Skip to content
Documentation
Command

/start-14-4.en

Lesson command

From plugin
ai-agent-camp
345200 skills8 agents200 commands
Install
$ npx -y skills add minicoohei/ai-agent-camp --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/start-14-4.en

Context preview

What this command does when you run it.

Lesson command

Command definition

start-14-4.en.md
description: "Lesson command"
chapter: "courses/aiagent/lesson03-core/module14-article-writing/chapter.yaml"
category: "lesson"
duration: "~40 min"
prerequisites: ["start-14-3"]
level: "intermediate"
tags: ["article", "illustration"]
nonInteractiveMode: deferred

๐ŸŽ“ Lesson 14-4: Illustration Planning and Generation - nanobanana + PlantUML

๐Ÿ“ What You'll Do

Welcome to **Lesson 14-4: Illustration Planning and Generation - nanobanana + PlantUML**!

| Item | Details | |------|---------| | Goal | Detect illustration markers in the article and auto-generate illustrations with nanobanana and PlantUML | | Duration | ~40 min | | Skills Used | nanobanana, diagram-generator | | Prerequisites | Gemini API key configured, Lesson 14-3 (draft) complete | | Course Page | Refer to [Module 14: Article Writing](https://ai-agent.camp/en/course/module-14) in parallel |

**Session flow:** 1. Check illustration markers (`<!-- illustration: ... -->`) in the draft 2. For type=diagram markers โ†’ generate diagrams with PlantUML 3. For type=image markers โ†’ generate images with nanobanana 4. Embed the generated images in Markdown

By the end of this session, an article draft with illustrations will be complete.

> **๐Ÿ’ก Hint**: If the AI response stops midway, type "please continue" or "it stopped" to resume. Responses may pause depending on the tool, but this is not a malfunction.

---

๐ŸŽฏ Readiness Check

First, let's confirm everything is ready.

**AskQuestion settings:**

{
  "title": "๐ŸŽฏ Pre-Session Check",
  "questions": [{
    "id": "readiness",
    "prompt": "Are you ready?",
    "options": [
      {"id": "ready", "label": "Ready! Let's start"},
      {"id": "check_prereq", "label": "I want to check the prerequisites"},
      {"id": "view_html", "label": "I want to see the course page first"},
      {"id": "different_lesson", "label": "I want to go to a different lesson"}
    ]
  }]
}

(ready โ†’ Proceed to Step 1) (check_prereq โ†’ Run prerequisite check) (view_html โ†’ Show course page path) (different_lesson โ†’ Display module list)

---

๐Ÿš€ Step 1: Check Illustration Markers in the Draft

In Codex, you typically select from choices in chat to choose the marker detection method.

**AskQuestion settings example:**

{
  "title": "๐Ÿš€ Step 1: Check Illustration Markers",
  "questions": [{
    "id": "marker_method",
    "prompt": "How would you like to detect illustration markers?",
    "options": [
      {"id": "auto_detect", "label": "Auto-detect markers"},
      {"id": "manual_specify", "label": "Manually specify illustration locations"}
    ]
  }]
}

**If "Auto-detect markers":** Input:

Read output/article-14-3-draft-final.md and
extract all illustration markers (<!-- illustration: ... -->).

List the following for each marker:
1. Line number
2. Type (image / diagram)
3. Description text
4. Surrounding context (which section it belongs to)

If markers are missing, suggest locations where they should be added.

**If "Manually specify illustration locations":**

Display the contents of output/article-14-3-draft-final.md.
Specify where you want to insert illustrations, and markers will be added.

**Expected result**: All illustration markers in the draft are listed, and a generation plan is established.

---

๐Ÿš€ Step 2: Generate Diagrams with PlantUML (type=diagram)

In Codex, you typically select from choices in chat: "Continue / Review examples / Skip".

**AskQuestion settings example:**

{
  "title": "๐Ÿš€ Step 2: Generate Diagrams with PlantUML",
  "questions": [{
    "id": "step_action",
    "prompt": "What would you like to do with this step?",
    "options": [
      {"id": "practice", "label": "Continue"},
      {"id": "review", "label": "Just review examples"},
      {"id": "skip", "label": "Skip (if no diagram markers)"}
    ]
  }]
}

**Post-selection instructions (example)**: Input:

Use the diagram-generator skill to generate diagrams for the following illustration markers.

Target marker:
<!-- illustration: type=diagram, description="Work efficiency improvement flow chart" -->

Generation conditions:
- Format: PlantUML โ†’ PNG image
- Style: Simple, easy-to-read color scheme
- Output: output/images/article-14-4-diagram-1.png

Execution command:
uv run python tools/generate_diagram.py --type flowchart --topic "Work efficiency improvement flow" --output output/images/article-14-4-diagram-1.png

Generate images for all diagram markers.

**Expected result**: PlantUML-based diagram images are generated in output/images/.

---

๐Ÿš€ Step 3: Generate Images with nanobanana (type=image)

In Codex, you typically select from choices in chat: "Continue / Review examples / Skip".

**AskQuestion settings example:**

{
  "title": "๐Ÿš€ Step 3: Generate Images with nanobanana",
  "questions": [{
    "id": "step_action",
    "prompt": "What would you like to do with this step?",
    "options": [
      {"id": "practice", "label": "Continue"},
      {"id": "review", "label": "Just review examples"},
      {"id": "skip", "label": "Skip (if no image markers)"}
    ]
  }]
}

**Post-selection instructions (example)**: Input:

Use the nanobanana skill to generate images for the following illustration markers.

Target marker:
<!-- illustration: type=image, description="Business professional working with AI tools" -->

Generation conditions:
- Style: Modern, clean illustration style
- Size: Aspect ratio suitable for article illustrations (16:9 or 4:3)
- Output: output/images/article-14-4-image-1.png

Execution command:
uv run python tools/nanobanana.py --prompt "Business professional working with AI tools, modern illustration style" --output output/images/article-14-4-image-1.png

Generate images for all image markers.

**Expected result**: Illustration images generated with nanobanana are saved in output/images/.

---

๐Ÿš€ Step 4: Embed Generated Images in Markdown

In Codex, you typically select from choices in chat: "Cont

Read more
Ships withai-agent-camp

AI Agent Training for Non-Engineers - Complete Guide to Claude Code / Cursor / Codex ### โš ๏ธ Before you clone Official repository (maintained by the authors): Running AI agents from this repo grants them shell, file-write, and external-API permissions on your

Get the whole plugin