Skip to main content
Prompts prompts.chat Project Taste Guidelines

developer coding developer risk: low

prompts.chat Project Taste Guidelines

Lists project-specific rules and confidence levels for GitHub Actions, architecture, TypeScript, styling, API, i18n, and database practices in the prompts.chat full-stack platform.

PROMPT 

# Taste

# github-actions
- Use `actions/checkout@v6` and `actions/setup-node@v6` (not v4) in GitHub Actions workflows. Confidence: 0.65
- Use Node.js version 24 in GitHub Actions workflows (not 20). Confidence: 0.65

# project
- This project is **prompts.chat** — a full-stack social platform for AI prompts (evolved from the "Awesome ChatGPT Prompts" GitHub repo). Confidence: 0.95
- Package manager is npm (not pnpm or yarn). Confidence: 0.95

# architecture
- Use Next.js App Router with React Server Components by default; add `"use client"` only for interactive components. Confidence: 0.95
- Use Prisma ORM with PostgreSQL for all database access via the singleton at `src/lib/db.ts`. Confidence: 0.95
- Use the plugin registry pattern for auth, storage, and media generator integrations. Confidence: 0.90
- Use `revalidateTag()` for cache invalidation after mutations. Confidence: 0.90

# typescript
- Use TypeScript 5 in strict mode throughout the project. Confidence: 0.95

# styling
- Use Tailwind CSS 4 + Radix UI + shadcn/ui for all UI components. Confidence: 0.95
- Use the `cn()` utility for conditional/merged Tailwind class names. Confidence: 0.90

# api
- Validate all API route inputs with Zod schemas. Confidence: 0.95
- There are 61 API routes under `src/app/api/` plus the MCP server at `src/pages/api/mcp.ts`. Confidence: 0.90

# i18n
- Use `useTranslations()` (client) and `getTranslations()` (server) from next-intl for all user-facing strings. Confidence: 0.95
- Support 17 locales with RTL support for Arabic, Hebrew, and Farsi. Confidence: 0.90

# database
- Use soft deletes (`deletedAt` field) on Prompt and Comment models — never hard-delete these records. Confidence: 0.95

ROLES & RULES

  1. Use `actions/checkout@v6` and `actions/setup-node@v6` (not v4) in GitHub Actions workflows. Confidence: 0.65
  2. Use Node.js version 24 in GitHub Actions workflows (not 20). Confidence: 0.65
  3. This project is **prompts.chat** — a full-stack social platform for AI prompts (evolved from the "Awesome ChatGPT Prompts" GitHub repo). Confidence: 0.95
  4. Package manager is npm (not pnpm or yarn). Confidence: 0.95
  5. Use Next.js App Router with React Server Components by default; add `"use client"` only for interactive components. Confidence: 0.95
  6. Use Prisma ORM with PostgreSQL for all database access via the singleton at `src/lib/db.ts`. Confidence: 0.95
  7. Use the plugin registry pattern for auth, storage, and media generator integrations. Confidence: 0.90
  8. Use `revalidateTag()` for cache invalidation after mutations. Confidence: 0.90
  9. Use TypeScript 5 in strict mode throughout the project. Confidence: 0.95
  10. Use Tailwind CSS 4 + Radix UI + shadcn/ui for all UI components. Confidence: 0.95
  11. Use the `cn()` utility for conditional/merged Tailwind class names. Confidence: 0.90
  12. Validate all API route inputs with Zod schemas. Confidence: 0.95
  13. There are 61 API routes under `src/app/api/` plus the MCP server at `src/pages/api/mcp.ts`. Confidence: 0.90
  14. Use `useTranslations()` (client) and `getTranslations()` (server) from next-intl for all user-facing strings. Confidence: 0.95
  15. Support 17 locales with RTL support for Arabic, Hebrew, and Farsi. Confidence: 0.90
  16. Use soft deletes (`deletedAt` field) on Prompt and Comment models — never hard-delete these records. Confidence: 0.95

EXPECTED OUTPUT

Format
unknown

CAVEATS

Missing context
  • Explicit instruction on how to apply these guidelines (e.g., 'Follow these when implementing code changes')
  • Success criteria or examples of compliant vs non-compliant code

QUALITY

OVERALL
0.70
CLARITY
0.95
SPECIFICITY
0.95
REUSABILITY
0.25
COMPLETENESS
0.75

IMPROVEMENT SUGGESTIONS

  • Prefix with a clear directive: 'You are an expert developer for prompts.chat. Strictly adhere to these project guidelines when writing or reviewing code:'
  • Add placeholders for confidence thresholds or make confidences actionable (e.g., 'Follow rules with confidence >=0.9 strictly')
  • Include examples of applying rules in code snippets for key sections

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR DEVELOPER