Skills
.Work. You
Rest

harness-metrics-audit

Community

Measure what your harness really improves

Software Engineering#automation#claude code#metrics#evaluation#regression#harness
AuthorFesto-Wampamba
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps you figure out whether your Claude Code harness is actually getting better in the way you care about, instead of only improving easy-to-count proxy metrics like skill count, automation coverage, or token savings.

Core Features & Use Cases

  • Clarifies the real target: Interviews the user to define what better means in plain language, such as faster delivery, fewer corrections, or higher trust.
  • Separates signal from proxies: Compares visible metrics against the outcome they are supposed to represent and exposes when they drift apart.
  • Designs regression checks: Proposes concrete evals for real workflows, friction counters, trust checks, and time or cost measurements.
  • Use Case: You changed your hooks and skills and want to know whether the setup is genuinely helping, not just looking more automated.

Quick Start

Ask the skill to interview your goals, identify proxy metrics that may be misleading, and produce a small regression suite for your Claude Code harness.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: harness-metrics-audit
Download link: https://github.com/Festo-Wampamba/Claude-Features/archive/main.zip#harness-metrics-audit

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 537,000+ vetted skills library on demand.