ui
CLAUDE.md447 starsChanged 3 months agoMITView on GitHub
SvelteKit + Svelte 5 + TypeScript + TailwindCSS + Io and Holocene design systems
We split this CLAUDE.md into the rules it gives an agent
10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 55
Type checking: Run pnpm check to verify TypeScript compliance
- Distinctive: line 56
Test execution: Run appropriate test suites based on changes
- Distinctive: line 57
Follow patterns: Use existing component patterns and utility functions
- Very specific: line 58
Design system: Prefer Io components (src/lib/io), then Holocene components (src/lib/holocene), over custom implementations.
- Distinctive: line 59
Accessibility: Ensure proper ARIA attributes and semantic HTML
- Distinctive: line 63
No comments: Don't add code comments unless explicitly requested
- Distinctive: line 64
Type safety: Always provide proper TypeScript types
- Distinctive: line 66
Test coverage: Write tests for new utilities and business logic
- Distinctive: line 67
Import organization: Follow the established import order
- Distinctive: line 71
Validation: Use Zod for runtime type validation
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md 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
Claude AI Assistant Rules for Temporal UI
SvelteKit + Svelte 5 + TypeScript + TailwindCSS + Io and Holocene design systems
Commands
pnpm lint # Run all linters
pnpm check # TypeScript type checking
pnpm test -- --run # Run unit testsSvelte 5 Patterns
// Props
let { class: className = '', adapter }: Props = $props();
// State
let count = $state(0);
// Computed
const doubled = $derived(count * 2);
// Effects
$effect(() => {
console.log('Count:', count);
return () => cleanup();
});
// SuperForms
const { form, errors, enhance } = $derived(
superForm(data, {
SPA: true,
validators: zodClient(schema),
onUpdate: async ({ form }) => {
/* handle submit */
},
}),
);Import Order
- Node.js built-ins
- External libraries (with
svelte/**first) - SvelteKit imports (
$app/**,$types) - Internal imports (
$lib/**) - Component imports (
$components/**/*.svelte) - Relative imports (
./,../)
Workflow
- Always run linting: Execute
pnpm lintafter making changes - Type checking: Run
pnpm checkto verify TypeScript compliance - Test execution: Run appropriate test suites based on changes
- Follow patterns: Use existing component patterns and utility functions
- Design system: Prefer Io components (
src/lib/io), then Holocene components (src/lib/holocene), over custom implementations. Io replaces Holocene over time - Accessibility: Ensure proper ARIA attributes and semantic HTML
Code Generation
- No comments: Don't add code comments unless explicitly requested
- Type safety: Always provide proper TypeScript types
- Component reuse: Leverage existing components and utilities
- Test coverage: Write tests for new utilities and business logic
- Import organization: Follow the established import order
Error Handling
- Validation: Use Zod for runtime type validation
- Error boundaries: Implement proper error boundaries for components
- Network errors: Handle API failures gracefully
- User feedback: Provide clear error messages and loading states
Naming
- Files: kebab-case (
workflow-status.svelte) - Components: PascalCase in imports, kebab-case for files
- Functions: camelCase
- Types: PascalCase
- Use
import typefor type-only imports
In this repository7 other files it gives its agents.
- auth-testingSkill
- local-temporalSkill
- proto-codegenSkill
- serverless-worker-awsSkill
- setup-worktreeSkill
- svelte-migrateSkill
- system-nexus-operationSkill
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.

