ayia

Manage the AI coaching system for NutriProfile. Use this skill when working with personalized nutrition advice, daily tips, motivational messages, challenges, or the coaching features. Handles user context, streak management, and gamification integration.

Design and implement REST API endpoints for NutriProfile. Use this skill when creating new endpoints, modifying API schemas, working with Pydantic models, or ensuring OpenAPI compliance. Follows FastAPI best practices.

Manage PostgreSQL database for NutriProfile. Use this skill when working with SQLAlchemy models, Alembic migrations, query optimization, or database schema changes. Covers async operations and Fly Postgres deployment.

Deploy NutriProfile to production. Use this skill when deploying backend to Fly.io, frontend to Cloudflare Pages, managing secrets, running health checks, or troubleshooting deployment issues.

Manage internationalization for NutriProfile's 7 languages. Use this skill when adding translations, creating new i18n keys, checking translation coverage, or working with RTL support for Arabic. Ensures consistency across FR, EN, DE, ES, PT, ZH, AR.

Analyze food items and calculate nutritional values for NutriProfile. Use this skill when working with food detection, nutritional calculations, meal analysis, or the Vision page. Covers calories, proteins, carbs, fats, and portion estimation.

Generate and manage AI-powered recipes for NutriProfile. Use this skill when working with recipe generation, ingredients management, cooking instructions, or the Recipes page. Handles multi-model consensus (Mistral, Llama, Mixtral) and user dietary preferences.

Implement mobile-first responsive design for NutriProfile. Use this skill when working on UI components, fixing layout issues, ensuring touch targets, or optimizing for different screen sizes (375px to 1920px+). Uses Tailwind CSS breakpoints.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Interactive chat tester for Alysse. Has a REAL adaptive conversation with a character (40-50 messages SFW+NSFW), scores on 10 human-feel dimensions + 8 hard floors + memory deep-test, learns from past tests, and iterates fixes until READY. **Use when:** - Testing a character's chat quality - After modifying a character config - After any chat/memory/LLM code change - Validating a new or cloned character **Trigger phrases:** "test chat", "chat QA", "interactive test", "test valentina", "test the chat" **Examples:** <example> user: "test chat on valentina" assistant: "Launching chat-tester for interactive Valentina chat quality test." </example> <example> user: "/chat-tester amara-diallo en fr" assistant: "Testing Amara Diallo in English and French." </example>

Deploy or refresh a RunPod vLLM pod for Alysse production, mirroring the B3G dev server config (Cydonia-24B-v4.3-AWQ + transformers 5.5.0). Picks the cheapest GPU under $0.18/hr (RTX A5000 24GB), installs the exact stack that produces the chat quality the user has tuned for, and updates the Fly.io VLLM_BASE_URL secret. TRIGGER when: user says "create runpod pod", "redeploy vllm", "fix prod chat", "the runpod is dead", or "match B3G config".

Generate one or more /meet gallery images for an Alysse character using the full Valentina-grade pipeline: scene spec → RunPod Hub LoRA generation → visual validation → R2 upload → old-key cleanup → manifest update. Captures every lesson learned during the 22-character gallery rebuild (May 2026). TRIGGER when: user says "generate gallery image for X", "create new gallery for Y", "redo X's gallery image N", "add a new pose to Z", "regenerate X gallery", or any variation of producing character meet-page imagery.