Security review skill for the vykar backup tool (Rust). Use when reviewing code for security issues, auditing cryptographic implementations, checking for credential leaks, reviewing unsafe code, or validating the security model of the backup tool. Covers encryption, key management, repository integrity, hook execution, config parsing, dependency auditing, and backup-specific attack surfaces.
Implement the requested changes. Write production-ready code, follow existing patterns, and run tests to verify your work.
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end across issue-tracker, EdgeWorker, and activity rendering.
Run all quality checks (tests, lint, typecheck), fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
Use when writing or editing config.yaml. Chain/contract structure, addresses, start_block, event selection, field_selection, custom event names, env vars, address_format, schema/output paths, YAML validation, and deprecated options.
Write and run tests for HyperIndex indexers using Vitest and createTestIndexer(). Covers test setup, processing block ranges, asserting entity changes with toMatchInlineSnapshot, and TDD workflow. Use when writing tests, debugging handler output, or verifying indexer behavior.
Set up or tune .codemap/config.json so Codemap focuses on code-relevant parts of the repo. Use when config is missing, boilerplate, noisy, or mismatched to the stack.
Write spec-aligned Dada tests. Use when creating new test files, organizing tests to match the specification, or adding test coverage for language features.
Use this agent when working with prompt injection detection integration tests, including running tests, debugging failures, or adding new test samples.
Handles all Golang testing tasks including running tests, writing new tests, and fixing test failures. Follows MCPSpy testing conventions with require for critical assertions and assert for non-critical ones.
Получение валидных JWT Bearer токенов для аутентификации MikoPBX REST API v3. Использовать когда нужно тестировать API эндпоинты, отлаживать проблемы аутентификации или при возникновении ошибок 401 Unauthorized. Автоматически обрабатывает вход с username/password и возвращает готовый к использованию access token.
Use when writing, editing, or reviewing agent e2e tests in packages/core/assistant-e2e. Use when creating new test files in the testing/ directory, adding test cases, or fixing failing agent e2e tests.
Regenerate cached LLM responses for tests that use memoized conversations. Use when tests fail with "No memoized conversation found for the given prompt", when fixing or adding memoized-llm tests, or when the user asks to regenerate or update LLM conversation cache.
Test assistant conversations, agents, and blueprints using AssistantTestLayer, Effect/vitest, ECHO types, and memoized LLM fixtures. Use when writing or fixing assistant-toolkit tests, blueprint.operation tests, AiConversation flows, or when CI fails on missing memoized conversations.
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling. Use PROACTIVELY for any TypeScript/JavaScript issues including complex type gymnastics, build performance, debugging, and architectural decisions. If a specialized expert is a better fit, I will recommend switching and stop.
Detect and remove hollow AI filler language, empty superlatives, and vague boosters that degrade Seedance 2.0 prompt quality. Use when a prompt feels generic, over-written, or 'AI-sounding', or when generation output looks bland and needs a quality pass.
Lock character identity, assign @Tag references, and maintain face and hand consistency across multi-character scenes in Seedance 2.0. Covers 360-degree consistency testing and first-frame art direction for image-to-video. Use when a character changes appearance between shots, when building multi-person scenes, or when hands or faces are distorting.
'Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.'
Write automated tests for features, validate functionality against acceptance criteria, and ensure code coverage. Use when writing test code, verifying functionality, or adding test coverage to existing code.
