skills.rest
phuhao00
phuhao00COMMUNITY
Explore all skills by this author →
WebsiteGitHub

claude-api

Build, debug, and optimize applications using the Anthropic SDK and Claude API.

12|3|Updated Jun 17, 2026
Search Tags:#api#llm#claude#agent#anthropic#prompt-caching
One-click install
npx skills add https://github.com/phuhao00/bony-agent --skill claude-api-phuhao00
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-api
Source: https://github.com/phuhao00/bony-agent/tree/main/.agent/skills/claude-api
Command: npx skills add https://github.com/phuhao00/bony-agent --skill claude-api-phuhao00

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, and includes references (resource) components.

What problem does it solve?

This skill streamlines the development of LLM-powered applications using the Anthropic SDK, ensuring best practices for model selection, prompt caching, and agentic workflows are followed.

Core Features & Use Cases

  • Model Management: Simplifies migration between Claude model versions (e.g., Opus 4.6 to 4.7) and handles retired-model replacements.
  • Feature Implementation: Provides standardized patterns for prompt caching, adaptive thinking, tool use, and managed agents.
  • Use Case: When building a stateful coding agent, use this skill to implement server-side compaction and prompt caching to maintain high performance within the 1M context window.

Quick Start

Use the claude-api skill to implement a new tool-use loop in my python project using Claude Opus 4.7.

Frequently Asked Questions about claude-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement prompt caching with the Anthropic SDK to optimize Claude API performance?▼

Implement prompt caching in the Anthropic SDK by structuring your context to cache reused prefixes, which optimizes Claude API performance by reducing latency and token processing overhead. This skill provides standardized patterns for efficient context management.

What is the best way to migrate my application to a newer Claude model version like Opus 4.7?▼

The best way to migrate to a newer Claude model version like Opus 4.7 is to update the model identifier in your Anthropic SDK calls and adjust for any deprecated parameters. This skill manages model versioning and handles retired-model replacements.

How do I build a stateful coding agent with Claude API managed agent workflows?▼

Build a stateful coding agent by using the Claude API to implement managed agent workflows with tool use loops and server-side compaction. This skill ensures adherence to official SDK patterns for maintaining high performance within the 1M context window.

Does the Claude API support adaptive thinking and tool use for LLM-powered software?▼

Yes, the Claude API supports adaptive thinking and tool use for LLM-powered software through the Anthropic SDK. This skill provides standardized implementation patterns for integrating these features into your application workflows.

Can I use this approach to maintain high performance within the Claude API 1M context window?▼

Yes, you can maintain high performance within the Claude API 1M context window by implementing server-side compaction and prompt caching. This skill streamlines context management to ensure efficient processing of large context volumes.

Related Skills

Explore More Software Engineering Skills→
heximaoheximao

claude-api

Generate and optimize Python code for Claude API applications using the Anthropic SDK.

Community
Advanced
giosuetedeschi-specgiosuetedeschi-spec

langfuse

Track LLM traces, spans, and metrics for production AI applications.

Community
Advanced
leafcoderleafcoder
2

AI Engineer

Integrate retrieval-augmented generation and agentic orchestration frameworks for LLM applications.

Community
Advanced
ag47-ptag47-pt
1

claude-api

Build and optimize Claude API applications with Anthropic SDK integrations.

Community
Advanced