Menu
Use when discussing architecture, adding features, or understanding fancai project structure. Provides technology overview and conventions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Deploy fancai to production VPS. Use when deploying, shipping, or pushing to production.
Create and run database migrations for fancai. Use when changing database schema, adding columns, creating tables, or modifying SQLAlchemy models.
Debug Celery task failures, memory issues, and queue problems. Use when celery tasks fail, book processing hangs, image generation times out, or workers consume too much memory.
Debug and improve the entity extraction, deduplication, and spoiler-free pipeline. Use when entities are missing, duplicated, have wrong spoiler levels, or chunk boundary issues occur.
Respond to production incidents on fancai.ru. Use when the site is down, slow, returning errors, or AI features are broken.
Monitor and debug OpenRouter AI pipeline health, costs, rate limits, model availability. Use when AI features fail, images don't generate, or LLM responses are degraded.
| name | tech-stack |
| description | Use when discussing architecture, adding features, or understanding fancai project structure. Provides technology overview and conventions. |
Fiction reader with AI illustrations and interactive entity glossary/wiki. Two core AI features: image generation from descriptions + spoiler-free entity encyclopedia (characters, locations, objects) with chapter tracking.
src/components/Reader/ — EPUB reader (22 files)src/components/Entities/ — Entity glossary UI (12 files)src/hooks/api/ — TanStack Query hooks (8 files)src/hooks/epub/ — EPUB functionality (26 files)src/services/ — IndexedDB cachingapp/services/book_parser.py — EPUB/FB2 parsingapp/services/gemini_extractor.py — Description extraction via OpenRouterapp/services/entity_service.py — Entity network, spoiler-free filteringapp/services/entity_deduplication_service.py — Fuzzy + LLM dedupapp/core/openrouter_client.py — Unified AI client (generate_text, generate_structured, generate_image)app/routers/books/ — Subpackage (crud.py, entities.py, processing.py, validation.py)All AI via OpenRouter (backend/app/core/openrouter_client.py):
# Frontend
cd frontend && npm run dev # Development
cd frontend && npm test # Tests
cd frontend && npm run build # Build
# Backend
cd backend && uv run python -m pytest -v # Tests
cd backend && alembic upgrade head # Migrations
docker compose up -d # Start all services (NOT docker-compose)
<type>(<scope>): <subject>
Types: feat, fix, docs, style, refactor, test, chore
docker-compose.prod.ymldocker-compose.dev.yml