Test runner

Skill Liber1917/agent-skill-infra/skills/test-runner

Agent Skill Infrastructure: quality check, behavior test runner, version awareness

Install

npx -y skills add Liber1917/agent-skill-infra --skill test-runner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Guide for writing behavior test cases (evals.json) for Agent Skills. Defines the eval schema, judgment criteria (trigger/flow/output), and snapshot testing conventions. Use when creating test cases for Skills or teaching others how to test Agent Skills.

SKILL.md

2.6 KB, as published. Nobody here has run it

Skill Behavior Test Guide

Define and run behavior tests for Agent Skills using the evals.json format.

evals.json Schema

{
  "$schema": "http://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "skill_name": { "type": "string" },
    "skill_version": { "type": "string" },
    "evals": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": { "type": "string" },
          "name": { "type": "string" },
          "trigger": {
            "type": "object",
            "properties": {
              "input": { "type": "string" },
              "should_trigger": { "type": "boolean" }
            },
            "required": ["input", "should_trigger"]
          },
          "flow": {
            "type": "object",
            "properties": {
              "expected_tools": { "type": "array", "items": { "type": "string" } },
              "expected_sequence": { "type": "boolean" }
            }
          },
          "output": {
            "type": "object",
            "properties": {
              "contains": { "type": "array", "items": { "type": "string" } },
              "not_contains": { "type": "array", "items": { "type": "string" } },
              "format": { "type": "string", "enum": ["text", "json", "markdown", "table", "code"] }
            }
          }
        },
        "required": ["id", "name", "trigger"]
      }
    }
  }
}

Judgment Criteria

Trigger Judgment

Input matches skill description → skill should activate
Input does not match → skill should NOT activate
Edge cases: ambiguous inputs, multi-language, partial matches

Flow Judgment (optional)

Which tools should the skill call?
In what order?
Are there unnecessary tool calls?

Output Judgment (optional)

Must contain specific keywords/phrases
Must NOT contain certain content
Expected output format (text/json/markdown/table/code)

Writing Guidelines

Each eval tests ONE behavior aspect (trigger, flow, or output)
Use descriptive IDs: trigger-positive-basic, output-format-json, flow-tool-sequence
Include at least 2 positive trigger tests and 1 negative trigger test per skill
Test edge cases: empty input, very long input, multi-language
Save evals.json alongside the SKILL.md being tested