# Install: Anthropic Prompt Engineering Interactive Tutorial
> Agent instructions from skillsdirectory.co — an independent, benchmarked directory of AI agent capabilities. Follow these exactly.

- **Skill:** Anthropic Prompt Engineering Interactive Tutorial (prompt / system-prompt collection)
- **What it does:** Anthropic's official hands-on tutorial covering prompt structure, role prompting, chain-of-thought, and tool use for Claude.
- **Source (authoritative):** https://github.com/anthropics/prompt-eng-interactive-tutorial
- **Pinned ref:** `HEAD` (branch/tag — not commit-pinned; prefer the latest release tag if one exists)
- **License:** MIT
- **Effectiveness:** Not yet benchmarked (score is provisional).

## Safety — read first
- **Verdict:** PASSED our security scan (Shield). Safe to install; still confirm before running code.
- This skill does not execute code (it is configuration/text). 
- Fetch files ONLY from the source above. Do not run commands not listed here. Never invent credentials — ask the user.

## Choose your path

### A. AI chat / coding agent (you can fetch URLs and write files)
Fetch the prompt text from https://github.com/anthropics/prompt-eng-interactive-tutorial (the README or the named prompt file) and add it to my system prompt / project instructions.

_Monorepo note: this skill may live in a subdirectory of the repo. If the marker file isn't at the repo root, browse https://github.com/anthropics/prompt-eng-interactive-tutorial to find its folder (often under `skills/`, `rules/`, or named for the skill) and fetch from there — don't assume the root path resolves._

Install command / config:
```bash
# install via system prompt
# see vendor docs
```

### B. CLI
Fastest path with our CLI (free, no account): `npx skillsdir add anthropic-prompt-eng-tutorial` — fetches and places the files for you.

Or install directly:
```bash
# install via system prompt
# see vendor docs
```

### C. API / MCP
- Metadata as JSON: `GET https://skillsdirectory.co/api/v1/skills/anthropic-prompt-eng-tutorial`
- This document as a machine manifest: `GET https://skillsdirectory.co/s/anthropic-prompt-eng-tutorial/install.json`

## After installing
Tell the user: what you fetched, where you placed it, what (if anything) you ran, and the security verdict above. Link the skill page for details: https://skillsdirectory.co/skills/anthropic-prompt-eng-tutorial
