Hung-Yi Lee Teaching Style
voidful/hung-yi-lee-skill
Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.
Routes a topic, question or bug to the exact lessons in the AI Engineering from Scratch curriculum and suggests the next command to run.
Install AI Engineering Course Guide
$ npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rohitg00/ai-engineering-from-scratch course-guide --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/course-guide .claude/skills/course-guide && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "course-guide" agent skill from https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guide into .claude/skills/course-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-guide", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guideType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rohitg00/ai-engineering-from-scratch course-guide --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/course-guide .agents/skills/course-guide && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "course-guide" agent skill from https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guide into .agents/skills/course-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-guide", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rohitg00/ai-engineering-from-scratch course-guide --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/course-guide .cursor/skills/course-guide && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "course-guide" agent skill from https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guide into .cursor/skills/course-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-guide", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rohitg00/ai-engineering-from-scratch.git --path skills/course-guide--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rohitg00/ai-engineering-from-scratch course-guide --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/course-guide .gemini/skills/course-guide && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "course-guide" agent skill from https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guide into .gemini/skills/course-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-guide", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rohitg00/ai-engineering-from-scratch course-guideInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/course-guide .github/skills/course-guide && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "course-guide" agent skill from https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guide into .github/skills/course-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-guide", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rohitg00/ai-engineering-from-scratch course-guide --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/course-guide .opencode/skills/course-guide && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "course-guide" agent skill from https://github.com/rohitg00/ai-engineering-from-scratch/tree/main/skills/course-guide into .opencode/skills/course-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-guide", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
course-guide- GitHub stars
- 66k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 829 words
- Files
- 1
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- MIT
At a glance
Routes a topic, question or bug to the exact lessons in the AI Engineering from Scratch curriculum and suggests the next command to run.
- Works in 4 steps: Interpret the ask, which arrives in one… → Scan the Contents tables for matching… → Answer in this shape, and keep it under… → …
- Finding which lesson covers a topic such as transformers or MCP
- SKILL.md covers Host invocation contract, Routing table and How to route
- Reaches aiengineeringfromscratch.com
What it does
It works as a wayfinding layer over a curriculum of 523 lessons in 20 phases. The learner says what they want to understand, build or fix, and the agent points to the matching lessons using the lesson tables in the repository README, read locally when the repo is cloned and otherwise fetched from GitHub, then names the command to run next.
Next steps are written in the syntax each host expects: skill names in Codex, slash commands in Claude Code and plain language elsewhere, and a slash command is never presented as universal. Focused routes send Claude certification preparation to claude-certification, Model Context Protocol topics to learn-mcp, and Agent Skills topics to learn-agent-skills, each with its own source file. A glossary of terms is also available.
When your agent uses it
- Finding which lesson covers a topic such as transformers or MCP
- Getting unstuck on a bug and asking what to do next in the course
- Preparing for a Claude certification through the course routes
Example prompts
- “Which lesson covers retrieval-augmented generation?”
- “I'm stuck on a tool-calling bug. Where in the course should I look?”
- “Teach me Agent Skills.”
- “Where do I prepare for a Claude certification?”
Requirements
- The curriculum repository cloned, or network access to fetch its README
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Interpret the ask, which arrives in one of six shapes
- Scan the Contents tables for matching lessons by title and phase
- Answer in this shape, and keep it under ~12 lines
- If nothing matches, say so plainly and name the closest phase. Never
What it can do on your machine
Read from SKILL.md and the folder at commit 7a181b4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
aiengineeringfromscratch.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
AI Engineering Course Guide loads about 1.7k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 829 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from rohitg00/ai-engineering-from-scratch at commit 7a181b4, republished under its MIT licence (© rohitg00). 829 words, ~1,664 tokens.
Download SKILL.mdSave it as
.claude/skills/course-guide/SKILL.md (or your agent's skills folder).- name
- course-guide
- description
- Topic router for the AI Engineering from Scratch curriculum. Give it a topic, a question, or a bug you are fighting, and it points at the exact lessons that teach it, plus the right next command. Trigger phrases: "where do I learn", "which lesson covers", "course guide", "I'm stuck on", "what should I do next", "teach me MCP", "teach me Agent Skills", "where do I prepare for a Claude certification"
- version
- 1.0.0
- tags
- navigation, curriculum, ai-engineering, router
Course Guide
You are the wayfinding layer over the AI Engineering from Scratch curriculum: 523 lessons, 20 phases. The learner tells you what they want to understand, build, or fix; you tell them exactly where in the course that lives and which command to run next. Works with any agent.
Host invocation contract
Skill names are portable, but invocation syntax belongs to the host. Render every recommended next action in the correct form:
- Codex:
learn,start-learning,course-guide, and otherskill-nameforms, or tell the learner to choose the skill from/skills. - Claude Code:
/learn,/start-learning,/course-guide, and other/skill-nameforms. - Other compatible hosts: natural language such as
Use learn to teach this lesson.
Never present a slash command as universal syntax. If the host is unknown, use natural language.
Routing table
The curriculum's single source of truth is the Contents section of the repo
README: every phase has a table listing each lesson's number, title, type
(Build/Learn), language, and directory path. Read README.md locally if the
repo is cloned; otherwise fetch:
https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/README.mdFor term definitions, the glossary lives at glossary/terms.md (same rule:
local first, raw fallback).
Claude certification routes are a separate, AI-native curriculum. For CCAO-F,
CCDV-F, CCAR-F, CCAR-P, Claude certification, exam preparation, diagnostics, or
mocks, route to claude-certification. Its sources are
certifications/claude/program.json, certifications/claude/tracks/*.json, and
certifications/claude/GETTING_STARTED.md.
Model Context Protocol (MCP) has a focused route. For MCP clients, servers, JSON-RPC,
stateless requests, transports, MRTR, tasks, authorization, gateways,
registries, reliability, or conformance, route to learn-mcp.
Its source of truth is learning-paths/model-context-protocol.json, its order is
manifest order rather than numeric next navigation, and its state lives in
MCP-LEARNING.md.
Agent Skills has a separate focused route. For Agent Skills, SKILL.md, skill
discovery, invocation, human or model invocability, permission boundaries,
sandboxes, skill evals, packaging, or portability, route to
learn-agent-skills. Its source of truth is
learning-paths/agent-skills.json. This route intentionally contains five
ordered lessons, so it is the exception to the usual 1-3 lesson limit. Tool
poisoning is a knowledge preflight for Lesson 26; Lesson 15 is an optional
refresher outside the route.
How to route
Interpret the ask, which arrives in one of six shapes:
- Topic ("attention", "how do diffusion models work") → find the lessons that teach it.
- Struggle ("my agent loops forever", "loss goes to NaN") → find the lessons whose material diagnoses it. Route bugs to the concept behind them, not just the tool: a NaN loss points at the loss-functions and numerical-stability lessons, not merely a framework FAQ.
- Meta ("what should I do next", "am I ready for phase 7") → read
LEARNING.mdin the current directory if it exists and answer from their actual progress; otherwise recommendstart-learningusing the host invocation contract. - Certification ("prepare me for CCDV-F", "Claude architect mock") →
route directly to
claude-certification. Do not mix certification state intoLEARNING.md; that tutor usesCLAUDE-CERTIFICATION.md. - Model Context Protocol (MCP) ("teach me MCP", "build a production MCP server")
→ route directly to
learn-mcp. Do not place the learner in the generic phase sequence; use the 17 ordered lessons in its manifest. - Agent Skills ("teach me skills", "how does a skill run in a sandbox")
→ route directly to
learn-agent-skills. Do not send the learner from Lesson 22 to numeric Lesson 23; the manifest order is 22, 24, 25, 26, 27 and progress lives inAGENT-SKILLS-LEARNING.md.
Scan the Contents tables for matching lessons by title and phase theme. Prefer precision: 1-3 lessons, not a phase dump. For a struggle, titles are not enough evidence: fetch each shortlisted lesson's
docs/en.md(local first, raw fallback) and confirm it actually covers the failing concept before recommending it. Skip this scan for the focused Model Context Protocol (MCP) and Agent Skills routes and use their manifests instead.Answer in this shape, and keep it under ~12 lines:
- The 1-3 lessons: phase, number, title, one line on why this one, and
the direct link
https://aiengineeringfromscratch.com/lesson?path=phases/<phase-dir>/<lesson-dir>. - Prerequisites, only if genuinely needed ("this assumes the backprop lesson; skip it if you can already derive a gradient by hand").
- The next action, rendered with the host invocation contract:
learnto be taught the lesson right now,check-understanding <phase>to test instead, orstart-learningif they have no plan and seem to want one. For Model Context Protocol (MCP), give the manifest link and makelearn-mcpthe next skill. For Agent Skills, give the five lesson order once and makelearn-agent-skillsthe next skill.
- The 1-3 lessons: phase, number, title, one line on why this one, and
the direct link
If nothing matches, say so plainly and name the closest phase. Never invent a lesson that does not exist.
Show full SKILL.md (89 more words)Show less
The learner may also just be deciding between the course's own commands.
The full set, for reference: start-learning (build the plan), learn (next
lesson, taught interactively), check-understanding <phase> (phase quiz),
find-your-level (placement only), and course-guide (this). Render the
selected skill with the host invocation contract above.
Use learn-agent-skills for the focused Agent Skills route and its
AGENT-SKILLS-LEARNING.md state.
Use learn-mcp for the focused MCP route and its
MCP-LEARNING.md state. Use the host invocation recorded in the
manifest.
Use claude-certification for a certification route, lab, diagnostic, mock,
or remediation session.
© rohitg00, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/course-guide of rohitg00/ai-engineering-from-scratch.
Open the folder on GitHubat commit 7a181b4
Compare with similar skills
AI Engineering Course Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| AI Engineering Course Guide this skillrohitg00/ai-engineering-from-scratch | 66k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill | 1.3k | — | ~13k | Automated safety check: Pass | None | |
| Learnfancyboi999/ai-engineering-from-scratch-zh | 1.2k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Workshopbrevdev/workshop-build-an-agent | 144 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Workshopbrevdev/workshop-build-an-agent | 144 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Claude Academy Guideanthropics/skills | 180k | 3 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Learn
fancyboi999/ai-engineering-from-scratch-zh
AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md，获取下一课， 在终端按章节教学，结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语：“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”，或 "next lesson", "teach…
Workshop
brevdev/workshop-build-an-agent
This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g.
Workshop
brevdev/workshop-build-an-agent
This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g.
- Official
Claude Academy Guide
anthropics/skills
Adds a matching Claude Academy course, tutorial or use case to the end of an answer about learning to use Claude, but only when the match is strong.
Feynman Learning Cycle Classroom
THU-MAIC/OpenMAIC
Turns a concept or lesson material into a Feynman-style classroom where learners explain first, find their smallest gap, rebuild the idea and apply it somewhere new.
More from rohitg00/ai-engineering-from-scratch
All 16 skills in this repoSkill Release Gate
rohitg00/ai-engineering-from-scratch
Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.
AI Engineering Placement Quiz
rohitg00/ai-engineering-from-scratch
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
AI Engineering Project Tutor
rohitg00/ai-engineering-from-scratch
Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.
AI Engineering Phase Quiz
rohitg00/ai-engineering-from-scratch
Quizzes you on a completed phase of the AI Engineering from Scratch course, taking a phase number or name and mapping it to that phase's directory.
Claude Certification Tutor
rohitg00/ai-engineering-from-scratch
Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.
AI Engineering Course Tutor
rohitg00/ai-engineering-from-scratch
Teaches the next lesson of the AI Engineering from Scratch curriculum in the terminal, quizzes you at the end and records your progress.
Related
Works with
Categories
Questions about AI Engineering Course Guide
What does AI Engineering Course Guide do?
Routes a topic, question or bug to the exact lessons in the AI Engineering from Scratch curriculum and suggests the next command to run. It works as a wayfinding layer over a curriculum of 523 lessons in 20 phases. The learner says what they want to understand, build or fix, and the agent points to the matching lessons using the lesson tables in the repository README, read locally when the repo is cloned and otherwise fetched from GitHub, then names the command to run next.
When should I use AI Engineering Course Guide?
AI Engineering Course Guide fits situations like: finding which lesson covers a topic such as transformers or MCP; getting unstuck on a bug and asking what to do next in the course; preparing for a Claude certification through the course routes.
How do I install AI Engineering Course Guide in Claude Code?
Run `npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a claude-code`. Or copy the skill folder (skills/course-guide in rohitg00/ai-engineering-from-scratch) into .claude/skills/course-guide in your project. Claude Code loads it when a task matches its description.
How do I install AI Engineering Course Guide in Codex?
Run `npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a codex`. Or copy the skill folder (skills/course-guide in rohitg00/ai-engineering-from-scratch) into .agents/skills/course-guide in your project. Codex loads it when a task matches its description.
Can I use AI Engineering Course Guide in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rohitg00/ai-engineering-from-scratch --skill course-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/course-guide, .gemini/skills/course-guide, .github/skills/course-guide and .opencode/skills/course-guide in your project.
What does AI Engineering Course Guide need to run?
SKILL.md names no scripts, command-line tools or credentials: AI Engineering Course Guide is instructions for the agent only. Our summary lists: The curriculum repository cloned, or network access to fetch its README.
Does AI Engineering Course Guide access the network?
SKILL.md names 1 domain. In commands or code: aiengineeringfromscratch.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is AI Engineering Course Guide safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does AI Engineering Course Guide use?
AI Engineering Course Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does AI Engineering Course Guide use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to AI Engineering Course Guide?
Skills that share tags, products or a category with AI Engineering Course Guide: Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars), Learn (fancyboi999/ai-engineering-from-scratch-zh, 1.2k stars), Workshop (brevdev/workshop-build-an-agent, 144 stars) and Workshop (brevdev/workshop-build-an-agent, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Engineering Course Guide?
rohitg00 (a GitHub user) maintains it in rohitg00/ai-engineering-from-scratch, which has 65,647 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.
Source: rohitg00/ai-engineering-from-scratch on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.