skills.rest
gaiastudio-ai
gaiastudio-aiOFFICIAL
Explore all skills by this author →
GitHub

gaia-test-manual

Execute manual software tests and capture run-record evidence.

2|Updated Apr 15, 2026
Search Tags:#verification#manual testing#evidence#execution#visual regression
One-click install
npx skills add https://github.com/gaiastudio-ai/gaia-framework --skill gaia-test-manual
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gaia-test-manual
Source: https://github.com/gaiastudio-ai/gaia-framework/tree/main/plugins/gaia/skills/gaia-test-manual
Command: npx skills add https://github.com/gaiastudio-ai/gaia-framework --skill gaia-test-manual

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides manual test execution and verification capabilities within the GAIA framework, enabling users to perform manual tests as a real user would and generate evidence of their execution.

Core Features & Use Cases

  • Manual Test Execution: Dispatch the manual-tester agent (Reese) to exercise a target as a human operator would, including interactive commands, observed output, and comparisons of expected vs. actual behavior.
  • Evidence Persistence: Persists evidence artifacts (run-record.md and exit-code.log) to verify execution.
  • Disambiguation: Differentiates from automated test suite execution to cater to exploratory testing, smoke testing, UX verification, and behaviors that resist automation.
  • Surface Verification: Supports verification surfaces like API, browser, mobile, and desktop, with detailed configuration and output handling.
  • Visual Regression: Provides pixel-level visual regression detection for the browser surface, ensuring design consistency across different runs.

Quick Start

Use the gaia-test-manual skill with the target 'example-feature'.

Frequently Asked Questions about gaia-test-manual

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

FAQPage Schema
How do I perform manual testing and capture execution evidence within the GAIA framework?▼

Manual testing in the GAIA framework is executed by dispatching a manual-tester agent to exercise features as a human operator, capturing run-record.md and exit-code.log artifacts as execution evidence.

What is visual regression detection and how does it work for browser surfaces?▼

Visual regression detection for browser surfaces performs pixel-level comparisons across different runs, ensuring design consistency by identifying visual changes between expected and actual behavior outputs.

Can I use manual test execution for exploratory and UX verification across multiple platforms?▼

Manual test execution supports exploratory testing, smoke testing, and UX verification across API, browser, mobile, and desktop surfaces, handling behaviors that resist automation for comprehensive platform coverage.

Does manual testing require agent dependencies to compare expected vs actual behavior?▼

Manual testing requires a manual-tester agent, command execution capabilities, and comparison of expected vs actual behavior to verify software functionality and generate execution evidence.

What's the difference between manual test execution and automated test suite execution?▼

Manual test execution differs from automated test suite execution by catering to exploratory testing, smoke testing, and UX verification, handling interactive commands and behaviors that resist traditional automation.

Related Skills

Explore More Software Engineering Skills→
ryankoleanryankolean
3

architect-plan-for-dispatch

Analyze a repository to generate a Code Report and Dispatch execution plan.

Community
Advanced
EmasoftEmasoft
13

amoa-verification-patterns

Generate evidence-based JSON verification reports for implemented code and systems.

Community
Advanced
katalon-labskatalon-labs
4

true-platform-testing

Orchestrate the 7-stage Katalon testing lifecycle with automated traceability.

Official
Advanced
flutterflutter
2.8k

run-evals

Orchestrate automated evaluation of agent skills using isolated subagents and rubrics.

Official
Advanced