Skip to content

Conversation

@paoloricciuti
Copy link
Member

@paoloricciuti paoloricciuti commented Nov 14, 2025

This adds a svelte 5 skill that you can download manually to put in Claude code OR Claude desktop/web, but also makes this repo a Claude marketplace/plugin.

This will ease the experience of sharing the skill and the MCP server.

I've created the skill with the claude-skill-creator aided by the svelte MCP server (so meta) but I've reviewed it manually and found it pretty good... I would appreciate some extra review (and possibly I would love for as much people as possible to actually try the skill disabling the MCP server to see if it's actually working).

If you want to try the skill you can download it pre-zipped here

svelte-code-writer.zip

@changeset-bot
Copy link

changeset-bot bot commented Nov 14, 2025

⚠️ No Changeset found

Latest commit: dc53ba0

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

@vercel
Copy link

vercel bot commented Nov 14, 2025

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Preview Comments Updated (UTC)
mcp Ready Ready Preview Comment Nov 14, 2025 11:11am

@svelte-docs-bot
Copy link

colinhowells added a commit to colinhowells/personal-site-v2 that referenced this pull request Nov 14, 2025
@cgaaf
Copy link

cgaaf commented Dec 15, 2025

I love the idea of having an official Svelte Skill!
One suggestion: I think more guidance on function bindings would be helpful. In my experience, LLMs still frequently misuse the $effect rune—there are cases where function bindings are the better pattern (e.g., input validation and transformation).
It might be worth adding:

Common $effect antipatterns to avoid
Recommended alternatives (particularly function bindings) for those cases

@cgaaf
Copy link

cgaaf commented Dec 15, 2025

Also, once async and remote functions graduate from experimental status, it would be great to have an agent skill that guides migration to async Svelte and remote functions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants