Security & Testing Agent Skills

Run the ProdGuard scanner on a repo to catch the security controls an AI coding agent turns off to make something work.

Verify that browser profiles are actually isolated from one another instead of assuming it - confirm each profile's timezone agrees with…

Auditing an EXISTING software project to detect weaknesses, technical debt, and areas for improvement, evaluating it against 4 pillars…

Run a critical, multi-dimensional quality review of the project using parallel adversarial agents.

Provides guidance for property-based testing across multiple languages and smart contracts.

Apply after completing a task, before declaring done.

Drive PWN::AI::Context from pwn_eval.

Generate synthetic evaluation datasets for the PXI eval harness (evals/pxi/).

Pairwise test generation

Enforces strict Python code quality standards using pytest, mypy, ruff, black, and isort.

Audits Python libraries for security vulnerabilities using Bandit, pip-audit, Semgrep, and detect-secrets.

When to activate: Python security review, OWASP, SQL injection, secrets management, authentication, cryptography

Use this when authoring integration tests against a real backend (PostgreSQL, Redis, Kafka, MinIO, NATS, MongoDB), debugging slow or flaky…

Simulates a multi-perspective QA advisory board to review requirements, technical designs, and test plans while surfacing blind spots and…

Verify claims in a session/PR/transcript against on-disk reality.

Use it when a developer wants to start writing tests for a module, prepare a release, research existing coverage, or…

Implement the "handoff context" produced by qa-discovery in concrete test code. Use it ONLY when a developer has already…

Multi-agent QA review team for code changes.

Generate QA test cases from branch diff and PR body for manual testing handoff.

Design focused QA cases and investigate suspected product defects with Opsphere evidence.

Add Google OAuth login to a Next.js app using NextAuth.js v4 + PrismaAdapter + JWT sessions.