What is skill-evaluator?

A plugin for testing AI skills across different model tiers, meaning different levels of model capability or cost. It uses blind tests, where the test model does not see the expected answers, and gives refinement recommendations.

It is for running skill evaluations, comparing model-tier results, analyzing failures, and improving skill instructions.

It helps reveal whether a skill works reliably across models without letting the expected result influence the test.

skill-evaluator — Plugin by ai-plugin-marketplace

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 ai-plugin-marketplace/template

agentmods

npx agentmods add plugins/ai-plugin-marketplace/template/skill-evaluator

Clone the repo

git clone --depth 1 https://github.com/ai-plugin-marketplace/template

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 original No closer match found 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

Copies of this mod

1 near-identical copy found in the catalogue:

skill-evaluator — 100% identical, 1 lines differ

plugins/skill-evaluator/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "schemaVersion": "0.1.0",
  "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.

2d ago First seen · 15 lines scan A e3d3856f1503

Subscribe to this mod's changes

skill-evaluator is a plugin published in the GitHub repository ai-plugin-marketplace/template (10 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Testing ai-skills claude-code cursor gemini-cli kiro vercel-skills

skill-evaluator

Getting it into your agent

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

claude-settings marketplace

n8n-as-code

codex-advisor

fable-advisor

claude-telemetry-hooks

claude-tools