review-interactive
Review code changes in the KPHP compiler and runtime codebase interactively
QA, penetration testing, and code quality.
Review code changes in the KPHP compiler and runtime codebase interactively
HashQL testing strategies including compiletest (UI tests), unit tests, and snapshot tests. Use when writing tests for HashQL code, using //~ annotations, running --bless, debugging test failures, or choosing the right testing approach.
Authorization Code Flow for web applications using MSAL.NET confidential client to sign in users and access APIs on their behalf
Client Credentials Flow for service-to-service (daemon) authentication in MSAL.NET without user involvement
On-Behalf-Of (OBO) Flow for web APIs to call downstream APIs while preserving user identity in MSAL.NET
Use when creating a fake test implementation in stripe-android — covers FakeClassName pattern, Turbine call tracking, ViewActionRecorder, and ensureAllEventsConsumed validation
Use when writing Compose UI tests in stripe-android — covers composeRule setup, Robolectric annotations, node assertions, and test tag patterns
Use when writing or structuring unit tests in stripe-android — covers runScenario pattern, fakes, Turbine Flow testing, and Truth assertions
Audit & fix unit tests for permission-gated components
Run all audit checks (RBAC, hooks, design system, tests) and verify build
Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access controls, complexity, decentralization, documentation, MEV risks, low-level code, and testing. Produces professional scorecard with evidence-based ratings and actionable recommendations. (project, gitignored)
Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias toward deletion.
Clarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are complex (>2 days), or involve cross-team coordination. Ask two core questions - Why? (YAGNI check) and Simpler? (KISS check) - to ensure clarity before coding.
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
Enforce correct form UI patterns when creating or modifying forms in packages/admin. Use when writing form fields, edit drawers, create modals, or any form-based UI in the admin package. Covers Form.Field pattern, labels, errors, hints, grids, submit guards, drawer/modal structure.
Review admin UI code for consistency with established patterns. Use after writing any UI code in packages/admin to catch anti-patterns — wrong form components, hardcoded strings, missing i18n, incorrect heading levels, manual error rendering, missing data-testid, raw Controller usage.
Review code changes for contract compliance, type safety, and regression risk. Use after completing any non-trivial implementation, before merging PRs, or when asked to review code quality across any mercur package.
Write tests that verify observable behavior (contract), not implementation details. Auto-invoked when writing or reviewing tests.
GROWI testing patterns with Vitest, React Testing Library, and vitest-mock-extended.