Standalone agent skills for Claude Code that cover system design, architecture documentation, decision records and diagrams. Each skill keeps its scope narrow, such as recording one decision or documenting current architecture without proposing a target.
@levnikolaevichEvaluates new product opportunities through demand, channels and economics before committing to build.
@levnikolaevichDefines product requirements, business rules and acceptance criteria for a committed intent; edits product docs only.
@levnikolaevichDesigns user flows, interaction states and mockups for a defined product scope; does not implement UI code.
@levnikolaevichDefines measurable architecture drivers and constraints before system design; edits architecture docs only.
@levnikolaevichDocuments current architecture from implementation evidence; does not propose a target or audit fitness.
@levnikolaevichDesigns target system boundaries, contracts and tradeoffs from requirements; does not plan tasks or implement.
@levnikolaevichRecords one architecture decision with alternatives, consequences and status; does not design the whole system.
@levnikolaevichCreates evidence-backed current or target architecture diagrams; not UI design.
@levnikolaevichPlans architecture migrations with compatibility, data safety, rollout and recovery; does not execute them.
@levnikolaevichBuilds dependency-ordered delivery plans from requirements and repository evidence; read-only.
@levnikolaevichPlans risk-based test portfolios and acceptance evidence; does not write or execute tests.
@levnikolaevichReviews a concrete implementation plan for missing decisions, feasibility and risk before execution; read-only.
@levnikolaevichIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
