AGENTS.md
Project Overview
This repository contains the official documentation for Modellix, an enterprise-grade MaaS (Model as a Service) platform. The docs are built with Mintlify and published at docs.modellix.ai. Modellix provides unified API access to 100+ AI models for:- Text-to-Image — Generate images from text prompts
- Image-to-Image — Transform and edit images with AI
- Text-to-Video — Create videos from text descriptions
- Image-to-Video — Animate images into videos
- Video Editing — AI-powered video transformations
Repository structure
model-api/ and register the page in docs.json navigation.
Setup Commands
Install the Mintlify CLI:http://localhost:3000.
If the dev environment is not running correctly:
Development Workflow
- All documentation pages use
.mdxformat with YAML frontmatter. - API reference pages are OpenAPI JSON files consumed by Mintlify.
- Navigation, theme, and site metadata live in
docs.json. - Changes pushed to the default branch deploy automatically via the Mintlify GitHub app.
- CI workflow
.github/workflows/notify-model-api-changes.ymlsends DingTalk notifications on pushes tomain.
Language Policy
Documentation output language
- Write all Mintlify documentation content in English.
- Keep page titles, descriptions, headings, body text, and code comments in docs in English.
- If source notes are in Chinese, translate and rewrite them into natural technical English.
Communication with user/developer
- Communicate with the user and developer in Chinese.
- Ask clarification questions in Chinese.
- Explain edits, plans, and next steps in Chinese.
Priority when conflicts happen
- For generated documentation files: English content has priority.
- For chat replies and collaboration messages: Chinese has priority.
Mintlify Writing Guidelines
You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.Core writing principles
Language and style
- Use clear, direct language appropriate for technical audiences
- Write in second person (“you”) for instructions and procedures
- Use active voice over passive voice
- Employ present tense for current states, future tense for outcomes
- Avoid jargon unless necessary and define terms when first used
- Maintain consistent terminology throughout all documentation
- Keep sentences concise while providing necessary context
- Use parallel structure in lists, headings, and procedures
Content organization
- Lead with the most important information (inverted pyramid structure)
- Use progressive disclosure: basic concepts before advanced ones
- Break complex procedures into numbered steps
- Include prerequisites and context before instructions
- Provide expected outcomes for each major step
- Use descriptive, keyword-rich headings for navigation and SEO
- Group related information logically with clear section breaks
User-centered approach
- Focus on user goals and outcomes rather than system features
- Anticipate common questions and address them proactively
- Include troubleshooting for likely failure points
- Write for scannability with clear headings, lists, and white space
- Include verification steps to confirm success
Required page structure
Every documentation page must begin with YAML frontmatter:Mintlify component reference
Callout components
<Note>— Supplementary information that supports the main content<Tip>— Expert advice, shortcuts, or best practices<Warning>— Critical information about potential issues or destructive actions<Info>— Background information or neutral announcements<Check>— Positive confirmations or successful completions
Code components
Single code block with optional filename:Structural components
<Steps>/<Step>— Sequential procedures with optional nested callouts<Tabs>/<Tab>— Platform-specific or alternative content<AccordionGroup>/<Accordion>— Collapsible progressive disclosure<Card>/<CardGroup>— Highlighted links and feature summaries
API documentation components
<ParamField>— Request parameters (path,query,body,header)<ResponseField>— Response fields with type and description<Expandable>— Nested object properties
Media components
<Frame>— Wrap images with optional caption<video>— Self-hosted video content<iframe>— Embedded YouTube videos<Tooltip>— Inline term explanations<Update>— Changelog entries
Component selection logic
- Use Steps for procedures and sequential instructions
- Use Tabs for platform-specific content or alternative approaches
- Use CodeGroup when showing the same concept in multiple programming languages
- Use Accordions for progressive disclosure of information
- Use RequestExample/ResponseExample specifically for API endpoint documentation
- Use ParamField for API parameters, ResponseField for API responses
- Use Expandable for nested object properties or hierarchical information
Content quality standards
Code examples
- Always include complete, runnable examples that users can copy and execute
- Show proper error handling and edge case management
- Use realistic data instead of placeholder values
- Include expected outputs and results for verification
- Test all code examples thoroughly before publishing
- Specify language and include filename when relevant
- Add explanatory comments for complex logic
- Never include real API keys or secrets in code examples
API documentation
- Document all parameters including optional ones with clear descriptions
- Show both success and error response examples with realistic data
- Include rate limiting information with specific limits
- Provide authentication examples showing proper format
- Explain all HTTP status codes and error handling
- Cover complete request/response cycles
Accessibility
- Include descriptive alt text for all images and diagrams
- Use specific, actionable link text instead of “click here”
- Ensure proper heading hierarchy starting with H2
- Provide keyboard navigation considerations
- Use sufficient color contrast in examples and visuals
- Structure content for easy scanning with headers and lists
Build and Deployment
Production deployment is handled by Mintlify. Install the Mintlify GitHub app from the dashboard. Pushes to the default branch deploy automatically.Pull Request Guidelines
Commit message format
Use Simplified Chinese for commit titles. Recommended format:Before submitting
- Run
mint devlocally and verify pages render correctly - Ensure new or edited
.mdxpages have valid frontmatter - Ensure new API endpoints are registered in
docs.json - Keep documentation content in English per the language policy
Additional Notes
- Modellix uses an asynchronous API design for media generation tasks. Document polling patterns and link to
common-api/query-task-result.json. - Official Modellix agent skill:
npx skills add https://github.com/modellix/modellix-skill --skill modellix - Support: support@modellix.ai · Discord · GitHub