Reference Sdk

You know how you're implementing streaming or tool calling and wonder "how does Vercel AI SDK actually do this?" This skill wraps btca ask to query reference implementations like Vercel AI SDK, Anthropic SDK, and Zod directly from your workflow. It's meant for those moments when you're debugging provider-specific quirks or need to see how established libraries handle edge cases before writing your own version. The skill isn't user-invocable, so Claude calls it automatically when the context suggests checking reference code would help. Honestly most useful when you're building multi-provider support and need to compare patterns across different SDKs without context switching to GitHub.

skills.sh installs: 482
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill reference-sdk --agent claude-code

Installs into .claude/skills of the current project.

Files

Reference SDK Check

When implementing SDK features or debugging provider-specific issues, check reference implementations.

When to Use

Implementing SDK features
Debugging provider-specific issues
Understanding how other libraries solve similar problems
"How does Vercel AI SDK do X?"
"Check Anthropic SDK for Y"

Commands

Use btca ask to check how reference SDKs implement similar features:

# Check Vercel AI SDK for streaming patterns
btca ask -r vercel-ai -q "How does streamObject work?"

# Check Anthropic SDK for tool calling
btca ask -r anthropic-sdk -q "How are tools defined and called?"

# Check Zod for validation patterns
btca ask -r zod -q "How does safeParse handle errors?"