Security & Testing Agent Skills for Codex CLI

Use when someone wants to know whether a change actually works and is not AI slop: "test this", "QA it", "write tests for the feature"…

Retrieve and analyze simulation results from a Coval run.

Go testing patterns for Gentleman.Dots, including Bubbletea TUI testing.

5-dimension harness readiness scorecard from `metaharness score <path>`.

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects.

Investigate and fix bugs, failing tests, regressions, build failures, or unexpected behavior using boundary localization, evidence, and…

Set up Playwright in a project. Use when user says "set up playwright", "add e2e tests", "configure playwright", "testing setup", "init…

Streamlines frontend JavaScript reverse engineering and security auditing through automated observation, runtime analysis, and environment…

Use this skill when asked to perform any of the following actions in a Java project: - To add jspecify support - To prevent…

Perform a focused, read-only security review of code, configuration, infrastructure, or a diff.

Validate functional equivalence after migration with side-by-side comparison and behavioral verification

Unified TDD skill with three input modes — from spec, from task, or from description.

Autonomous research-driven application and repository security hardening skill for AI coding agents.

Audits .NET test mock usage by tracing each mock setup through the production code's execution path to find dead, unreachable, redundant…

Reference data for .NET test framework detection patterns, assertion APIs, skip annotations, setup/teardown methods, and common test smell…

Open source license compliance check for a dependency list, a single library, or outbound code.

Analyzes software patches and compares binary versions to identify vulnerabilities and verify security remediations.

Assess Active Directory security posture using PingCastle, BloodHound,

Execute and test GraphQL depth limit attacks using deeply nested recursive

Detect and flag personally identifiable information (PII) in text, code, and configurations.

Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls.