Security & Testing Agent Skills for OpenAI Agents SDK

Manage explicit source approval, exclusion, readmission, retry, and batch validation for Topprismwiki.

Run bin/ci and drive it to green — diagnose every failure, route it to the right fixer (/rspec-test-expert, /fix-system-test, /debug)…

MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, any access to…

Adversarial code review — challenge your code harshly, find what will break in production.

This skill should be used when the user asks to "review my code", "audit this for security", "investigate this bug", "ship this feature"…

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check…

Write property-based tests using Hegel across Rust, Go, C++, TypeScript, Java, and OCaml projects.

Run frontend E2E tests with video evidence.

HIPAA-specific entrypoint for healthcare privacy and security work.

Standardizes high-speed link bench test workflows across AWG, oscilloscopes, DUTs, and LeCroy pre-processing controls.

HIPAA compliance directives for AI-assisted development.

Govern Huawei Cloud SWR (Software Repository for Container) — image retention policy, vulnerability scanning via VSS (Vulnerability Scan…

MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory…

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants…

Use when proactively hunt for adversary abuse of legitimate system binaries

Write, execute, and assert HTTP requests safely using Hurl text files.

Drive and visually inspect a native GUI app (Iced, egui, GTK, winit…) on Hyprland through a headless output, leaving the user's desktop…

Scan the codebase for mission-critical (CbC-mandatory) files and propose cbc=mandatory .gitattributes tags for human ratification

Use when preparing an IEEE S&P (Oakland) artifact-evaluation submission after acceptance, including choosing among the Available…

Use when designing or auditing the evaluation of an IEEE S&P (Oakland) paper, including end-to-end attack demonstration…

Use when hardening the reproducibility of an IEEE S&P (Oakland) paper's evidence before submission, including environment pinning for…