Testing Skill Leaderboard

An Android red-team pipeline that automates APK acquisition, jadx decompilation, secret grepping, and Frida instrumentation templates.

Browser automation using Playwright for UX validation, responsive checks, and automated web testing.

Six skills that apply Lighthouse audit criteria to performance, Core Web Vitals, accessibility, SEO, and best practices, including a combined web quality audit.

Diagnose-first guidance for Terraform/OpenTofu: identifies failure modes, proposes risk-controlled remediation, and enforces a response contract with validation and rollback plans.

Implements a think-act-prove orchestration method for AI agents featuring domain research and adversarial verification of outputs.

Scans Xcode projects for App Store rejection patterns using app-type checklists and asc CLI metadata. Outputs severity-ordered reports with fix suggestions for metadata, subscriptions, privacy, entitlements, and design compliance.

Five guard skills for reviewing AI-generated code, documentation, tests, WordPress plugins, and WooCommerce extensions against systematic failure modes.

Provides language-agnostic coding principles, backend technical decision criteria, and anti-pattern detection for code reviews and feature implementation.

An evidence-first development skill that uses executable specs, coverage, and mutation testing to ensure high-assurance code reliability.

Expert guidance for Swift Testing covering test structure, #expect/#require macros, traits, parameterized tests, parallel execution, async waiting, and XCTest migration.

A meta-skill for researching, packaging, evaluating, and publishing governed Qiaomu agent skills from existing workflows and scripts.

Conducts maintainability audits by scanning for code and test smells, measuring structure metrics, and reporting technical debt with evidence.

Forces heavy token consumption for LLM backend stress testing, A/B testing, cost modeling, and autoscaling validation. Supports four computation loads from small to xlarge.

A management tool to create, evaluate, optimize, and package agent skills through a test-and-improve lifecycle.

Testing workflow skill with scan, test, workload, review, and doctor modes for prioritizing test candidates, writing focused tests, generating adversarial workloads, reviewing test value, and diagnosing test-suite health.

Uses three isolated subagents—Hunter, Skeptic, Referee—to find, challenge, and verify code bugs, delivering a severity-sorted report of confirmed findings.