Skip to main content
skill CX Codex

create-lecture — Claude Code skill: what it does, how to install

Scaffolds LaTeX Beamer lecture decks from research papers, enforcing consistent math notation and strict pedagogical invariants.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add pedrohcgs/claude-code-my-workflow --skill create-lecture -a claude-code
Open on GitHub

What create-lecture does

The skill generates a complete Beamer .tex lecture file from source PDFs or rough notes. It initiates the process with a Pre-Flight Report that inspects the course notation registry, flags symbol conflicts, defines a pedagogical goal, and establishes a running empirical application. When run on an empty knowledge base, it proposes a starter stub to prevent deadlocks.

Drafting proceeds incrementally in batches of 5 to 10 slides once the outline receives approval. Strict constraints govern every slide: definitions require an applied example within two slides, colored boxes are capped at two per frame, and overlay tags like \pause are barred.

This tool scaffolds new slide decks rather than recompiling existing .tex files. It relies directly on .claude/rules/knowledge-base-template.md and .claude/rules/content-invariants.md residing in your project repository.

What it helps with

  • scaffold a Beamer lecture deck from research papers
  • prevent notation conflicts across course slide decks
  • generate TikZ diagrams and R figure code for lecture slides
  • enforce pedagogical constraints like examples following definitions

Example prompts for the agent

  • create a lecture on instrumental variables from these papers
  • scaffold a new Beamer file for topic 3 and check notation
  • build me a lecture from these PDFs using the project template

How to install create-lecture

1Skills CLI (Vercel)

npx skills add pedrohcgs/claude-code-my-workflow --skill create-lecture -a claude-code

2Manually: put the files in place

~/.claude/skills/create-lecture/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/create-lecture/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about create-lecture

How do I install create-lecture in Claude Code?

Run npx skills add pedrohcgs/claude-code-my-workflow --skill create-lecture -a claude-code in your terminal.

What does create-lecture do?

It scaffolds Beamer presentation decks from papers or notes while validating math notation against a central registry and adhering to strict slide design rules.

Can create-lecture compile an existing LaTeX file?

No, it only plans and drafts the slide deck structure. Compiling an existing .tex file is handled separately by /compile-latex.

Source text

SKILL.md · MIT
---
name: create-lecture
description: Create a new Beamer lecture `.tex` from source papers and materials, with notation consistency checks and the project's preamble wired in. Use when user says "create a lecture on X", "new lecture from these papers", "start a deck on topic Y", "scaffold a new Beamer file", "build me a lecture from these PDFs". Scaffolds the full deck — NOT for compiling existing `.tex` (use `/compile-latex`).
argument-hint: "[Topic name]"
allowed-tools: ["Read", "Grep", "Glob", "Write", "Edit", "Bash", "Agent", "Task"]
disable-model-invocation: true
---

# Lecture Creation Workflow

Create a beautiful, pedagogically excellent Beamer lecture deck.

**This is a collaborative, iterative process. The instructor drives the vision; Claude is a thinking partner.**

---

## CONSTRAINTS (Non-Negotiable)

1. **Read the knowledge base FIRST** — notation registry, narrative arc, applications database
2. Every new symbol MUST be checked against the notation registry
3. Motivation before formalism — no exceptions
4. Worked example within 2 slides of every definition
5. Max 2 colored boxes per slide
6. No `\pause` or overlay commands (check project rules)
7. Transition slides at major conceptual pivots
8. Thread at least 1 running empirical application throughout
9. All citations verified against the bibliography
10. **Work in batches of 5-10 slides** — share for feedback, don't bulk-dump

---

## WORKFLOW

### Phase 0: Intake & Context (Pre-Flight Report required)

Read the inputs, then produce a Pre-Flight Report in your response before Phase 1 starts.

Inputs to read:
- `.claude/rules/knowledge-base-template.md` — notation registry, narrative arc, applications
- `.claude/rules/content-invariants.md` — INV-1..INV-8 govern slide content
- Any source papers / existing slides the user provided
- The previous lecture's `.tex` (last section + ending slide) if one exists

Required Pre-Flight Report block:

```markdown
## Pre-Flight Report

**Sources read:**
- [source 1]: [one-line takeaway — what notation, what result, what diagram]
- [source 2]: ...

**Notation registry check:**
- New symbols this lecture will introduce: [list]
- Symbols reused from prior lectures: [list, with the lecture each was introduced in]
- Conflicts detected: [none / specific clashes]

**Narrative position:** [Where does this lecture sit in the course arc? What did the previous lecture end on? What does the next lecture need you to set up?]

**Pedagogical goal:** [one sentence]

**Running application:** [which real-world example threads through this deck]
```

State the pedagogical goal, get user confirmation, then proceed.

**First-lecture fallback (fresh fork, empty knowledge base).** If `.claude/rules/knowledge-base-template.md` still has unfilled placeholder tables (no notation registry entries, no applications, no prior lectures in `Slides/`), do NOT halt waiting for it. Instead:

1. Acknowledge the template is empty and we're creating the course's first lecture.
2. Propose a **minimal starter knowledge base** from the user's topic: 5-8 key symbols with conventions, 1-2 running applications, a short narrative arc (intro → main idea → implications). Present for approval.
3. Write the approved stub into the knowledge base template so subsequent lectures inherit it.
4. Continue to Phase 1.

This prevents `/create-lecture` from deadlocking for every new forker.

### Phase 1: Paper Analysis (When Papers Provided)
- Split into chunks, extract key ideas
- Map paper notation → course notation
- Identify slide-worthy content
- Present summary for approval

### Phase 2: Structure Proposal
- Propose outline (5-Act or 3-Part template)
- List TikZ diagrams and R figures needed
- List new notation to introduce
- **GATE: User approves before Phase 3**

### Phase 3: Draft Slides (Iterative)
- Work in batches of 5-10 slides
- Check notation, apply creation patterns
- Quality checks during drafting

### Phase 4: Figures & Code
- R scripts following conventions
- TikZ diagrams in Beamer source (single source of truth)
- Save RDS for future Quarto integration

### Phase 5: Polish & Compile
- Full 3-pass compilation
- Run Devil's Advocate
- Run Substance Review (if domain reviewer configured)
- Update knowledge base with new notation

---

## Post-Creation Checklist

```
[ ] Lecture compiles without errors
[ ] No overfull hbox > 10pt
[ ] All citations resolve
[ ] Every definition has motivation + worked example
[ ] Max 2 colored boxes per slide
[ ] 2-3 Socratic questions embedded
[ ] Transition slides between sections
[ ] At least 1 running application threaded throughout
[ ] New notation added to knowledge base
[ ] Session log updated
[ ] Devil's Advocate run
```

## Cross-references

- [`.claude/skills/translate-to-quarto/SKILL.md`](../translate-to-quarto/SKILL.md) — port the finished Beamer deck to a Quarto RevealJS mirror.
- [`.claude/skills/qa-quarto/SKILL.md`](../qa-quarto/SKILL.md) — adversarial Beamer↔Quarto parity (loop-until-dry).
- [`.claude/skills/deploy/SKILL.md`](../deploy/SKILL.md) — render + publish the lecture to GitHub Pages.
- [`.claude/skills/scaffold-exercises/SKILL.md`](../scaffold-exercises/SKILL.md) — problem sets + solutions to accompany the lecture.

© pedrohcgs · MIT · pedrohcgs/claude-code-my-workflow

Similar skills

All skills for Writing and docs →

From the same set56

deep-audit Splits a theory, proof, paper or codebase into components, fans out independent skeptics and fixes every confirmed defect. Built for when one review pass is not enough. CX Codex +1 ★ 1,671repo stars data-management-plan Generates funder-compliant Data Management Plans for NSF, NIH, ERC, and Horizon Europe proposals. Useful when drafting grant applications or planning project data workflows. CX Codex +1 ★ 1,671repo stars data-analysis This skill runs an R analysis workflow from data inspection to regressions and publication-ready tables and figures. Use it when a dataset needs empirical analysis. CX Codex +1 ★ 1,671repo stars credible-claims A skill for delegated and AI-assisted research: write the brief before the run, the claim record after. Keeps fast execution from passing as credible evidence. CX Codex +1 ★ 1,671repo stars context-status This skill checks estimated context use, the active plan, and session preservation. Use it to see what may remain after compaction. CX Codex +1 ★ 1,671repo stars compress-session This skill turns the current conversation into a structured note with decisions, open questions and next steps before auto-compaction eats the context. CX Codex +1 ★ 1,671repo stars compile-latex Compiles Beamer slide decks using XeLaTeX across three passes and BibTeX. Helpful when rendering slides inside Slides/ with custom themes and citations. CX Codex +1 ★ 1,671repo stars commit Runs quality, consistency and passport gates, branches off main, stages named files, and writes a commit whose subject states what now holds true. CX Codex +1 ★ 1,671repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor