Skip to content
Agentmart
Submit a tool

create-lecture

Generates a structured lecture from an unordered list of topics.

Skill by atrnh

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/atrnh-create-lecture

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generates a structured lecture from an unordered list of topics. The agent sequences the topics pedagogically, produces _outline.md for review, and then generates the full lecture as index.rst following the Lecture Style Guide and RST conventions. Trigger when the user asks to "create a lecture", "generate lecture content", or "write a lecture from topics." Topics may be provided inline or in a file. Do NOT trigger for converting existing documents or editing already-written lectures.

Use cases: writing, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/create-lecture

What's inside

Skill name
create-lecture
Description
Generates a structured lecture from an unordered list of topics. The agent sequences the topics pedagogically, produces _outline.md for review, and then generates the full lecture as index.rst following the Lecture Style Guide and RST conventions. Trigger when the user asks to "create a lecture", "generate lecture content", or "write a lecture from topics." Topics may be provided inline or in a file. Do NOT trigger for converting existing documents or editing already-written lectures.
License
MIT
Instructions
229 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • lecture-style-guide.md · references/

SKILL.md (first lines)

# Create Lecture

Generate a well-structured lecture from an unordered list of topics, following
the Lecture Style Guide and producing a Sphinx-compatible `index.rst`.

## Step 1: Read the Prerequisites

Two sources define the rules that apply throughout this skill. Read both
before drafting any content:

- **`references/lecture-style-guide.md`** (bundled with this skill) --- the
  authoritative source for publication formats, page structure, tone, voice,
  pronouns, and content progression. Pay close attention to the Do/Don't
  examples; they're the fastest way to calibrate the correct register.

- **The `convert-to-restructuredtext` skill** --- defines heading decorations,
  list formatting, inline markup, code blocks, dashes and quotes, hyperlinks,
  and other general RST conventions used throughout the lecture.

Later steps reference these sources instead of restating them. If you're
unsure about a rule while writing, re-open the relevant file rather than
guessing.

## Step 2: Parse Topics

Collect all topics from the user's input. Topics may be:

- Listed inline in the user's message

- Provided in a file (use the Read tool if a path is given)

Do not assume any order is intended---you determine the order in Step 3.

If an output directory is not clear from context, ask the user where to save
the output files before continuing.

## Step 3: Determine Topic Order

Sequence the topics pedagogically so the lecture builds understanding
progressively:

- **Foundational first**: prerequisites before the concepts that depend on them

- **Cluster related topics**: group concepts that share context or vocabulary

- **Simple to complex**: concrete, narrow cases before abstract or general ones

- **Problem-solution framing**: introduce the problem a concept solves before
  introducing the concept itself

Write down your ordered list and the reasoning behind your sequencing
decisions---you'll reference this when writing the outline.

## Step 4: Create `_outline.md`

Write `_outline.md` to the output directory. Use this skeleton, following the
page structure from the Lecture Style Guide:

```markdown
# [Lecture Title]

## Overview

[One paragraph: what this lecture covers and why it matters to the reader as a
developing professional.]

## Learning Goals

- [Concrete, measurable goal 1]
- [Concrete, measurable goal 2]
- ...

## [Topic Section 1 Title]

### [Subsection Title] *(if needed)*

- **Key concept**: [What it is and why it matters]
- **Example / analogy**: [The concrete anchor to use]
- **Gotcha**: [Common mistake or stumbling block to flag] *(if applicable)*

## [Topic Section N Title]

...

## Looking Ahead

[What concepts or skills does this lecture lead into?]

## Further Study

- [Resource 1 --- title and brief description]
- [Resource 2 --- title and brief description]

## Coming Up

[Brief preview of the next related lab or lecture.]
```

After writing the file, **present the outline to the user and ask for
confirmation before generating the lecture**. If the user requests changes,
revise `_outline.md` and confirm again before proceeding.

## Step 5: Generate `index.rst`

Using the confirmed outline, write the full lecture to `index.rst` in the
output directory.

Apply the tone, voice, and content-progression rules from
`references/lecture-style-guide.md` (read in Step 1) and the general RST
formatting rules from the `convert-to-restructuredtext` skill (also read in
Step 1). Do not try to recall them from memory---re-open either file if you're
unsure.

The sections below cover only what's specific to lectures and not already in
those sources: the lecture skeleton and a handful of lecture-only RST
directives.

---

From atrnh/skills, MIT.

More from atrnh/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 22, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from atrnh

Cite this page

create-lecture skill. Agent Mart. https://agentmart.dev/skills/atrnh-create-lecture (last updated 2026-10-24)