claude
npx machina-cli add skill G1Joshi/Agent-Skills/claude --openclawClaude
Claude (by Anthropic) is OpenAI's main competitor. It is famous for its large context window (200k+), low hallucination rates, and "Artifacts" UI.
When to Use
- Coding: Claude 3.5 Sonnet is widely considered the best coding model in 2025.
- Long Context: Analyzing massive PDFs or codebases.
- Safety: Enterprise-grade safety guardrails.
Core Concepts
Models
- Opus: The smartest, largest model.
- Sonnet: The sweet spot. Fast and incredibly capable.
- Haiku: Fast and cheap.
Artifacts
A UI feature (now an API pattern) where the model generates standalone content (React components, SVGs) in a side window.
Computer Use
Claude can interact with a computer GUI (moving mouse, clicking) via API.
Best Practices (2025)
Do:
- Use Sonnet for Dev: It beats GPT-4o in many coding benchmarks.
- Use XML Tags: Claude loves
<instructions>and<context>tags in prompts. - Prefill Responses: Guide Claude by prefilling the
{"role": "assistant", "content": "{"}to force JSON.
Don't:
- Don't ignore System Prompts: Claude relies heavily on strong system instructions.
References
Source
git clone https://github.com/G1Joshi/Agent-Skills/blob/main/skills/ai-ml/claude/SKILL.mdView on GitHub Overview
Claude by Anthropic is a family of large-context AI models designed for analysis and coding tasks, with enterprise-grade safety. It offers Opus, Sonnet, and Haiku, plus features like the Artifacts UI and GUI interaction via API. This makes Claude a strong alternative for developers and teams needing robust safety and long-context capabilities.
How This Skill Works
Claude provides multiple model choices—Opus for the largest capacity, Sonnet as the fast, capable development-focused option, and Haiku for speed and cost. It supports Artifacts for generating standalone content like React components or SVGs, and can interact with a computer GUI through an API, enabling automated workflows within real environments.
When to Use It
- Coding with Claude 3.5 Sonnet as a top coding model
- Analyzing massive PDFs or codebases using long context
- Implementing enterprise-grade safety guardrails for AI assistants
- Leveraging Artifacts to generate standalone content (React components, SVGs)
- Automating GUI tasks by controlling a computer via Claude's API
Quick Start
- Step 1: Choose Claude Sonnet for development tasks or Opus for maximum context.
- Step 2: Include XML-style tags in prompts, e.g., <instructions> and <context>, to guide behavior.
- Step 3: Prefill the response as JSON to steer output: {"role": "assistant", "content": "{"}
Best Practices
- Use Sonnet for Dev: It beats GPT-4o in coding benchmarks.
- Use XML Tags: Claude loves <instructions> and <context> tags in prompts.
- Prefill Responses: Prefill the JSON structure to guide outputs. (Example: {"role": "assistant", "content": "{"})
- Don't ignore System Prompts: Provide strong system instructions to guide behavior.
- Leverage Artifacts: Use the UI pattern to request standalone outputs like React components or SVGs when relevant.
Example Use Cases
- A developer uses Claude 3.5 Sonnet to auto-generate and refactor code in a large project.
- A data team analyzes a 200k-page PDF using Claude's long-context capability to extract insights.
- An enterprise deploys Claude with strong safety guardrails to power an AI assistant for internal users.
- A frontend team uses Artifacts to generate React components and SVG assets directly from prompts.
- An operations engineer uses Claude's Computer Use API to automate GUI tasks on a workstation.
