← 返回 Skills 市场

Claude API Builder

Name: Claude API Builder
Author: wimi321

作者 wimi321 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

171

总下载

当前安装

版本数

在 OpenClaw 中安装

/install claude-code-claude-api-builder

功能描述

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

使用说明 (SKILL.md)

Claude API Builder

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

Detect the project language and SDK surface.
Choose the smallest fitting pattern: simple messages, streaming, tools, batches, or files.
Prefer official docs and SDK-native examples.
Keep model names, error handling, and retries explicit.
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.

安全使用建议

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.

功能分析

Type: OpenClaw Skill Name: claude-code-claude-api-builder Version: 1.0.0 The skill bundle is a legitimate set of instructions and configurations designed to assist users with Anthropic Claude API integrations. Analysis of SKILL.md and agents/openai.yaml reveals no malicious instructions, data exfiltration patterns, or suspicious execution logic; the content is strictly focused on providing guidance for using official Anthropic SDKs.

能力评估

✓ 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.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install claude-code-claude-api-builder
安装完成后，直接呼叫该 Skill 的名称或使用 /claude-code-claude-api-builder 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial extraction from local Claude Code source

元数据

Slug claude-code-claude-api-builder

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题