MrBinnacle

Skill Harness

Name: Skill Harness
Author: MrBinnacle

Productivity community

SOURCE https://github.com/MrBinnacle/skill-harness

Description

I wanted to know whether a skill was actually any good. This runs the same task with the skill and without it, and reports what can honestly be said about the difference - often "not enough to call it". A missing figure is a typed refusal, never an invented score. First-class Claude Code support.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

skill-harness

[![CI](https://github.com/MrBinnacle/skill-harness/actions/workflows/ci.yml/badge.svg)](https://github.com/MrBinnacle/skill-harness/actions/workflows/ci.yml) [![Python 3.12+](https://img.shields.io/badge/python-3.12%2B-blue.svg)](https://www.python.org/downloads/) [![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](https://github.com/MrBinnacle/skill-harness/blob/main/LICENSE) [![PyPI](https://img.shields.io/pypi/v/skill-harness.svg)](https://pypi.org/project/skill-harness/)

Why this exists

I wanted to know if you could tell if a skill was any good.

Search for a skill that makes AI writing sound less like AI writing and you get a dozen of them. Each one costs context in every conversation, whether or not it fires. Which of them changes an outcome is a different question from which of them reads well, and no amount of reading the file answers it.

Two public repositories: [MrBinnacle/skills](https://github.com/MrBinnacle/skills) holds the skills, and this repository is the instrument built to answer the question about them. How lopsided that split got, and the two commands that re-derive it from a fresh clone, are in [why this exists](https://github.com/MrBinnacle/skill-harness/blob/main/docs/why-this-exists.md).

skill-harness runs the same task with a skill and without it, and reports what can honestly be said about the difference. Often what can honestly be said is "not enough to call it."

It has first-class support for Claude Code skills and is built to extend to other agent ecosystems.