Separate skill for contributing to existing LiveKit agent codebases

[rathoresids]

What should the skill teach agents to do?

Add a separate skill (e.g. livekit-agents-contributing or a variant of the existing skill) tailored for developers working within an established LiveKit agent codebase. It would retain the timeless principles from the current skill (verify APIs via MCP, latency-first thinking, mandatory testing) while dropping the setup/bootstrapping content.

Why is this needed?

The current livekit-agents skill is focused on building voice AI agents from scratch — cloud setup, project connection, workflow architecture design (handoffs/tasks), and initial agent creation. This is great for greenfield projects.
However, teams that already have a LiveKit agent codebase in production need different guidance. The challenges shift from "how to build an agent" to "how to add features, debug issues, and maintain an existing agent."

Scope

• Extending an existing agent — adding modules, providers, tools, and integrations without breaking what's already there
• Debugging production issues — common failure patterns (event loop errors in forked processes, provider failures, latency regressions)
• Performance optimization — prewarm strategies, async patterns, context size management
• Testing within an established test infrastructure — working with existing fixtures and factories rather than creating a tests/ directory from scratch
• Safe async patterns — especially relevant for LiveKit's fork-based worker model where asyncio.run() in the wrong place breaks everything

[rathoresids]

I could raise a PR with this skill that I created on top of the one created for agent building.

[Topherhindman]

I could raise a PR with this skill that I created on top of the one created for agent building.

More than happy if you'd like to open a PR @rathoresids and we can review it and help ensure it fits with the overall direction we want to keep the skills going!

[rathoresids]

Sure @Topherhindman
How would you want me to structure the new skill?
The idea is this skill would be less "building from scratch" focussed and more "working within an existing agent codebase"
Covering the challenges that arise after initial setup: safe async patterns in the worker process model, provider lifecycle management, performance profiling, testing within established infrastructure, and production operations like graceful shutdown and SDK upgrades.

I'm thinking a separate skill (livekit-agents-production) alongside the existing one rather than modifying it, so each skill stays focused:

• livekit-agents — how to build a voice agent
• livekit-agents-production — how to extend, debug, and operate one

Raising a PR with the above structure. Happy to know your inputs

PR - #7

[rathoresids]

Let me know if this aligns with the direction you guys want the skills to go in. More than happy to take feedback :)

[rathoresids]

Following up here @Topherhindman