project-overview
Background knowledge about CaCrFeedFormula project architecture, features, and context. Automatically loaded for AI reference, not directly user-invocable.
Best use case
project-overview is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Background knowledge about CaCrFeedFormula project architecture, features, and context. Automatically loaded for AI reference, not directly user-invocable.
Teams using project-overview should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/project-overview/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How project-overview Compares
| Feature / Agent | project-overview | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Background knowledge about CaCrFeedFormula project architecture, features, and context. Automatically loaded for AI reference, not directly user-invocable.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# CaCrFeedFormula Project Overview
**Intelligent Feed Formula Optimization System** built with Tauri + Rust + React TypeScript.
## Project Context
**CaCrFeedFormula** is an industrial-grade desktop application for feed formula optimization, integrating AI-assisted optimization, linear programming (HiGHS solver), and comprehensive feed management capabilities.
### Core Technology Stack
**Backend (Rust 2021)**:
- **Framework**: Tauri 2.9.0 + Tokio 1.37 (full async runtime)
- **Database**: SQLite + SQLx 0.7 (compile-time type safety)
- **Optimization**: HiGHS 1.12 (industrial-grade LP solver)
- **Caching**: Moka 0.12 (high-performance concurrent cache)
- **Type Binding**: specta 2.0 + tauri-specta 2.0 (auto TypeScript generation)
- **AI Integration**: reqwest + eventsource-stream (streaming responses)
- **Parallel Compute**: Rayon 1.8
**Frontend (React 19.1 + TypeScript 5.8)**:
- **UI Framework**: Ant Design 5.26 + Tailwind CSS 4.1
- **State Management**: TanStack Query 5.17
- **Build Tool**: Vite 7.0
- **Visualization**: Recharts 2.15
- **Animation**: Framer Motion 11
## Project Structure
```
cacrfeedformula/
├── src/ # Rust backend source
│ ├── ai/ # AI service module
│ ├── database/ # Database connection
│ ├── formula/ # Formula optimization core
│ ├── material/ # Material management
│ ├── species/ # Species management
│ ├── factory/ # Factory management
│ ├── premix/ # Premix design
│ ├── profit/ # Profit/loss analysis
│ ├── prediction/ # Nutrition prediction
│ ├── production_batch/ # Production batch management
│ └── system/ # System services
├── frontend/ # React frontend source
│ └── src/
│ ├── components/ # React components
│ │ ├── AIChat/ # AI chat component
│ │ └── common/ # Common components
│ └── bindings.ts # Auto-generated type bindings
├── migrations/ # Database migrations
└── .claude/
├── skills/ # Custom Claude Code skills
└── rules/ # Detailed development standards
```
## Core Features
### 1. Formula Optimization System
- Linear programming optimization (cost minimization)
- Manual formula design
- Premix reverse calculation design
- Formula version management
- Formula analysis and reporting
- **167 Tauri commands** for comprehensive formula operations
### 2. Data Management
- Material management (built-in China Feed Composition & Nutrition Value Database)
- Species management (multiple species, growth stages, nutrition standards)
- Factory management (multi-factory data isolation)
- Production batch management (batch lifecycle, material requirement calculation)
- Inventory management (stock check, variance analysis, purchase planning)
### 3. Analysis & Decision Support
- Profit/loss analysis (comprehensive cost accounting, real-time P&L)
- Nutrition prediction (NRC-based energy prediction)
- Sensitivity analysis (shadow prices, bottleneck constraint identification)
### 4. AI Intelligent Assistant
- Context-aware professional feed formula consultation
- Streaming responses with typewriter effect
- Multi-turn conversations
- Supports OpenAI, DeepSeek, OpenRouter platforms
## Project Characteristics
1. **Desktop Application**: Not a web app; cross-platform desktop app built with Tauri
2. **High-Performance Computing**: Rust backend ensures speed and stability
3. **Type Safety**: specta auto-generates TypeScript types, ensuring frontend-backend type consistency
4. **Async-First**: Comprehensive use of Tokio async runtime
5. **Industrial-Grade Optimization**: HiGHS solver supports large-scale formula optimization
6. **AI Integration**: Streaming AI responses with real-time typewriter effect
## Development Workflow Context
### Typical Development Scenarios:
- **Formula Engine**: Implementing complex linear programming algorithms with HiGHS
- **Material Database**: Managing large datasets with SQLite + SQLx
- **Desktop UI**: Building responsive Ant Design interfaces with React 19
- **Tauri Commands**: Creating type-safe Rust ↔ TypeScript communication
- **AI Features**: Integrating streaming AI responses into desktop workflows
- **Batch Processing**: Handling production batch calculations and scheduling
### Key Integration Points:
- **Rust ↔ TypeScript**: specta generates bindings.ts after every Rust change
- **Database ↔ Business Logic**: SQLx macros provide compile-time SQL validation
- **Frontend ↔ Backend**: TanStack Query manages server state via Tauri commands
- **AI ↔ User**: Streaming SSE responses with real-time UI updates
## Project Scale
- **167 Tauri commands** across 10 modules
- **Comprehensive feed database** with 1000+ materials
- **Multi-tenancy support** with factory-level data isolation
- **Complex optimization** handling 100+ variables and 50+ constraints
## Development Standards
The project follows strict development standards documented in `.claude/rules/`:
- Rust backend standards (02-rust-backend-standards.md)
- React frontend standards (03-react-frontend-standards.md)
- Database standards (04-database-standards.md)
- LSP usage standards (05-lsp-usage-standards.md)
All these standards are enforced via automated hooks and skills.
## When This Context Is Useful
This project overview is automatically loaded to help Claude understand:
- **Architecture decisions** when proposing changes
- **Technology choices** when solving problems
- **Integration patterns** when adding features
- **Scale considerations** when optimizing performance
- **Domain context** (feed formulation, nutrition, optimization)
This knowledge enables Claude to make more informed, project-appropriate recommendations without requiring repeated explanations of the project's nature and structure.Related Skills
project-scaffolder
Guide for setting up Claude Code infrastructure in new or existing projects
project-qtax
UK taxation expert for HMRC compliance, Making Tax Digital (MTD ITSA/VAT) and Self-Assessment: explain tax treatment; compute income tax/NI/dividend/CGT with band-by-band breakdown; advise on deadlines/forms/penalties; and support MTD developer integration + tax software UX/flows. Use WebSearch (gov.uk/HMRC) to verify current rates and mandation timelines. (project)
project-orchestration
Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management
project-object
Session memory that compounds - remember decisions, patterns, and corrections across AI coding sessions. Includes standards injection for consistent code quality.
project-mngt
Product Owner / Project Manager skill for MVP/MMP/MMR implementation planning
project-logger
SQLite-based project documentation logger for tracking API references, components, and project progress. Use this skill when documenting code changes, adding API documentation, recording component updates, or tracking project milestones. Automatically invoked when user mentions documentation, changelog, API docs, component docs, or project updates.
project-init
Automatically detects new project initialization, collaborates with user on project planning, and sets up the appropriate tech stack with matching skills and agents. Use when starting a new project, creating a new repository, or working in an empty/minimal directory that needs project structure.
project-index
Use this skill for large project maintenance with layered CLAUDE.md index system. Triggers when users need to (1) analyze and document existing codebases, (2) generate hierarchical CLAUDE.md files for modules, (3) set up incremental update hooks after code changes, or (4) navigate large projects efficiently. Supports legacy project onboarding and automatic context management.
project-guidelines-example
Example project-specific skill template based on a real production application.
project-development
This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
project-context-discovery
Discover project structure, package managers, test frameworks, and automation without hardcoded assumptions
project-claude-initializer
為新專案初始化 Claude Code 配置,建立標準化的 .claude 目錄、CLAUDE.md 和 gitignore。當使用者說「初始化 Claude 配置」、「設定專案 Claude」時使用。