I was wondering if there is a standardized system prompt or context that new ServiceStack.NET projects can utilize? Also if there are any links, documentation, or MCP where AI could use to be better accustomed to SS.NET api’s?
Cline’s
I was wondering if there is a standardized system prompt or context that new ServiceStack.NET projects can utilize? Also if there are any links, documentation, or MCP where AI could use to be better accustomed to SS.NET api’s?
Cline’s
The ServiceStack Razor SSG websites including docs.servicestack.net, servicestack.net, etc include support for llms.txt and llms-full.txt so you can feed it the entire ServiceStack Docs website for context from:
From this AI based documentation discussion thread it looks like DocsGPT is a good tool for creating a local knowledgebase from docs.
That’s good know. Some how I missed that blog post.
I was more thinking in terms of AI generating new SS projects and if SS had a default system context prompt to be used for laying out the project and all SS best practices, etc.
For example Cline (and this is probably specific to Cline) lays out exactly how the project should be laid out and and other rules.
Basically was looking for a default best practices with project(s) structure and best practices that the AI should conform to when generating SS solutions. Yeah the system prompt would probably be changed based upon corporate rules, but was looking for something to start with.
# Project Configuration
## Tech Stack
- Next.js 14+ with App Router
- Tailwind CSS for styling
- Supabase for backend
- Vercel for deployment
- GitHub for version control
## Project Structure
/src
/app # Next.js App Router pages
/components # React components
/lib # Utility functions
/types # TypeScript types
/supabase
/migrations # SQL migration files
/seed # Seed data files
/public # Static assets
## Database Migrations
SQL files in /supabase/migrations should:
- Use sequential numbering: 001, 002, etc.
- Include descriptive names
- Be reviewed by Cline before execution
Example: 001_create_users_table.sql
## Development Workflow
- Cline helps write and review code changes
- Vercel automatically deploys from main branch
- Database migrations reviewed by Cline before execution
## Security
DO NOT read or modify:
- .env files
- \*_/config/secrets._
- Any file containing API keys or credentials
I don’t do anything special for ServiceStack Apps (which are just ASP .NET Core Apps), but I don’t use Cline/RooCode/Cursor/etc either.
Unfortunately there’s no clear winner and everyone’s going to have their own personal preferences on the AI tools they prefer using, personally I’m using augmentcode.com, GitHub Copilot and Gemini Code assist in both Rider + VS Code and whatever AI Assistants IntelliJ bakes into their IDEs.
I’m not sure how good the other AI tools are but augment code’s context engine and agents are fantastic at learning how your App is structured, the structure of DTOs to add new functionality using client code to call new ServiceStack APIs following the existing coding patterns used in your App.
Maybe we need an area where everyone can share what works best for them, a new GitHub Discussions Thread would likely be best for long-lived collaborative content.
I’ve added a discussion thread that we can hopefully use to gather feedback and AI Tool recommendations:
FYI: found this Cline prompts that could be tailored to other AI/models.
No need to respond to this.
[Edit: Added github repo link for the prompts]