Skip to content
Agentmart
Submit a tool

generate-course-outline

Routine: Generate a structured course outline from a topic or source material, then stage it as a draft in TI Academy.

Skill by thoughtindustries

IndexedMIT
Write a review

Chalk Labs

Need help deploying generate-course-outline?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/thoughtindustries-generate-course-outline

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

Routine: Generate a structured course outline from a topic or source material, then stage it as a draft in TI Academy.

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/generate-course-outline

What's inside

Skill name
generate-course-outline
Description
Routine: Generate a structured course outline from a topic or source material, then stage it as a draft in TI Academy.
License
MIT
Instructions
79 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Generate Course Outline

This is a **Routine** skill — a reliable, repeatable sequence of Actions. Follow the steps exactly. Minimize judgment — the process is fixed.

## Purpose

Take a topic, learning objectives, or source material from the user and produce a complete course structure (modules/sections/lessons/topics) staged as a draft in the TI platform.

## Process

### Step 1 — Elicit inputs

Ask the user for:
- **Topic or source material** (text, URL, document, or free-form description)
- **Target audience** (beginner, intermediate, advanced; role; industry)
- **Desired length** (number of modules/lessons, or approximate duration)
- **Tone** (formal, conversational, technical, etc.)

If the user provides source material (a document, URL content, or pasted text), use it as the foundation. If they provide only a topic, generate from domain knowledge.

### Step 2 — Generate the outline

Produce a structured outline in this format:

```
Course: [Title]
  Section 1: [Module Title]
    Lesson 1.1: [Lesson Title]
      Topic 1.1.1: [Topic Title] — [brief description]
      Topic 1.1.2: [Topic Title] — [brief description]
    Lesson 1.2: [Lesson Title]
      ...
  Section 2: [Module Title]
    ...
```

Guidelines:
- 3–7 sections (modules) per course
- 2–5 lessons per section
- 1–3 topics per lesson
- Each topic should have a clear, specific scope
- **Keep the total under 25 children** (sections + lessons + topics combined) — the create endpoint rejects more than 25 per course. If the outline is larger, create the first ~25 with `create-course-draft` and attach the rest with `update-course-content` afterward.

### Step 3 — Confirm with user

Present the outline to the user. Ask for approval or edits. Iterate until the user confirms.

Do NOT proceed to Step 4 until the user explicitly approves.

### Step 4 — Create the draft

Invoke the **`create-course-draft`** action with the confirmed outline structured as the API payload:

```bash
node "${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/actions/create-course-draft/}create-course-draft.js" --file=outline.json
```

Build the JSON payload with:
- `kind`: `"courseGroup"` (default) or as specified by user
- `title`: the course title
- `sections`: array with nested `lessons` and `topics`
- Each lesson **must** include `openType` (use `"studentsOnly"` unless the user asks otherwise) — it is required by the API.
- Each topic **must** include `type` — use `"text"` for outline placeholders. A topic without `type` makes the API reject the whole request with a generic `"A processing error occurred"`. Never use `"article"` for a lesson topic (it 404s for learners and cannot be deleted); `"text"` is the correct type for HTML body content.
- Each topic `body` should contain a placeholder: `<p>[Content to be written]</p>`

Example lesson entry:
```json
{ "title": "What is an API?", "openType": "studentsOnly", "topics": [ { "title": "Overview", "type": "text", "body": "<p>[Content to be written]</p>" } ] }
```

Report back the created course IDs to the user.

<HARD-GATE>
- All content is created as DRAFT. Never call releaseContent.
- Never skip Step 3 (user confirmation). The user must approve the outline before creating it in TI.
- Do not generate full lesson body content in this routine — only titles and placeholder bodies. Use the `rewrite-lesson` routine or the `author-course` playbook for content generation.
</HARD-GATE>

From thoughtindustries/ti-admin-plugin, MIT.

More from thoughtindustries/ti-admin-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 14, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from thoughtindustries

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get generate-course-outline running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying generate-course-outline?

CallGet help
Cite this page

generate-course-outline skill. Agent Mart. https://agentmart.dev/skills/thoughtindustries-generate-course-outline (last updated 2026-10-24)