How do I install the New Course skill?

Run npx skillmds@latest add https-deeplearning-ai/new-course in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is New Course safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with New Course?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is New Course free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published New Course?

https-deeplearning-ai (@https-deeplearning-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

New Course by https-deeplearning-ai

Name: New Course
Author: https-deeplearning-ai

New Course

Adds a new course to the spec-build-lab. Use this skill ANY time the user wants to register, scaffold, set up, add, create, init, or start tracking a NAMED COURSE in this repo — including phrasings like "scaffold a new course called X", "set up a course folder for X", "make a new course called X", "add the X course", "init the X course", "let's start tracking the X course", "I want to add a new course", "/new-course X", or any user message naming a course they want to begin. This skill copies templates/course/ to courses/<name>/ and nothing else; it does NOT read materials, write spec.md, or run a build. If the user asks anything about an EXISTING course, do NOT use this skill. Always run from the repo root.

File contents

new-course

Scaffold courses/<name>/ from templates/course/. This skill ONLY copies the template; it does not read materials and does not generate spec.md.

Steps

Verify cwd is the repo root. Confirm both paths exist relative to cwd:
- templates/course/
- .claude/skills/new-course/ If either is missing, refuse with: "Run /new-course from the repo root — the folder containing templates/ and .claude/." Stop.
Require the course name. If $ARGUMENTS is empty (or the user did not provide a name in their message), ask: "What should the course be called? It becomes the folder name under courses/." Stop until they answer.
Refuse on collision. If courses/$ARGUMENTS/ exists, refuse with: "courses/$ARGUMENTS/ already exists. Pick a different name or remove the existing folder first." Stop.

Copy the template:

cp -R templates/course/ "courses/$ARGUMENTS/"

Report and hand off. Tell the user, in this order:
1. "Scaffolded courses/$ARGUMENTS/."
2. "Get notebooks + transcripts from https://course-context-lab.vercel.app — that's where this lab's course materials are produced. Download them yourself; I won't WebFetch from there."
3. "Tip: once they're downloaded, drag the files from Finder into this terminal window. The terminal pastes their absolute paths, and I can cp them into courses/$ARGUMENTS/materials/notebooks/ and courses/$ARGUMENTS/materials/transcripts/ — saves tokens versus having me traverse your filesystem."
4. "Then cd courses/$ARGUMENTS and run /generate-spec when the materials are in place — say 'go ahead' when you're ready."
5. "Optional extra: if you also want the course's real code, find the course at https://github.com/deeplearningai-eng/courses and run /ingest-course-repo <course-folder-URL> before /generate-spec — it adds the .ipynb files and helper.py under courses/$ARGUMENTS/materials/notebooks/from-repo/. This is an addition to step 2, not a replacement: the notebooks .md and the transcripts still come from the site."

Don't

Don't read or write materials/, spec.md, builds/, or evals/.
Don't cd for the user — they choose when to move into the course folder.
Don't run from inside an existing course folder. The session is anchored at the repo root.
Don't WebFetch from course-context-lab.vercel.app — point the user at it; let them download manually. The agent doesn't pull course content from the web.

---name: new-coursedescription: Adds a new course to the spec-build-lab. Use this skill ANY time the user wants to register, scaffold, set up, add, create, init, or start tracking a NAMED COURSE in this repo — including phrasings like "scaffold a new course called X", "set up a course folder for X", "make a new course called X", "add the X course", "init the X course", "let's start tracking the X course", "I want to add a new course", "/new-course X", or any user message naming a course they want to begin. This skill copies templates/course/ to courses/<name>/ and nothing else; it does NOT read materials, write spec.md, or run a build. If the user asks anything about an EXISTING course, do NOT use this skill. Always run from the repo root.---# new-courseScaffold `courses/<name>/` from `templates/course/`. This skill ONLY copiesthe template; it does not read materials and does not generate `spec.md`.## Steps1. **Verify cwd is the repo root.** Confirm both paths exist relative to cwd: - `templates/course/` - `.claude/skills/new-course/` If either is missing, refuse with: "Run /new-course from the repo root — the folder containing templates/ and .claude/." Stop.2. **Require the course name.** If `$ARGUMENTS` is empty (or the user did not provide a name in their message), ask: "What should the course be called? It becomes the folder name under courses/." Stop until they answer.3. **Refuse on collision.** If `courses/$ARGUMENTS/` exists, refuse with: "courses/$ARGUMENTS/ already exists. Pick a different name or remove the existing folder first." Stop.4. **Copy the template:** ```bash cp -R templates/course/ "courses/$ARGUMENTS/" ```5. **Report and hand off.** Tell the user, in this order: 1. "Scaffolded courses/$ARGUMENTS/." 2. "Get notebooks + transcripts from https://course-context-lab.vercel.app — that's where this lab's course materials are produced. Download them yourself; I won't WebFetch from there." 3. "Tip: once they're downloaded, drag the files from Finder into this terminal window. The terminal pastes their absolute paths, and I can `cp` them into courses/$ARGUMENTS/materials/notebooks/ and courses/$ARGUMENTS/materials/transcripts/ — saves tokens versus having me traverse your filesystem." 4. "Then `cd courses/$ARGUMENTS` and run /generate-spec when the materials are in place — say 'go ahead' when you're ready." 5. "Optional extra: if you also want the course's real code, find the course at https://github.com/deeplearningai-eng/courses and run `/ingest-course-repo <course-folder-URL>` before /generate-spec — it adds the `.ipynb` files and `helper.py` under courses/$ARGUMENTS/materials/notebooks/from-repo/. This is an addition to step 2, not a replacement: the notebooks `.md` and the transcripts still come from the site."## Don't- Don't read or write `materials/`, `spec.md`, `builds/`, or `evals/`.- Don't `cd` for the user — they choose when to move into the course folder.- Don't run from inside an existing course folder. The session is anchored at the repo root.- Don't WebFetch from `course-context-lab.vercel.app` — point the user at it; let them download manually. The agent doesn't pull course content from the web.

Frequently asked questions