---
title: "multica-ai skills · skilld"
canonical_url: "https://skilld.dev/gh/multica-ai"
meta:
  description: "4 agent skills published by multica-ai on skilld."
  "og:description": "4 agent skills published by multica-ai."
  "og:title": "multica-ai on skilld"
---

`

![Avatar for multica-ai](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Fmultica-ai.png)

# **multica-ai**

[@multica-ai](https://github.com/multica-ai)org

4 skills2 repos 216k Synced 1 day ago

[GitHub](https://github.com/multica-ai)

## Skills

### [multica-ai/multica](https://skilld.dev/gh/multica-ai/multica)

Make humans and AI agents work as one team — open-source and self-hostable.

3 skills 52k

`npx skilld add multica-ai/multica`

- [

  **/multica-onboarding**52k

  Use when a product-authored kickoff starts or resumes Mika's interactive onboarding for a Multica workspace. The opening greeting has already been sent; carry the member from their first message to one real, confirmed, issue-based execution and a clear handoff. /multica-onboarding by multica-ai](https://skilld.dev/gh/multica-ai/multica/multica-onboarding)
- [

  **/multica-working-on-issues**52k

  Superseded by the multica-platform skill — load that instead. This file only records where the Multica issue contracts moved to. /multica-working-on-issues by multica-ai](https://skilld.dev/gh/multica-ai/multica/multica-working-on-issues)
- [

  **/web-design-guidelines**52k

  Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". /web-design-guidelines by multica-ai](https://skilld.dev/gh/multica-ai/multica/web-design-guidelines)

### [multica-ai/andrej-karpathy-skills](https://skilld.dev/gh/multica-ai/andrej-karpathy-skills)

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

1 skill 216k

`npx skilld add multica-ai/andrej-karpathy-skills`

- [

  **/karpathy-guidelines**216k

  Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. /karpathy-guidelines by multica-ai](https://skilld.dev/gh/multica-ai/andrej-karpathy-skills)

Skills published by multica-ai. Checked GitHub just now