skills.rest
yaalalabs
yaalalabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ak-test

Set up, write, and run Agent Kernel tests for CLI and API agents.

113|60|Updated Jul 18, 2025
Search Tags:#testing#ci/cd#debugging#troubleshooting#pytest#agent kernel
One-click install
npx skills add https://github.com/yaalalabs/agent-kernel --skill ak-test
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ak-test
Source: https://github.com/yaalalabs/agent-kernel/tree/main/ak-py/src/agentkernel/skills/ak-test
Command: npx skills add https://github.com/yaalalabs/agent-kernel --skill ak-test

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of testing and debugging Agent Kernel projects, ensuring your agents function as expected and helping you resolve common issues efficiently.

Core Features & Use Cases

  • Test Framework Setup: Guides you through configuring pyproject.toml and config.yaml for testing.
  • Test Writing: Provides examples for writing tests for both CLI and API-based agents using pytest.
  • Test Modes: Explains and demonstrates fuzzy, judge, and fallback testing modes.
  • Debugging Common Issues: Offers solutions for frequent problems like "No agents available," session state issues, and tool context errors.
  • Use Case: After developing a new agent, use this Skill to write and run comprehensive tests to verify its behavior, then use its debugging guidance to fix any encountered problems before deployment.

Quick Start

Configure your project to use fuzzy test mode by updating your config.yaml file.

Frequently Asked Questions about ak-test

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

FAQPage Schema
How do I write tests for Agent Kernel projects using pytest?▼

To test Agent Kernel projects, you configure pyproject.toml and config.yaml, then write pytest test cases for both CLI and API-based agents to verify their expected behaviors.

What testing modes are available for debugging Agent Kernel agents?▼

Available test modes include fuzzy matching, LLM-based judging, and fallback testing. These modes help validate agent behavior and provide detailed debugging guidance for common Agent Kernel issues.

Why does my Agent Kernel project show no agents available?▼

The "no agents available" error is a common Agent Kernel issue. You can resolve this and other session state or tool context errors by following the specific debugging guidance provided for troubleshooting agent configurations.

Can I test both CLI and API agents within the same framework?▼

Yes, this testing framework supports both CLI and API-based agent types. It provides specific examples for writing pytest cases and configuring the environment to validate either agent type.

How do I configure fuzzy test mode for an agent?▼

To use fuzzy test mode, you update your config.yaml file to apply the fuzzy matching configuration. This allows your test suite to validate agent outputs with flexible matching logic.

Related Skills

Explore More Software Engineering Skills→
yaalalabsyaalalabs
113

ak-add-integration

Add messaging platform integrations to Agent Kernel projects via configuration files and webhook handlers.

Official
Intermediate
kynoptickynoptic
1

Running and Debugging Tests

Run, diagnose, and fix failing test suites across language ecosystems.

Community
Intermediate
archview-aiarchview-ai

openwebf-host

Route WebF host requests to focused OpenWebF skills by trigger terms.

Official
Advanced
ken-cavanagh-gleanken-cavanagh-glean
4

evaluation

Design evaluation frameworks with rubrics and LLM-as-judge workflows.

Community
Advanced