The single canonical dev and debug skill for APEX-OmniHub. Use for developing, debugging, restoring, repairing, scaling, optimizing, or enhancing any OmniHub component. Corrected path registry (live tree is apps/omnihub-site, not src/), two-surface integration ownership, and an all-viewport responsive mandate. Does not cover non-OmniHub products.
Production skill engineering system that forges, audits, and packages agent skills with measured trigger accuracy, hard token budgets, and a marketplace-ready distribution pack (one-line install, before/after README, evidence scorecard). Use whenever the user wants to create, build, improve, audit, optimize, package, or publish a skill — including vague requests like "turn this workflow into a skill". Does not cover MCP server development or general prompt optimization.
Synchronizes external application JSON payloads into unified APEX-OmniHub state vectors for OmniBoard application integration and onboarding. Use when mapping external API schemas, normalizing disjointed app data, or initializing OmniBoard app sync. Does not cover client onboarding, direct database migrations, or CSV/PDF parsing.
apply a repeatable user-shoes validation gate for product surfaces, widgets, modals, agent flows, dashboards, and production rescue work. use when asked to audit, certify, harden, rescue, validate, test like a user, preserve visual quality, prevent product drift, create go/no-go reports, or ensure each ui surface has a functioning, relevant, logical purpose. especially use for apex-omnihub, omnidash, omniboard, links, omnislate, module actions, modal behavior, unsupported states, and visual-preservation reviews.
Elicits a high-rigor reasoning and review discipline — multi-pass verification, adversarial self-check, explicit assumption-tracking — modeled on the publicly documented behavior of a now-retired frontier reviewer model. Use when you want any model to catch subtle bugs, audit its own reasoning, or raise rigor on code, analysis, or decisions. Does not transfer another model's weights, capabilities, or benchmark scores, and is not a replacement for domain skills or tests.
APEX-OMNI-TEST v1.0: 20x omnipotent software testing intelligence. 48 test types: unit, integration, E2E (Playwright), API contract, performance, stress, SAST/DAST, fuzz, snapshot, a11y (WCAG 2.2), visual regression, mutation, chaos, data integrity, AI/LLM behavioral, prompt injection (garak/PyRIT), agent loop, mobile, CLI, smart contract, compliance, observability, synthetic monitoring, GraphQL, WebSocket, gRPC, SBOM (syft/grype), container (Trivy), IaC (checkov), idempotency, ML drift, OAuth/OIDC, RBAC, PII detection, PWA/offline, temporal, i18n. 10 execution modes. 20-item quality rubric. First-pass perfection. Triggers: test QA quality verify validate assert spec coverage regression playwright cypress vitest jest pytest selenium appium k6 broken failing flaky e2e unit integration performance security load stress smoke fuzz audit a11y visual mutation mock stub fixture CI pipeline WCAG OWASP SLO contract chaos graphql grpc websocket sbom trivy checkov garak deepeval promptfoo pii rbac idempotency.
Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).
Portable UI/UX + frontend engineering + debugging operating system. Use when designing screens/flows, auditing usability, implementing frontend UI, creating design systems, fixing UI/state/layout bugs, improving accessibility, or optimizing frontend performance across web/mobile/desktop stacks.