skills.rest
danielscholl
danielschollCOMMUNITY
Explore all skills by this author →
GitHub

test-framework

Validate plugin skills across four layers with dry-run and JSON CI outputs.

23|3|Updated Oct 10, 2025
Search Tags:#automation#qa#triggers#scenarios#claude-code#test-framework#plugin-testing
One-click install
npx skills add https://github.com/danielscholl/claude-sdlc --skill test-framework
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: test-framework
Source: https://github.com/danielscholl/claude-sdlc/tree/main/plugins/skilltest/skills/test-framework
Command: npx skills add https://github.com/danielscholl/claude-sdlc --skill test-framework

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rich.

What problem does it solve?

Four-layer test framework to validate Claude Code plugin skills across structure, triggers, session behavior, and skill value, ensuring reliable, repeatable testing of AI-driven workflows.

Core Features & Use Cases

  • Layered testing across L1–L4: structure validation, trigger evaluation, multi-turn sessions, and value comparisons.
  • Dry-run and JSON output options for CI integration and quick feedback on skill design.
  • Real-world workflow validation: verify correct routing, coordination between agents and skills, and measurable improvements when added.

Quick Start

Install and run the provided scripts to validate a skill and execute trigger evals and session tests.

Frequently Asked Questions about test-framework

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate Claude Code plugin skills for reliable performance?▼

The test framework supports dry-run validation and JSON outputs designed specifically for CI pipelines. This enables automated integration into your continuous integration workflow for quick feedback on skill design.

What is the best way to test trigger evaluation in Claude Code plugins?▼

Trigger evaluation is tested in the L2 layer of the test framework. This layer assesses whether your plugin skills activate correctly under the right conditions, verifying correct routing and coordination between agents and skills.

Does the test framework support multi-turn session testing for plugin skills?▼

Yes, multi-turn session testing is supported through the L3 layer of the test framework. This layer validates real-world workflow behavior by testing session interactions to ensure skills perform reliably across multiple conversational turns.

What do I need to run end-to-end tests on Claude Code plugin skill directories?▼

You need a plugin skill directory containing a SKILL.md file and the rich dependency installed. The framework applies to directories meeting this structure requirement to enable structure validation, trigger evaluation, and session testing.

Can I measure skill value improvements when adding a plugin to my workflow?▼

Yes, the L4 layer of the test framework performs value comparisons to measure improvements when a skill is added. This validates that your plugin provides measurable value enhancements to the AI-driven workflow.

Related Skills

Explore More Software Engineering Skills→
Ameng2001Ameng2001
1

plugin-validator

Validate Claude Code plugin structure, SKILL.md metadata, and dependency integrity.

Community
Advanced
FlexNetOSFlexNetOS

alpha

Execute predefined test scenarios in CI/CD environments.

Official
Basic
hainamchunghainamchung
54

agent-assistant-deploy

Route deployment tasks to the Agent Assistant workflow via /deploy in Codex-based agents.

Community
Intermediate
global-osglobal-os

benchmark-testing

Set up isolated directories, install vercel-plugin, and run Claude Code with prompts.

Official
Advanced