Skip to content

Add livekit-agents-production skill for existing codebases#7

Open
rathoresids wants to merge 1 commit intolivekit:mainfrom
rathoresids:improve-livekit-agents-skill
Open

Add livekit-agents-production skill for existing codebases#7
rathoresids wants to merge 1 commit intolivekit:mainfrom
rathoresids:improve-livekit-agents-skill

Conversation

@rathoresids
Copy link
Copy Markdown

What does this PR do?

Adds a new skill (livekit-agents-production) focused on extending, debugging, and operating existing LiveKit agent codebases. This complements the existing livekit-agents skill (which covers building from scratch) with production-stage guidance.

The new skill covers:

  • Worker process model — parent-child architecture, shared state inheritance, and async context implications
  • Safe async patterns — avoiding the most common class of production bugs (event loop conflicts in worker processes)
  • Provider lifecycle — prewarming strategies, cold-start mitigation, failure handling
  • Testing within existing infrastructure — using established fixtures, mocking at boundaries, async test patterns
  • Performance profiling — what to measure (time-to-first-audio, tool execution, context growth) and common anti-patterns
  • Production operations — graceful shutdown, SDK upgrade strategy, observability, debugging common failures

Addresses #6

Design decisions

  • Separate skill, not a rewrite — keeps each skill focused: livekit-agents for building, livekit-agents-production for extending and operating
  • No code examples — all patterns described as behavioral principles per the "freeze forever" principle
  • Not Python-specific — worker model and async patterns framed universally, applicable to both Python and Node SDKs
  • 258 lines — well under the 500-line limit

Checklist

  • Content passes the "freeze forever" test — would it still be correct if never updated?
  • API specifics are directed to MCP/docs, not hardcoded in skill content
  • Skill stays under 500 lines
  • Trigger phrases in skill description are clear and representative
  • Tested with an AI coding agent to verify the skill produces correct behavior

   Adds a new skill focused on extending, debugging, and operating
   existing LiveKit agent codebases. Complements the existing
   livekit-agents skill (which covers building from scratch) with
   production-stage guidance: worker process model, safe async
   patterns, provider lifecycle, performance profiling, testing
   within established infrastructure, and production operations.
@CLAassistant
Copy link
Copy Markdown

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

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