site-audit

Orchestrate parallel quality audits with weighted scoring and sprint comparisons.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/c3z/agent-pomodoro --skill site-audit-c3z
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: site-audit
Source: https://github.com/c3z/agent-pomodoro/tree/main/.claude/skills/site-audit
Command: npx skills add https://github.com/c3z/agent-pomodoro --skill site-audit-c3z

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams evaluate the quality of Agent Pomodoro from multiple perspectives at once, making it easier to catch regressions, prioritize fixes, and keep the product reliable for both humans and AI agents.

Core Features & Use Cases

  • Parallel review orchestration: Coordinates four reviewer perspectives so quality feedback is gathered efficiently.
  • Weighted scoring: Combines agent access, end-user experience, developer experience, and performance into one consolidated audit.
  • Sprint regression checks: Compares each audit against the previous sprint to surface improvements and new issues.
  • Use case: Run it after a release or sprint to generate structured review files and a summary score for the repository.

Quick Start

Ask the assistant to run the site-audit skill on the current Agent Pomodoro repository and produce the reviewer files and consolidated score.

Frequently Asked Questions about site-audit

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

FAQPage Schema
How do I run a multi-perspective sprint review for agent access and developer experience?

A multi-perspective sprint review evaluates agent access, end-user experience, developer experience, and performance simultaneously. You can orchestrate parallel reviewer execution to gather feedback efficiently and generate a consolidated weighted score.

What is a site quality audit and how does it catch regressions in a skill ecosystem?

A site quality audit assesses a skill ecosystem by comparing current sprint results against prior ones. This comparison surfaces improvements and catches new regressions by writing structured review files for each evaluated perspective.

How do I consolidate performance and DevEx scores into a single weighted audit?

You consolidate performance and DevEx scores into a weighted audit by applying a scoring mechanism across parallel review perspectives. This generates file-based outputs and a summary score that reflects the overall repository quality.

Does the site audit require prior sprint artifacts to evaluate quality?

The site audit compares current results against prior sprint artifacts to evaluate quality. Having previous review files allows the audit to detect regressions and improvements, though generating current review files remains the primary output.

When should I run a parallel reviewer execution for a project release?

You should run parallel reviewer execution after a release or sprint. This timing allows the audit to capture the latest changes, compare them with previous sprint results, and produce review artifacts for the repository.

Can I evaluate agent access and end-user experience simultaneously during a sprint?

You can evaluate agent access and end-user experience simultaneously by orchestrating a site audit. This coordinates four reviewer perspectives in parallel, combining them into one consolidated audit with a weighted score.