Documents observed or proposed software architecture with evidence-backed context, container, component, dynamic, data-flow, and deployment views. Use when the user needs architecture diagrams, onboarding material, trust boundaries, or a design view before a…
Issues an evidence-backed READY, READY WITH WARNINGS, or BLOCKED verdict using only release dimensions relevant to the artifact and its risks. Use before shipping, merging, publishing, or declaring a software task complete.
Routes ambiguous software-work requests to the smallest useful workflow after checking intent, lifecycle stage, risk, evidence, cost, and available capabilities. Use when the user asks what to do next, invokes concierge, or no single specialist clearly owns…
Turns a vague software request into a compact implementation brief with actors, triggers, preconditions, behavior, failures, permissions, data effects, edge cases, and observable acceptance conditions. Use before planning when product intent or scope is…
Reconstructs a reference interface from screenshots, URLs, or design exports by measuring layout, type, spacing, color, imagery, borders, shadows, responsive behavior, states, and content. Use when the user asks to reproduce an existing design faithfully.
Audits and improves web discoverability across crawlability, HTTP status, rendering, indexability, canonical metadata, titles, descriptions, internal links, sitemaps, robots rules, social previews, and eligible structured data. Use for technical SEO without…
Diagnoses and improves usability by walking real user tasks, finding hesitation, backtracking, errors, recovery gaps, accessibility barriers, and inefficient paths. Use for UX audits, onboarding, forms, navigation, error messages, or confusing flows.
Creates or improves a repository README for prospective users, evaluators, and contributors using verified product facts, executable commands, examples, and links. Use when the repository front page is missing, stale, unclear, or overrun by internal detail.