deep-codebase-audit
Explore a codebase like an AI would, surface architectural friction, and propose deep-module changes that improve testability and agent-friendliness.
docs-code-samples
Use this skill when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted with Bluehawk and used as Mintlify snippets. Applies when extracting code blocks from documentation, creating runnable code samples, using snippet delineators, or wiring Bluehawk output into MDX includes.
android-concurrency
Standards for Coroutines, Flow, and Threading. Use when writing suspend functions, choosing coroutine scopes, switching between StateFlow and SharedFlow, injecting Dispatchers for testability, or debugging threading issues in Android. (triggers: **/*ViewModel.kt, **/*UseCase.kt, **/*Repository.kt, suspend, viewModelScope, lifecycleScope, Flow, coroutine, Dispatcher, DispatcherProvider, GlobalScope)
Acceptance Criteria
Acceptance criteria define the observable behavior that must be true for a story or feature to be considered done. This skill turns feature context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent.
HTTP Security Header Audit
Checks a site's response headers against modern web-security best practices and returns prioritized findings with concrete fixes. The analysis core is pure and offline-testable; live scanning uses only Python's stdlib `urllib`.