Claude API Builder

Use when code imports Anthropic SDKs or the user asks to build with the Claude API, Agent SDK, tool use, streaming, files, or batches.

Security Scan

The skill's requested resources and instructions match its stated purpose (helping build with the Claude/Anthropic SDKs); it is instruction-only, requests no credentials, and contains nothing that contradicts its description.

Purpose & Capability

Name and description match the instructions. The skill is an instruction-only helper for Anthropic/Claude SDK patterns and does not request unrelated binaries, environment variables, or config paths.

Instruction Scope

Runtime instructions are focused on detecting SDK usage, choosing appropriate API patterns, and recommending docs and examples. The triggers imply the agent may inspect project code (e.g., imports) and may browse live Anthropic docs for up-to-date details — which is expected for a code-integration helper. No instructions request unrelated files, credentials, or external endpoints beyond using official docs.

Install Mechanism

No install spec and no code files beyond SKILL.md and small metadata — lowest-risk model (instruction-only). Nothing is fetched or written to disk by the skill itself.

Credentials

The skill declares no required environment variables, credentials, or config paths. That is proportionate for documentation-and-pattern guidance for Claude/Anthropic SDKs.

Persistence & Privilege

always is false and the skill is user-invocable with normal autonomous-invocation allowed. Given the lack of elevated access or credential requests, this level of presence is appropriate.

Assessment

This instruction-only skill appears coherent and low-risk: it provides guidance on using Anthropic/Claude SDKs, asks for no credentials, and performs no installs. Before enabling, confirm whether you will allow the agent to read your project files or browse the web for live docs (the skill's triggers imply inspecting imports and consulting docs). If you prefer, restrict the agent's file or network access while you test the skill. If you need more assurance, ask the skill author for a brief example of what files or paths the agent will read when applied to your repo.

Use this skill when the task is specifically about Anthropic or Claude API integration.

Trigger Signals

• Imports like anthropic, @anthropic-ai/sdk, or Agent SDK packages
• Requests about streaming, tool use, prompt caching, file uploads, or Claude batch jobs
• Questions about choosing Anthropic API patterns for an app

Workflow

1. Detect the project language and SDK surface.
2. Choose the smallest fitting pattern: simple messages, streaming, tools, batches, or files.
3. Prefer official docs and SDK-native examples.
4. Keep model names, error handling, and retries explicit.
5. Explain when to browse live docs for fast-moving API details.

Guardrails

• Do not pivot to non-Anthropic SDKs unless the user asks.
• Prefer primary documentation over memory for model/API specifics.
• Separate one-shot prompts from stateful agent workflows.

Source Provenance

Derived from src/skills/bundled/claudeApi.ts and the bundled Claude API references.