amoa-verification-patterns
Use when verifying implementations. Trigger with verification, testing, or evidence requests. Loaded by ai-maestro-orchestrator-agent-main-agent
Best use case
amoa-verification-patterns is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when verifying implementations. Trigger with verification, testing, or evidence requests. Loaded by ai-maestro-orchestrator-agent-main-agent
Teams using amoa-verification-patterns should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/amoa-verification-patterns/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How amoa-verification-patterns Compares
| Feature / Agent | amoa-verification-patterns | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when verifying implementations. Trigger with verification, testing, or evidence requests. Loaded by ai-maestro-orchestrator-agent-main-agent
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Verification Patterns for AMOA
## Overview
Evidence-based verification for proving code and systems work correctly. Collect measurable, reproducible evidence -- not assumptions.
## Prerequisites
- Python 3.8+, Bash, Git
- Optional: Selenium (E2E), Docker (containerized tests), SQLite/PostgreSQL (integration)
## Output
Verification reports with pass/fail status, collected evidence, and formatted results per test-report-format.md.
## Core Patterns
1. **Evidence-based** -- [evidence-based-verification.md](./references/evidence-based-verification.md)
<!-- TOC: What is Evidence | Evidence-Based Verification Steps -->
2. **Exit code proof** -- [exit-code-proof.md](./references/exit-code-proof.md)
<!-- TOC: What is an Exit Code | Exit Code Proof Steps -->
3. **E2E testing** -- [end-to-end-testing.md](./references/end-to-end-testing.md)
<!-- TOC: What is E2E Testing | E2E Testing Steps -->
4. **Integration** -- [integration-verification.md](./references/integration-verification.md)
<!-- TOC: What is Integration Verification | Integration Verification Steps -->
## Principles
See: [verification-principles.md](./references/verification-principles.md)
<!-- TOC: Principle 1: Never Trust Assumptions | Principle 2: Measure What Matters | Principle 3: Reproducibility | Principle 4: Fail Fast | Principle 5: Document Evidence -->
## Instructions
1. Select the appropriate verification pattern (evidence-based, exit code, E2E, or integration)
2. Set up the test environment per testing-protocol.md
3. Execute verification and collect measurable evidence
4. Format results per evidence-format.md and test-report-format.md
5. Report pass/fail with evidence; escalate failures immediately (fail-fast)
6. Update GitHub issues per github-integration.md and clean up test environment
Copy this checklist and track your progress:
- [ ] Select pattern, set up environment
- [ ] Execute verification, collect evidence
- [ ] Format results, report pass/fail
- [ ] Update GitHub issues, clean up
## Examples
**Input:** Agent receives verification request for a new function.
**Output:** Verification report with pass/fail, collected evidence, formatted results.
See [examples.md](./references/examples.md) for worked examples.
<!-- TOC: Example 1: Evidence-Based Verification | Example 2: Exit Code Proof -->
## Resources
- [combining-patterns.md](./references/combining-patterns.md) -- Combining patterns
- 5.1 Pattern Combinations
- 5.2 Verification Pyramid
- 5.3 Complete Verification Strategy Example
- [cross-platform-support.md](./references/cross-platform-support.md) -- Cross-platform
- 6.1 Platform-Specific Behavior
- 6.2 UTF-8 Encoding
- 6.3 Platform Detection
- 6.4 Path Handling
- ...
- [troubleshooting.md](./references/troubleshooting.md) -- Troubleshooting
- 10.1 Tests Pass Locally but Fail in CI/CD
- 10.2 Exit Code is 0 but Process Failed
- 10.3 Integration Test Fails with Timeout
- 10.4 E2E Test is Flaky
- ...
- [docker-troubleshooting.md](./references/docker-troubleshooting.md) -- Docker
- 1. Assessing Docker Container Needs for a Project
- 2. Selecting Appropriate Base Images
- 3. Applying Docker Best Practices
- 4. Configuring Multi-Service Environments
- ...
- [quick-reference.md](./references/quick-reference.md) -- Quick reference & checklist
- Pattern Selection Guide
- Exit Codes
- Output Format
- Error Handling
- ...
## Error Handling
Fail-fast: failures propagate immediately, no fallbacks. See troubleshooting.md and docker-troubleshooting.md in Resources.Related Skills
amoa-two-phase-mode
Use when running Plan-then-Execute workflows. Trigger with plan-execute or two-phase requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-task-distribution
Use when distributing tasks. Trigger with task assignment requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-remote-agent-coordinator
Use when coordinating remote AI agents via AI Maestro messaging. NOT for human coordination. Trigger with agent delegation or multi-agent requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-progress-monitoring
Use when monitoring agent progress. Trigger with status check or stall detection requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-plan-phase
Use when running Plan Phase of two-phase mode. Trigger with planning, requirements, or plan approval requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-orchestration-patterns
Use when breaking down tasks for human developers. Trigger with task decomposition requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-orchestration-loop
Use when running the orchestrator loop or managing stop hook behavior. Trigger with loop, stop hook, or state file requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-module-sync
Use when syncing modules with GitHub Issues or troubleshooting module state. Trigger with sync, issue, or module troubleshooting requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-module-management
Use when managing modules during Orchestration Phase. Trigger with module add, modify, or reassign requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-module-lifecycle
Use when adding, modifying, removing, prioritizing, or reassigning modules. Trigger with module CRUD requests. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-messaging-templates
Use when sending inter-agent messages. Trigger with task assignment, status report, or escalation needs. Loaded by ai-maestro-orchestrator-agent-main-agent
amoa-label-taxonomy
Use when applying GitHub labels. Trigger with label query or assignment requests. Loaded by ai-maestro-orchestrator-agent-main-agent