skills add https://github.com/peopleforrester/claude-dotfiles --skill eval-harness-peopleforrester
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: eval-harness
Source: https://github.com/peopleforrester/claude-dotfiles/tree/main/skills/optimization/eval-harness
Command: npx skills add https://github.com/peopleforrester/claude-dotfiles --skill eval-harness-peopleforrester

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It provides a structured, repeatable framework to assess code quality and produce evidence-based scores across dimensions.

Core Features & Use Cases

  • Structured Rubric: Dimensions include Correctness, Security, Performance, Maintainability, Testing, and Documentation with clear weights.
  • Evidence-based Scoring: Captures concrete tests, metrics, and artifacts to justify each score.
  • Use Case: Ideal for pre-merge evaluations, project health checks, and external audits to generate a ranked quality report.

Quick Start

Run the evaluation harness on a project directory to generate a structured quality report file and a scoring rationale.

Frequently Asked Questions about eval-harness

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

FAQPage Schema
How do I evaluate code quality across multiple projects using a structured rubric?▼

Evidence-based code quality scoring captures concrete tests, metrics, and artifacts to justify each score, ensuring repeatable assessments across dimensions like correctness and security rather than relying on subjective manual reviews.

What's the best way to generate an automated code quality assessment report?▼

To set up code quality scoring, define evaluation dimensions and scoring scales, then collect evidence from tests and artifacts before applying weighted aggregation to generate a final verdict and structured quality report.

Can I use a weighted scoring rubric for pre-merge code evaluations and project health checks?▼

Yes, a structured rubric supports pre-merge evaluations by scoring correctness, security, performance, maintainability, testing, and documentation with clear weights, capturing concrete artifacts to justify each score before merging.

What dimensions should I include in a code quality scoring rubric?▼

A code quality scoring rubric should include dimensions for correctness, security, performance, maintainability, testing, and documentation. Each dimension requires clear weights and evidence collection to support the final aggregated score.

Why does my code quality assessment lack repeatability across different projects?▼

Code quality assessments lack repeatability when they do not use a structured rubric with defined dimensions, scoring scales, and evidence collection. Applying weighted aggregation to concrete artifacts ensures a consistent final verdict across different projects.

Related Skills

Explore More Software Engineering Skills→
jeffbalagosajeffbalagosa
1

openspec-verify-change

Verify OpenSpec change implementations against delta artifacts and codebase evidence.

Community
Advanced
SjdjdiejdrirhdkjejSjdjdiejdrirhdkjej

optimization-phase

Run post-implementation quality gates and generate reports before release.

Community
Advanced
KrismithReddy12KrismithReddy12

health

Calculate a weighted 0-10 code quality score from linters and test runners.

Community
Advanced
robertzengcnrobertzengcn

health

Aggregate code quality metrics from multiple tools into a weighted 0-10 composite score.

Community
Advanced