deployment-smoke-test

Run automated smoke tests against OpenClaw agent workspaces and return structured JSON results.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/Heretek-AI/heretek-openclaw --skill deployment-smoke-test
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deployment-smoke-test
Source: https://github.com/Heretek-AI/heretek-openclaw/tree/main/skills/deployment-smoke-test
Command: npx skills add https://github.com/Heretek-AI/heretek-openclaw --skill deployment-smoke-test

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deployment of multiple OpenClaw agents often requires quick validation to ensure all components communicate correctly after rollout. This skill automates a small, deterministic suite of tests to verify basic A2A, health endpoints, triad deliberation, and memory persistence.

Core Features & Use Cases

  • Automated health ping of all agent endpoints and gateway readiness
  • A2A messaging and triad deliberation sanity checks across the agent network
  • Basic user context and memory persistence validations to catch regressions

Quick Start

Run the smoke test script to validate all agent workspaces post-deployment.

Frequently Asked Questions about deployment-smoke-test

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

FAQPage Schema
How do I run automated smoke tests to verify agent deployment health?

Automated smoke tests verify agent deployment health by pinging all agent endpoints, validating A2A messaging, triad coordination, context handling, and memory persistence across workspaces. The skill executes a deterministic test suite and returns structured JSON results.

What is the best way to validate A2A communication and triad deliberation after rollout?

Validating A2A communication and triad deliberation after rollout requires running automated smoke tests across the agent network. This skill sequences A2A messaging and triad sanity checks to quickly catch coordination regressions in deployed workspaces.

Can I use this smoke test skill to check memory persistence and context handling for all 11 agents?

Yes, this smoke test skill checks memory persistence and context handling for all 11 agents. It automates basic user context validations and memory persistence tests, returning a structured JSON with per-test results and an overall status.

Do I need an OpenClaw gateway deployment to run these automated sanity checks?

Yes, these automated sanity checks are applicable to OpenClaw gateway deployments. The skill verifies gateway readiness and agent endpoint health to ensure all components communicate correctly after rollout.

Why does my agent network return unexpected results during post-deployment validation?

Post-deployment validation failures indicate that A2A communication, health endpoints, triad deliberation, or memory persistence have regressions. Running this automated smoke test suite specifies test prerequisites, sequences, and expected outcomes to isolate deployment issues.

How do deployment smoke tests work with OpenClaw agents?

Deployment smoke tests work by executing a small, deterministic suite of automated tests against all OpenClaw agent workspaces. The script validates basic A2A, health endpoints, triad deliberation, and memory persistence to ensure correct component communication.