Security & Testing Agent Skills for DeepSeek Harness

Validate CSRF protection implementations for security gaps.

Validate production readiness of Vertex AI Agent Engine deployments

Designs and establishes structured directories, naming conventions, and cleanup rules for new Vanessa Automation BDD testing projects.

Secure-by-default environment variable management for Claude Code sessions.

Manage training data and model artifacts securely on Vast.ai GPU instances.

Mutation-driven test vector generation. Finds implementations of a cryptographic algorithm or protocol, runs mutation testing to identify…

Automated vendor security assessment through questionnaire generation, response parsing, and risk scoring

Implement data handling, PII protection, and GDPR/CCPA compliance for

Fast, precise unit test runner — enforces TDD (RED-GREEN-REFACTOR), runs test suites with coverage, generates test scaffolding, and…

Claiming work is complete without verification is dishonesty, not efficiency.

Use when about to declare work complete, fixed, passing, or done

Help users verify Ethereum state (balances, nonces, storage, code) without trusting their RPC provider using beacon chain light client…

Set a repo up to prove engineering-task work actually works before it ships.

Verify an Obsidian plugin with Node unit tests, typecheck, production build, and Selenium E2E against real Obsidian.

Verify, inspect, discharge, or waive CbC claims for cbc=mandatory artifacts using the evidence ledger

A behavioral skill that forces every claim the agent makes to be evidence-gated and honestly labeled.

Select and execute the verification that actually proves the change works, based on what type of change it is.

Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)

Extracts and verifies the runnability and code coverage of all Python code blocks inside a Markdown file.

Use for a technical incident, disputed diagnosis, bug fix, or claim that a change works.

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED…