How do I start using this skill?

Add the SDKs you want to reference with btca config resources add, then query with btca ask to view how features are implemented.

Which resources are commonly used?

vercel-ai for streaming and tool calling, anthropic-sdk for Anthropic API patterns, and zod for schema validation.

When should I reference SDK implementations?

Before implementing features, during debugging, for multi-provider support, and to study validation patterns.

reference-sdk

npx machina-cli add skill parcadei/Continuous-Claude-v3/reference-sdk --openclaw

Files (1)

SKILL.md

1.5 KB

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?"

Configured Resources

vercel-ai - Streaming, tool calling, structured output
anthropic-sdk - Anthropic API patterns
zod - Schema validation

Add more: btca config resources add -n <name> -t git -u <url> -b <branch>

When to Check

Before implementing - See how others solved similar problems
When debugging - Find how reference code handles edge cases
Multi-provider support - Compare implementations across SDKs
Validation patterns - Check idiomatic approaches

Don't Use For

Documentation lookups (use /nia-docs instead)
Simple API questions (use WebSearch)
Project-specific patterns (use Grep/Glob)

Source

git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/reference-sdk/SKILL.mdView on GitHub

Overview

Reference SDK Check helps you explore how reference implementations tackle common SDK tasks using btca ask. It guides you through streaming, tool calling, and validation patterns across popular SDKs, helping you implement features consistently and debug more effectively. Understanding these references saves time and reduces provider-specific issues.

How This Skill Works

Leverage btca ask to peek into established SDKs (e.g., vercel-ai, anthropic-sdk, zod) and extract proven approaches. You query specific capabilities (streaming, tool definitions, validation) and compare results across resources configured with BTCA. Then apply the discovered patterns to your own SDK work.

When to Use It

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

Quick Start

Step 1: Add or update resources to include target SDKs using btca config resources add
Step 2: Run btca ask -r vercel-ai -q 'How does streamObject work?'
Step 3: Review results from vercel-ai, anthropic-sdk, and zod and apply patterns to your SDK

Best Practices

Use btca ask to inspect streaming patterns, tool calling, and structured output in reference SDKs
Compare how different SDKs address similar problems to guide your implementation
Refresh reference resources: vercel-ai, anthropic-sdk, zod for patterns
Add or update resources with btca config resources add as you explore
Review edge cases in reference implementations before coding

Example Use Cases

Check Vercel AI SDK for streaming patterns
Check Anthropic SDK for tool calling
Check Zod for validation patterns
Debug provider-specific issues by inspecting reference code
Compare implementations across multiple SDKs for multi-provider support

Frequently Asked Questions

Add this skill to your agents