skills.rest
wade56754
wade56754COMMUNITY
Explore all skills by this author →
GitHub

ai-ad-agents-test-orchestrator

Orchestrate static test inspections to gate AI agent deployments.

Updated Nov 8, 2025
Search Tags:#automation#testing#CI/CD#AI agents#orchestration#quality gate#regression testing
One-click install
npx skills add https://github.com/wade56754/AI_ad_spend02 --skill ai-ad-agents-test-orchestrator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-ad-agents-test-orchestrator
Source: https://github.com/wade56754/AI_ad_spend02/tree/main/.claude/skills/ai-ad-agents-test-orchestrator
Command: npx skills add https://github.com/wade56754/AI_ad_spend02 --skill ai-ad-agents-test-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solves?

Ensuring the quality and stability of AI agents after code changes requires continuous testing, but full test runs can be time-consuming. This Skill orchestrates static test patrols for AI agents, automatically mapping code changes to relevant tests, executing them one by one, and providing a quality gate verdict for deployment.

Core Features & Use Cases

  • Change-Driven Test Selection: Automatically identifies and runs only tests relevant to recent code changes in agents/ or skills/ directories.
  • Static Test Execution Orchestration: Calls ai-ad-agents-test-runner to perform static analysis-based tests, tracking PASS/FAIL/UNCERTAIN outcomes.
  • Quality Gate Verdict: Provides a clear "BLOCK", "ALLOW", or "WARN" verdict based on test results, acting as a pre-CI/CD quality gate.
  • Use Case: After modifying an AI agent's core logic, use this Skill to automatically run a targeted test patrol. It will identify affected tests, execute them statically, and tell you if your changes are safe to proceed to full CI/CD, accelerating your development and ensuring quality.

Quick Start

Use ai-ad-agents-test-orchestrator with "auto" scope for changed files 'agents/agent_core/fe_agent.py' and 'agents/tools/fs_tool.py'.

Frequently Asked Questions about ai-ad-agents-test-orchestrator

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

FAQPage Schema
How do I automatically run tests after AI agent code changes?▼

This Skill orchestrates static test execution by mapping changed files in your agents/ codebase to relevant tests, then invoking ai-ad-agents-test-runner to execute them sequentially without pytest, delivering a BLOCK/ALLOW/WARN quality gate verdict for deployment.

Can I use automated testing to gate AI agent deployments before CI/CD?▼

Yes. This Skill acts as a pre-deployment quality gate, analyzing code changes across agent_core, skills, and tools directories, selecting only affected tests, and providing a clear pass/fail verdict to prevent unsafe deployments.

What's the best way to run targeted regression tests for AI agents?▼

Change-driven test selection automatically identifies tests relevant to your modifications in agents/ or skills/, executes them through static analysis orchestration, and reports coverage assessment and test outcomes without full test-suite overhead.

How does static test orchestration work for AI agent quality assurance?▼

The Skill implements a five-stage read-only workflow: ANALYZE-CHANGES identifies modified files, DISCOVERY maps them to tests, SELECT-TESTS filters by scope, RUN-LOOP executes tests individually, and SUMMARY delivers verdicts—all without writing files or executing pytest directly.

Can I validate AI agent changes locally before submitting pull requests?▼

Yes. The Skill supports quick local validation by accepting changed_files input and optional test_scope parameters, running targeted static-analysis tests immediately, and blocking unsafe changes before PR submission.

What are the limitations of static test orchestration for AI agents?▼

The Skill performs static analysis without executing pytest or writing files, so it cannot verify runtime behavior or side effects. Full CI/CD testing remains necessary for comprehensive validation before production deployment.

Related Skills

Explore More Software Engineering Skills→
aquariuscookaquariuscook

qcsd-cicd-swarm

Analyze CI/CD pipeline test results and output RELEASE, REMEDIATE, or BLOCK decisions.

Community
Advanced
PaulKinlanPaulKinlan
2

regression-check

Run full test suites and compare results against a baseline to detect regressions.

Community
Intermediate
kennyolofsson23-netizenkennyolofsson23-netizen

qa

Run a full QA pass across backend, frontend, ML, and config changes.

Community
Advanced
robkamrobkam
12

full-audit-gate-c

Orchestrate C-language builds, static analysis, valgrind, and pytest quality gates.

Community
Advanced