clj-skill-eval

Community

Prove skill impact with real before/after tests

Authorhumorless
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill prevents vague or hypothetical claims about Clojure skills by forcing a measurable comparison between with-skill and without-skill development on identical real tasks.

Core Features & Use Cases

  • Rigorous A/B skill testing: Run the same task in two isolated projects and compare outcomes rather than opinions.
  • Behavior-focused analysis: Examine context-logs for REPL usage, exploration patterns, and debugging approach to verify the skill actually changes workflow.
  • Actionable scoring & reporting: Produce an evaluation report covering quantitative signals (time/tokens/LOC/tests) and qualitative signals (documentation depth, API choices, defensiveness).

Quick Start

Ask an agent to evaluate whether a specific Clojure skill (like clj-debug) improves real development by running the same task in two isolated projects and writing a single evaluation report comparing behavior, code quality, documentation depth, and test coverage.

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: clj-skill-eval
Download link: https://github.com/humorless/clj-native-agent/archive/main.zip#clj-skill-eval

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 471,000+ vetted skills library on demand.