openstory / rules
Cursor rule693 starsChanged 2 months agoMITView on GitHub
Context7 MCP integration for up-to-date documentation
We split this context7-integration.mdc into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Always use Context7 MCP when you need current documentation for:
- Very specific: line 19
Use these Context7 library IDs for OpenStory's tech stack:
- Distinctive: line 71
Instead of relying on potentially outdated training data, Context7 provides:
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- description: Context7 MCP integration for up-to-date documentation globs: [] alwaysApply: true --- # Context7 MCP Integration Always use Context7 MCP when you need current documentation for: - Code generation and setup steps - Library/API documentation - Configuration examples - Framework-specific patterns This means you should automatically use the Context7 MCP tools to resolve library IDs and get library docs without me having to explicitly ask. ## Pre-configured Library IDs Use these Context7 library IDs for OpenStory's tech stack: ### Core Framework - `/vercel/next.js` - Next.js 15 documentation and patterns - `/microsoft/typescript` - TypeScript best practices - `/facebook/react` - React 19 features and hooks ### UI & Styling - `/tailwindlabs/tailwindcss` - Tailwind CSS 4 utilities and configuration - `/radix-ui/primitives` - Radix UI component APIs - `/shadcn/ui` - shadcn/ui component library ### Backend & Data - `/elysiajs/elysia` - Elysia web framework patterns - `/drizzle-team/drizzle-orm` - Drizzle ORM queries and migrations - `/temporalio/sdk-typescript` - Temporal TypeScript SDK - `/tanstack/query` - TanStack Query v5 patterns - `/arktypeio/arktype` - ArkType runtime validation (backend validation) ### AI Integration - `/fal-ai/client` - Fal.ai SDK for image/video generation - `/openai/openai-node` - OpenAI API for script analysis ### Infrastructure - `/upstash/redis` - Redis for caching (via @upstash/redis) - `/oven-sh/bun` - Bun runtime and package manager ## When to Use Context7 Automatically invoke Context7 when: - Setting up new components or features - Working with framework-specific APIs (Next.js 15 App Router, React Server Components) - Implementing authentication patterns (Better Auth) - Configuring AI model integrations (Fal.ai models) - Working with async job queues (QStash patterns) - Implementing real-time features (Supabase Realtime) - Setting up validation schemas (Zod) - Troubleshooting integration issues - Learning new library features ## OpenStory-Specific Context Needs Prioritize Context7 for: - **Next.js 15**: Server Actions, async request params, React 19 features - **Elysia**: Route handlers, plugins, lifecycle hooks - **Drizzle ORM**: Query patterns, relations, migrations - **Temporal**: Workflow definitions, activity patterns, worker setup - **TanStack Query**: Query keys factory pattern, optimistic updates - **Fal.ai**: Model-specific parameters (flux, imagen4, veo3, kling, wan) ## Example Usage Instead of relying on potentially outdated training data, Context7 provides: - Current API signatures (especially for Next.js 15 breaking changes) - Latest configuration options (Tailwind 4, React 19) - Up-to-date code examples (async params in App Router) - Recent best practices (Server Components vs Client Components) - Breaking changes and migrations (React 18→19, Next.js 14→15) This ensures all generated code uses current, working patterns rather than deprecated or incorrect approaches.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/bun-test.mdcCursor rule
- .cursor/rules/drizzle-patterns.mdcCursor rule
- .cursor/rules/production-review-panel.mdcCursor rule
- .cursor/rules/project-context.mdcCursor rule
- .cursor/rules/react-rules.mdcCursor rule
- .cursor/rules/tanstack-react-router_api.mdcCursor rule
- .cursor/rules/tanstack-react-router_guide.mdcCursor rule
- .cursor/rules/tanstack-react-router_installation.mdcCursor rule
- .cursor/rules/tanstack-react-router_routing.mdcCursor rule
- .cursor/rules/tanstack-react-router_setup-and-architecture.mdcCursor rule
- .cursor/rules/use-bun-instead-of-node-vite-npm-pnpm.mdcCursor rule
- sd25-peSkill
- react-patternsSkill
- update-model-versionsSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.