eval-harness

Name: eval-harness
Availability: InStock
Author: titta

Validates markdown artifacts against declarative JSON rubrics for structural quality.

29|12|Updated Mar 30, 2026

Search Tags:#automation #quality assurance #linting #markdown #validation #gtm

Ready to run

npx skills add https://github.com/matteotitta/genesys-skills --skill eval-harness-matteotitta

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: eval-harness
Source: https://github.com/matteotitta/genesys-skills/tree/main/skills/meta/catalog/eval-harness
Command: npx skills add https://github.com/matteotitta/genesys-skills --skill eval-harness-matteotitta

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the problem of inconsistent quality and structural errors in GTM deliverables by providing a deterministic, programmatic gate that validates markdown artifacts before they reach expensive LLM review stages.

Core Features & Use Cases

Structural Validation: Automatically checks for required sections, frontmatter fields, and citation tags using regex and section extraction.
Quality Guardrails: Enforces keyword blocklists and word/sentence count bounds to ensure brand consistency and readability.
Use Case: Use this to lint client proposals, positioning documents, or messaging libraries during a CI/CD process to catch structural blockers like missing sections or banned buzzwords before human or LLM review.

Quick Start

Run the eval-harness script against your target skill directory to generate a structural quality report.

Frequently Asked Questions about eval-harness

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

FAQPage Schema

What is structural validation for GTM deliverables?▼

You can validate markdown structure by running a deterministic linting gate that checks frontmatter validity, section presence, and keyword constraints against declarative JSON rubrics before qualitative LLM review. This filters out structurally malformed content during pre-commit or CI stages.

How do I enforce word count limits and banned buzzwords in markdown documents?▼

To enforce word count limits and banned buzzwords in markdown documents, apply quality guardrails using regex and section extraction to check word and sentence count bounds alongside keyword blocklists, ensuring brand consistency and readability.

Can I use a deterministic linter instead of an LLM to check positioning documents?▼

Yes, you can use a deterministic structural linter to check positioning documents. It programmatically validates required sections and frontmatter fields using JSON rubrics, operating as a pre-commit gate to filter out structurally malformed content before expensive LLM review.

How do I lint client proposals for missing sections during a CI/CD process?▼

You can lint client proposals during a CI/CD process by running a structural validation script against the target directory. It extracts sections and checks for required frontmatter fields and citation tags, generating a structural quality report to catch missing sections.

When should I not use deterministic structural validation for markdown artifacts?▼

You should not use deterministic structural validation when evaluating the qualitative content, tone, or semantic meaning of markdown artifacts, as it only enforces structural rules, section presence, and keyword constraints rather than assessing content quality.