Visual Storytellingof Story Design, Text writing, AI Image (Gemini), HTML Layout, Integration Editing an agent team collaborates to production to line. 'Visual Story ', 'in Planning', 'Image+ combination', 'Visual in', 'Story page production', ' Story', 'Visual Planning', 'Image in', ' Story', 'Visual Narrative' etc. Imageand Text Storytelling productionin . Text Image casein Layout Integration . , video Editing, DTP, (JS ) of .
An agent team collaborates to produce visual story design, text writing, AI image generation, HTML layout, and integrated editing.
Agent Team — 5 members communicate directly via SendMessage and cross-validate each other's work.
| Agent | File | Role | Type |
|---|---|---|---|
| story-architect | .claude/agents/story-architect.md | Narrative Structure, Scene Design | general-purpose |
| essay-writer | .claude/agents/essay-writer.md | Body text, Caption, Quote writing | general-purpose |
| image-prompter | .claude/agents/image-prompter.md | Gemini Image Prompt, | general-purpose |
| layout-builder | .claude/agents/layout-builder.md | HTML/CSS Layout production | general-purpose |
| editorial-reviewer | .claude/agents/editorial-reviewer.md | cross-validate, Verification | general-purpose |
_workspace/ and _workspace/images/ generate_workspace/00_input.mdin save_workspace/, copy to _workspace/ and skip the corresponding Phasecompositionand . between of relationship and :
| sequence | of | |||
|---|---|---|---|---|
| 1 | Story Design | architect | None | _workspace/01_story_blueprint.md |
| 2a | Text writing | writer | 1 | _workspace/02_essay_text.md |
| 2b | Image Prompt· | prompter | 1 | _workspace/03_image_prompts.md, images/ |
| 3 | HTML Layout | builder | 2a, 2b | _workspace/04_layout.html |
| 4 | Editing Review | reviewer | 2a, 2b, 3 | _workspace/05_review_report.md |
2a(Text)and 2b(Image) executed in parallel. 1(Story Design)in ofto whenin when .
Inter-team communication flow:
Reviewof based on :
_workspace/ within File verify01_story_blueprint.md02_essay_text.md03_image_prompts.md04_layout.html05_review_report.mdimages/of in Agent :
| Pattern | mode | Agent |
|---|---|---|
| "Visual Story ", " to" | Full Pipeline | 5 All |
| "Story Planning " | Planning mode | architect + reviewer |
| " in Image " ( Text) | Image mode | prompter + reviewer |
| "Textand Imageto HTML " ( ) | Layout mode | builder + reviewer |
| " Visual Story " | Review mode | reviewer only |
Using Existing Files: Text Image , copy the files to _workspace/in and of Agent .
| Strategy | ||
|---|---|---|
| File-Based | _workspace/ | Storing and sharing major deliverables |
| Message-Based | SendMessage | Real-time delivery of key information, revision requests |
| Task-Based | TaskCreate/TaskUpdate | Progress tracking, dependency management |
File naming convention: {}_{Agent}_{}.{}
| in type | Strategy |
|---|---|
| Image | vs Prompt 1 when → when + Prompt Text |
| StoryDesign 3 Suggestion after | |
| Agent failure | 1 retry -> if still fails, proceed without that deliverable, note omission in review report |
| RED found in review | Request revision from relevant agent -> rework -> re-verify (up to 2 times) |
| Image-Text Emotion conflict | Image Prompt Text |
Prompt: "'whenof ' to Visual in . 8Scene " Expected Result:
Prompt: " in in Image and HTMLto " + Text File Expected Result:
_workspace/02_essay_text.mdtoPrompt: "Visual Story , " Expected Result:
per Agentof before Extended Skill:
| subject Agent | Role | |
|---|---|---|
image-prompt-engineering | image-prompter | 5-Layer Prompt Structure, Style , Consistency technique |
narrative-structure-patterns | story-architect | 3/5/hero's journey Structure, Emotion Curve, Visual rhythm |