skill-evaluator

A testing tool for comparing AI skills across different model levels using blind tests, where the model being tested is not identified in advance.

In plain words
What is it for?
Use it to test an AI skill across model tiers and get refinement recommendations.
Why use it?
It helps reveal how well a skill works without opinions about which model is running it, and suggests ways to improve the skill.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add 8090-inc/software-factory-plugin
agentmods
npx agentmods add plugins/8090-inc/software-factory-plugin/skill-evaluator
Clone the repo
git clone --depth 1 https://github.com/8090-inc/software-factory-plugin

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Security

Grade A, and why

skill-evaluator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to skill-evaluator — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

scratch/skill-evaluator/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "skill-evaluator",
  "version": "0.0.1",
  "description": "Evaluate AI skills across model tiers with blind testing and refinement recommendations",
  "author": {
    "name": "AI Plugin Marketplace Template"
  },
  "keywords": ["evaluation", "testing", "skills", "model-tiers"],
  "skills": ["./skills/evaluate-skill"],
  "agents": ["./agents/experimenter.md", "./agents/test-subject.md"],
  "commands": ["./commands/evaluate.md"],
  "hooks": "./hooks/claude.json"
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 14 lines scan A 81572901b123

Subscribe to this mod's changes

skill-evaluator is a plugin published in the GitHub repository 8090-inc/software-factory-plugin (7 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 100% identical to skill-evaluator, differing in 1 line, and is treated as a copy.