moai-workflow-project

Generates project documentation, multilingual structures, and optimized templates for MoAI projects.

Updated Jul 24, 2026
One-click install
npx skills add https://github.com/jjjh7401/AI-Lighting_Console --skill moai-workflow-project-jjjh7401
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: moai-workflow-project
Source: https://github.com/jjjh7401/AI-Lighting_Console/tree/main/.claude/skills/moai-workflow-project
Command: npx skills add https://github.com/jjjh7401/AI-Lighting_Console --skill moai-workflow-project-jjjh7401

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Keeping project context documents (product.md, structure.md, tech.md), multilingual documentation, and code templates accurate and current is repetitive manual work that drifts out of sync with the codebase. This Skill automates documentation scaffolding, language initialization, template optimization, and SPEC-to-docs generation so project context stays aligned with reality. ## Core Features & Use Cases - Documentation Management: Generates product/structure/tech.md from templates, detects project type, and produces docs via Sphinx, MkDocs, TypeDoc, OpenAPI, or Nextra in Markdown, HTML, or PDF. - Multilingual Initialization: Auto-detects project language, creates per-language doc directories (docs/ko, docs/en), and localizes agent prompts with token-cost analysis. - Template Optimization: Analyzes template size, complexity, and redundancy, then optimizes with mandatory backups and benchmarking. - Navigator Audit & AST Enrichment: Ships scripts that diff design docs against the SPEC capability map (missing/orphan SPECs) and extract tree-sitter symbols across 16 languages. - Use Case: After writing a SPEC for a new authentication feature, run the project workflow to regenerate the capability map, audit design-vs-implementation drift, and emit API reference docs automatically. ## Quick Start Ask the agent to initialize project documentation and run the navigator audit for the current repository.

Frequently Asked Questions about moai-workflow-project

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate project documentation from a SPEC file?▼

Provide a complete SPEC with id, title, requirements, and api_endpoints, then run the documentation generation workflow. It extracts requirements and endpoint schemas into structured Markdown with API reference tables, and supports Sphinx, MkDocs, TypeDoc, OpenAPI, and Nextra generators.

What documentation generators does this workflow support?▼

It supports Sphinx for Python API docs, MkDocs for general Markdown projects, TypeDoc for TypeScript libraries, OpenAPI/Swagger for REST APIs, and Nextra for Next.js MDX docs sites. Output formats include Markdown, HTML, and PDF.

How does multilingual documentation initialization work?▼

The system auto-detects project language from file content, config files, and system locale, then creates per-language directories like docs/ko and docs/en with language negotiation and fallback configuration. Agent prompts can stay in English to reduce token cost by roughly 20-50%.

Does the navigator audit modify my SPEC files or design docs?▼

No. The audit is strictly read-only over product.md, structure.md, tech.md, the capability map, and SPEC frontmatter. It writes only audit-report.md and audit-report.json, exits 0 on missing inputs, and never auto-creates or retires SPECs.

Why should I back up templates before optimization?▼

Template optimization rewrites files to reduce size and complexity, so a failed or over-aggressive pass could destroy working templates. The workflow always creates a backup first (backup: true) and supports restoration from the timestamped backup directory.

Which languages does the AST symbol enrichment support?▼

Fourteen working tree-sitter grammars extract symbols: Go, Python, TypeScript, JavaScript, Rust, Java, Kotlin, C#, Ruby, PHP, Elixir, C++, Scala, and Swift. R and Flutter/Dart are scaffolded but fail open with Supported: false.