Review Git changes with the OCR CLI, using either a configured model provider or the host agent for review reasoning.
Testing AI Skills
Find skills for checking software behavior and examining code for defects and security issues.
56 skillsExplore Testing skills
56 skillsSystematically explore and test a web application to find bugs, UX issues, and other problems.
Diagnose WxJava credentials, signatures, certificates, callbacks and multi-account configuration.
Review UI code for Web Interface Guidelines compliance.
Automatically fix broken OpenCLI adapters when commands fail.
Review security boundaries and investigate evidence-backed vulnerabilities across code, APIs, services and command-line tools.
Apply practical large-model training and operations guidance, and evaluate GPU cluster performance and readiness.
Evaluates an ML GPU cluster for a cloud trial or acceptance test: environment dump, isolated newest PyTorch, matmul FLOPS (MAMF/MSMF) on every GPU while the others compute, intra-node all-reduce bandwidth and per-call latency of every collective, the same inter-node on every node you were given (omit those sections if there is only one node), fio on local disk and shared FS, dated markdown report.
Related guides
- Testing Skills for AI Agents: Browser Flows and Headless Tests
Choose a testing Skill for local web app flows, browser interactions or headless Godot test suites.
- Code Review Skills for AI Agents: Diffs, Context and Findings
Compare code review skills for Git changes, graph context, focused findings and visual feedback. Choose a child workflow and give it a clear review boundary.
- Security Skills for AI Agents: Audit, Hardening and Testing
Compare five security Skills for source audits, secure implementation, Skill inspection, and authorized web and API penetration testing.
About Testing AI skills
Find skills for checking software behavior and examining code for defects and security issues.
- Test web applications
- Review code and investigate bugs
- Examine security and quality