Master XML tag structure, system prompts, role prompting, scratchpad reasoning, and few-shot examples for Claude.
Andromity loads skills from folders you trust. Install with andromity skill install anthropic-prompt-engineering — autonomy and approval limits stay configurable per session.
# Install the "Anthropic Claude Prompt Engineering" skill You are installing an AgenticMarket skill into this workspace. Follow these steps exactly. ## 1. Detect your environment and choose the destination file - Andromity: `.andromity/skills/anthropic-prompt-engineering/SKILL.md` (or user scope `~/.andromity/skills/anthropic-prompt-engineering/SKILL.md`) - Antigravity / Gemini CLI: `.agent/skills/anthropic-prompt-engineering/SKILL.md` - Cursor: `.cursor/rules/anthropic-prompt-engineering.mdc` - Claude Code: append to `CLAUDE.md` (or `.claude/skills/anthropic-prompt-engineering.md`) - Windsurf: append to `.windsurfrules` - Cline / Roo Code: `.clinerules/anthropic-prompt-engineering.md` - GitHub Copilot: append to `.github/copilot-instructions.md` - ChatGPT / web only: paste the content into Custom Instructions - Any other agent: save to `.agent/skills/anthropic-prompt-engineering/SKILL.md` ## 2. Create the destination file - Preserve every existing file and configuration entry. - Create parent folders as needed. - Never overwrite unrelated content. ## 3. Write exactly this content ```markdown --- name: anthropic-prompt-engineering description: "Master XML tag structure, system prompts, role prompting, scratchpad reasoning, and few-shot examples for Claude." author: anthropic license: mit version: 1.0.0 --- # Anthropic Claude Prompt Engineering Techniques for Claude 3.5 and 3.7 models: - Use explicit XML tags (`<context>`, `<instructions>`, `<rules>`, `<examples>`) to separate input elements. - Give the model a scratchpad (`<thinking>`) for complex logical deduction. - Provide canonical positive and negative examples. ``` ## 4. Verify - Confirm the file exists and is readable. - Report the destination path and confirm the "Anthropic Claude Prompt Engineering" skill is installed and active. Skill metadata: - Slug: anthropic-prompt-engineering - Category: ai-agents - License: mit - Source: AgenticMarket
Techniques for Claude 3.5 and 3.7 models:
AgenticMarket<context>, <instructions>, <rules>, <examples>) to separate input elements.<thinking>) for complex logical deduction.Master XML tag structure, system prompts, role prompting, scratchpad reasoning, and few-shot examples for Claude.
Anthropic Claude Prompt Engineering works seamlessly with Cursor (.cursor/rules), Claude Code (CLAUDE.md & .claude/skills), Windsurf (.windsurfrules), Google Antigravity (.agent/skills), Andromity (.andromity/skills), and Cline.
Click '1-Click Prompt Install' in the right sidebar or copy the prompt into your agent chat (Cursor Composer, Claude Code, or Andromity). The agent automatically configures the skill instruction file into your workspace.
Yes, Anthropic Claude Prompt Engineering is 100% free and open-source under the mit license on AgenticMarket with no per-call fees or paywalls.
Replace with description of the skill and when Claude should use it.
Build stateful AI agents, durable workflows, real-time WebSocket communication, and MCP servers on Workers.
