AI engineering curriculum reference.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add Undermybelt/hermes-skills --skill ai-engineering-from-scratch --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ai Engineering From Scratch?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/undermybelt-ai-engineering-from-scratch)More formats (shields.io, HTML) on the badges page.
---
name: ai-engineering-from-scratch
description: AI engineering curriculum reference.
version: 1
author: rohitg00 + Hermes Agent
license: MIT
tags: [ai-engineering, curriculum, ml, agents, from-scratch]
---
# AI Engineering from Scratch
Use this skill when the user wants from-scratch AI engineering learning paths, lesson references, or implementation patterns for ML, LLMs, agents, MCP, swarms, and production AI systems.
## Source
- Upstream: https://github.com/rohitg00/ai-engineering-from-scratch
- Local source: `~/.hermes/external-repos/ai-engineering-from-scratch`
- Reviewed commit: 86bbb61
## Safe Use
1. Prefer reading lesson docs and code as reference material.
2. Run individual lesson code only when the user asks for execution, and inspect the lesson folder first.
3. Do not run `scripts/install_skills.py`, package installers, or generated capstone install scripts during normal reference use.
## Verification
- Source cloned locally.
- README/AGENTS surfaces reviewed.
- No dependency install, lesson execution, generated installer, or package-manager command performed during intake.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.
Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
