pr-test-analyzer

What This Skill Does

The pr-test-analyzer is an intelligent agent skill designed to audit pull requests for insufficient testing. It bridges the gap between raw code changes and robust verification by mapping modifications to their corresponding test suites. By evaluating coverage through the lens of behavioral verification rather than just line-by-line metrics, it ensures that your PRs are resilient, maintainable, and regression-proof. The analyzer identifies high-risk areas—such as security flaws, data persistence errors, and edge-case failures—and generates a structured report prioritizing fixes by severity, ranging from mission-critical security patches to useful edge-case hardening.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/anton-abyzov/sw-pr-test-analyzer Ensure you have the necessary repository permissions configured within OpenClaw to allow the agent access to your codebase.

Use Cases

• PR Auditing: Quickly assess if a developer has included adequate tests for complex logic changes.
• Refactoring Safety: Use the analyzer before merging major refactors to verify that existing behavior remains consistent.
• Onboarding Assistance: Help junior developers understand the required testing standards by providing objective feedback on their PRs.
• CI/CD Optimization: Identify which code paths are frequently missed in automated test suites, allowing for strategic test suite expansion.

Example Prompts

1. "Analyze the current PR changes and generate a coverage gap report for all files modified in the last commit."
2. "Review the authentication service updates in this PR. Are there any edge cases regarding expired tokens or malformed headers that we are missing?"
3. "Evaluate the test coverage for the new payment gateway integration and list any critical paths currently lacking unit or integration tests."

Tips & Limitations

• Behavioral Focus: The agent prioritizes functional outcomes. If your test suite is heavily tied to implementation details, the agent may suggest refactoring tests to be more resilient.
• Context Awareness: The analyzer is most effective when the codebase follows standard naming conventions (e.g., src/foo.ts mapping to tests/foo.test.ts). If your project uses a non-standard structure, provide a brief mapping context to the agent.
• Manual Verification: While highly accurate, the analyzer's output should be reviewed by a human senior developer to verify the business logic context, especially in complex system architectures.