Security & Testing Agent Skills for OpenAI Agents SDK

/cs:iso27001-audit-prep <scope> — ISO 27001 ISMS audit readiness 6-question forcing interrogation.

Expert skill for GPU debugging using CUDA-GDB and NVIDIA Compute Sanitizer.

Find the most appropriate CWE for the vulnerability using the Varsel MCP's local CWE catalog, then propose it onto the case.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Systematic debugging frameworks for finding and fixing bugs - includes root cause analysis, defense-in-depth validation, and verification…

Create, review, and harden GitHub Dependabot configuration for new or existing repositories.

Use when the user asks to "add a dependency", "vet a license", "check if this package is safe to use", "can we use this library", "add…

Deploys Palo Alto Networks Prisma Access for SASE-based zero trust network access, configuring GlobalProtect agents, ZTNA Connectors…

Deploy AI and NLP-powered detection systems to identify business email

Detect abuse of elevation control mechanisms (T1548), including Windows UAC

Docker-based test environment management for isolated, reproducible test execution.

Write resilient Playwright e2e tests and testable React UIs.

Orchestrate E2E test triage and fix implementation: runs triage-ci then implement sequentially.

Index of engineering failure-mode skills — routes to the right one for evidence-driven bug hunting, fuzzing, data correctness, resilience…

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Validate EV code signing certificate chain and timestamp for Windows SmartScreen

Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.

PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas.

Find and fix bugs worth fixing instead of inventing hypothetical edge cases.

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"…