Security & Testing Agent Skills for Claude Code

Apply Google Testing on the Toilet (TotT) rules when writing tests, reviewing a test diff, choosing mocks vs fakes, diagnosing brittle or…

Create and audit durable verification and validation evidence for software, documentation, configuration, or operations.

Gate a built v1 to go / no-go on two recorded tests — a true stranger reaches first correct value in ≤60 seconds unaided, AND the…

Diagnosis loop for hard bugs and performance regressions.

Validate AGENTS.md files for structural completeness, operational contract coverage, neutrality, and repository alignment.

Validate that a branch or pull request implementation matches introduced product, technical, security, and related specs.

Use after code changes or before handoff to choose and run validation proportional to risk.

Creates, refactors, and diagnoses Turbo Gherkin feature files for 1C:Enterprise UI automated testing with Vanessa Automation.

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

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits

Prima di dichiarare una task completata, fixata, funzionante o pronta per il deploy, esegui il comando di verifica e leggi l'output.

Use when verification needs bounded claims, evidence, and approval gates.

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

Independently verify one ready-for-verification agent ticket against its scope, repository state, real-interface tests, and fresh evidence.

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.

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 test-program change or conclusion through fresh deterministic evidence and iterative repair.

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