An automated full-stack quality verification engine that prioritizes real execution over mocks to ensure production-ready code delivery.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install post-dev-verification
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install post-dev-verification using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Post-Development Verification?
Post-Development Verification is a sophisticated Openclaw Skills module designed to handle the critical transition from code completion to deployment. It operates on a real execution first philosophy, meaning it prefers running internal services and databases over using mocks. This ensures that the AI agent validates software through actual HTTP requests, CLI invocations, and browser interactions rather than just isolated function tests.
By implementing a multi-layered quality gate system, this skill evaluates development tasks against four distinct metric layers: Design, Execution, Delivery, and Iteration Efficiency. It systematically eliminates common testing anti-patterns and provides a feedback-driven loop to automatically fix code failures until it meets 100% of the core business requirements.
Post-Development Verification Use Cases
- Automatically triggering full-stack validation after an AI agent completes a development task.
- Running comprehensive quality checks before creating pull requests or merging code.
- Validating complex business flows that require real database migrations and service orchestration.
- Performing regression testing after major refactors or bug fixes to ensure 100% safety.
- Generating reusable test scripts that are compatible with existing CI/CD pipelines.
How Post-Development Verification Works
- Environment Awareness: The skill analyzes the project structure, detects the tech stack, and determines the maximum possible realism level (L0 to L3) for testing.
- Test Design: It maps requirements to a specific test taxonomy (MFT, INV, DIR) and scans for anti-patterns like Happy Path Obsession before writing a single line of code.
- Execution & Evaluation: Services are started in a sandbox environment, and tests are executed using the project's native runner, capturing real-world metrics and coverage.
- Feedback & Fix Loop: If quality gates fail, the skill generates a detailed feedback report, prioritizes the largest failure clusters, and attempts to fix the code automatically.
- Validation: A final round of hidden tests is performed to ensure the fixes are genuine and not overfitted to the initial test cases.
Post-Development Verification Setup
To integrate this into your workflow, ensure your environment meets the following requirements:
# Ensure Docker is available for L2/L3 realism levels
docker --version
# The skill automatically detects package managers
# Supported: npm, pip, mvn, go
# Run the environment analysis (Phase 0) to verify compatibility
openclaw run post-dev-verification --phase 0
Post-Development Verification Data Schema & Taxonomy
The skill organizes its output into structured reports and artifacts:
| Artifact | Format | Description |
|---|---|---|
| Environment Report | Markdown | Details detected framework, test runner, and service availability. |
| Test Plan | Markdown | List of MFT/INV/DIR scenarios and real vs. mock classification. |
| Feedback Report | JSON | Diagnostic data for the fix loop, including metric pass/fail status. |
| Quality Report | Markdown | The final verdict (PASS/FAIL) with a summary of all 15 quality metrics. |
| Test Scripts | Native Code | Reusable scripts (e.g., .js, .py) generated in the project's native format. |
Post-Development Verification Advanced Features
- Multi-level realism scaling (L0-L3) based on environment capabilities and user intent.
- Automated detection of 5 major testing anti-patterns including Leap-to-Code and Hallucinated Dependencies.
- Hidden Test Separation: Reserves 30-40% of tests to prevent the AI from overfitting solutions during the fix loop.
- Convergence Control: Automatically stops the fix loop if the regression rate is too high or fixes aren't converging.
- Full-stack orchestration: Manages service lifecycles, health checks, and database seeding within test environments.
SKILL.md
Loading
Related Openclaw Skills
Using Harness
A mandatory governance framework for forcing structured task decomposition, routing, and package-first execution within AI agent environments.
Seedream5.0 Image Generation
A high-performance AI image generation skill for creating professional posters, illustrations, and reference-based visuals via the Seedream5.0 API.
WanXiang 2.6 Text-to-Image Generator
A specialized AI image generation skill leveraging Alibaba's WanXiang 2.6 model to create professional WeChat covers and technical architecture visualizations.
flomo-sync
A streamlined automation skill designed to instantly synchronize text, links, and tags from your AI agent directly to your flomo notes.
Gate Exchange Activity Center
A comprehensive campaign hub for discovering trading competitions, airdrops, and personalized activity rewards on the Gate platform.
Gate News Listing Tracker
An automated crypto exchange announcement tracker that provides detailed listing reports with fundamental and market data.
Featured*
