- Home
- Skills
- Code Quality & Review
- Test Gap Finder
Works with the AI Agents you already use
Test Gap Finder
Audit implementation behavior against test suites to find critical gaps in edge cases, security, and state transitions.
$9.99
Test Gap Finder
Example session with this skill installed
Analyze the test coverage for this PR diff. I've added a new payment retry logic, but I'm worried about duplicate charges and database timeouts. Here are the implementation and test files.
- Read your context and instructions
- Compiled the test gap finder
Verdict: Material test gaps. Score: 65/100. Critical Gap: No test for idempotency when a timeout occurs after a successful charge but before the DB update. Recommendation: Add an integration test simulating a 504 Gateway Timeout post-authorization to verify the idempotency key prevents re-billing.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
High code coverage percentages often mask critical missing tests for edge cases, race conditions, and security boundaries. Developers frequently ship features that pass CI but fail in production due to untested failure paths or tenant isolation leaks.
What it does
- Analyzes code changes and PR diffs against existing test suites to find behavioral gaps.
- Maps implementation logic to a behavior-to-test matrix to identify unprotected state transitions.
- Audits coverage for high-risk areas including concurrency, retries, rollbacks, and cross-tenant permissions.
- Provides a prioritized list of specific test recommendations categorized by severity (Critical to Low).
- Calculates a 100-point test evidence score and issues a release-readiness verdict.
Frameworks & tools
Works with any testing framework including Jest, Vitest, Playwright, Pytest, and JUnit. Compatible with unit, integration, contract, and E2E test suites.
Why this beats prompting it yourself
General LLM prompts often miss subtle infrastructure risks like dead-letter routing or idempotent retries. This skill follows a 24-step audit workflow that forces inspection of boundary conditions and integration assumptions that standard coverage tools ignore.
Use cases
- Reviewing a PR to ensure a bug fix includes a valid regression test.
- Identifying missing permission checks before deploying multi-tenant API changes.
- Finding shallow assertions that provide false confidence without verifying side effects.
- Determining if a complex data migration has sufficient rollback and integrity tests.
Known limitations
Does not execute code or run tests locally. Analysis is based purely on provided implementation files, diffs, and test code.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Does not execute code, run builds, or perform runtime analysis. Analysis quality depends on the provided implementation and test code visibility.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
No special permissions declared or detected