Security & Testing Agent Skills for DeepSeek Harness

When to activate: pytest plugins, conftest, custom markers, test architecture, fixtures design, pytest-xdist, coverage strategies

Use when iterating on a fix after an adversarial code review (Codex, human reviewer) surfaces design-level findings — not typos, lint, or…

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.

Adversarial code review that breaks the self-review monoculture.

Entry point for the Adversis security plugin.

Full-stack diagnostic for agent and LLM applications.

Testing and benchmarking LLM agents including behavioral testing,

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks.

Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.

Audits and validates AI agent skills against strict structural and pre-release packaging checklists.

Full agent verification suite. Runs security, patterns, quality, and language-specific checks. Use when asked to "verify agent", "verify…

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI…

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

Regression testing strategies for AI-assisted development.

The Definitive Guide and Engineering Patterns for Opengrep (opengrep.dev), covering the open-source static code analysis engine (SAST)...

This skill should be used when the user asks "is this regex safe", "what is ReDoS", "why does CPU spike on one request", "how do I safely…

Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular…

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari"…

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create…

Use when a security incident has been detected or declared and needs classification, triage, escalation path determination, and forensic…