storyboard-prompting — Claude Code skill
storyboard-prompting is a Claude Code skill that generates detailed storyboard-frame prompts for Midjourney, DALL-E, and Stable Diffusion. It supports planning a script’s visual sequence.
MIT 1 installs ★ 1,931 updated 2026-09-16
npx skills add a5c-ai/babysitter --skill storyboard-prompting -a claude-codeWhat storyboard-prompting does
The skill runs across all major AI editors: Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It includes a six-component prompt architecture (subject, composition, lighting, mood, style, technical), templates for each shot type (extreme wide to extreme close-up), and ready-made libraries for different lighting scenarios and genres (noir, sci-fi, horror, romance).
Each image generation platform gets an optimized structure. Midjourney receives parameters like --ar 16:9 and --s 150; DALL-E gets natural English prose; Stable Diffusion gets positive and negative prompts with weights. The skill includes a storyboard template with fields for scene context, visual specs, and prompt variants for each platform.
Useful for directors and designers during preproduction—quickly generate frame variants for concept approval. Output quality depends on how specific the original scene description is: concrete character and environment details yield better prompts.
What it helps with
- write storyboard frame prompts for multiple image generators
- standardize composition, lighting, and mood descriptions across shots
- generate frame variations quickly with different cameras and angles
- match visual style references to a project's aesthetic
Example prompts for the agent
- Generate storyboard prompts for: detective in trench coat, close-up, noir style, rim lighting—ready for Midjourney and DALL-E
- Create prompt variants for a desert dawn wide shot, golden hour, across all three platforms with different aspect ratios
- Write Stable Diffusion prompts with positive and negative text for a dramatic close-up face with high-contrast lighting
How to install storyboard-prompting
1Skills CLI (Vercel)
npx skills add a5c-ai/babysitter --skill storyboard-prompting -a claude-code2Manually: put the files in place
~/.claude/skills/storyboard-prompting/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/storyboard-prompting/
1Skills CLI (Vercel)
npx skills add a5c-ai/babysitter --skill storyboard-prompting -a codex2Manually: put the files in place
.agents/skills/storyboard-prompting/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add a5c-ai/babysitter --skill storyboard-prompting -a cursor2Manually: put the files in place
.cursor/skills/storyboard-prompting/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install a5c-ai/babysitter library/specializations/domains/social-sciences-humanities/arts-culture/film-tv-production/skills/storyboard-prompting2Manually: put the files in place
.github/skills/storyboard-prompting/SKILL.md1Skills CLI (Vercel)
npx skills add a5c-ai/babysitter --skill storyboard-prompting -a gemini-cli2Platform CLI
gemini skills install https://github.com/a5c-ai/babysitter --path library/specializations/domains/social-sciences-humanities/arts-culture/film-tv-production/skills/storyboard-promptingManually: put the files in place
.devin/skills/storyboard-prompting/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add a5c-ai/babysitter --skill storyboard-prompting -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about storyboard-prompting
How do I install storyboard-prompting in Claude Code?
Run npx skills add a5c-ai/babysitter --skill storyboard-prompting -a claude-code. The skill file will be at ~/.claude/skills/storyboard-prompting/SKILL.md. For other editors, swap claude-code for codex, cursor, gemini-cli, or opencode.
What does storyboard-prompting do?
Structures image generation prompts for storyboard frames by organizing composition, lighting, atmosphere, and style. Provides templates for each shot type (wide to extreme close-up) and adapts the text for Midjourney, DALL-E, and Stable Diffusion formats.
Which platforms and image generators does it support?
The skill installs on Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It includes optimization instructions for three image generators: Midjourney, DALL-E 3, and Stable Diffusion.
Source text
SKILL.md · MIT
--- name: storyboard-prompting id: SK-FTV-005 version: 1.0.0 description: Generate detailed image prompts for storyboard frames optimized for Midjourney, DALL-E, and Stable Diffusion specialization: film-tv-production graph: domains: [domain:arts-culture] skillAreas: [skill-area:visual-design, skill-area:prompt-engineering, skill-area:image-processing] roles: [role:creative-director, role:design-lead] --- # Storyboard Prompting Skill ## Purpose Create detailed, production-ready image generation prompts for storyboard frames. These prompts should produce consistent, cinematic images that communicate composition, lighting, mood, and action for pre-visualization. ## Prompt Architecture ### Core Structure ``` [SUBJECT] + [COMPOSITION] + [LIGHTING] + [MOOD/ATMOSPHERE] + [STYLE] + [TECHNICAL] ``` ### Component Breakdown | Component | Description | Examples | |-----------|-------------|----------| | Subject | Who/what is in frame | "detective in trench coat" | | Composition | Framing and arrangement | "medium close-up, rule of thirds" | | Lighting | Light sources and quality | "rim lighting, high contrast" | | Mood | Emotional atmosphere | "tense, ominous" | | Style | Visual reference | "noir, cinematic" | | Technical | Camera/image specs | "35mm, shallow DOF" | ## Platform-Specific Optimization ### Midjourney ``` Midjourney v6 parameters: --ar [aspect ratio] (16:9, 2.39:1, 4:3) --s [stylize] (0-1000, default 100) --c [chaos] (0-100, for variation) --q [quality] (0.25, 0.5, 1, 2) --style raw (less Midjourney aesthetic) Structure: [Subject and action], [composition], [lighting], [mood], [style reference], cinematic still, film photography --ar 16:9 --s 150 ``` ### DALL-E ``` DALL-E 3 optimization: - Natural language descriptions work well - Be specific about what you want - Include negative instructions when needed - Reference artistic styles by description, not artist name Structure: A cinematic film still of [subject], [composition description]. The scene has [lighting description] creating a [mood] atmosphere. Shot on [camera/lens], [style description]. ``` ### Stable Diffusion ``` Positive prompt: (cinematic:1.3), (film still:1.2), [subject], [composition], [lighting], [mood], [style], detailed, high quality, 8k Negative prompt: cartoon, anime, illustration, drawing, painting, blurry, low quality, watermark, text, deformed, ugly, bad anatomy Settings: - CFG Scale: 7-12 - Steps: 30-50 - Sampler: DPM++ 2M Karras or Euler a ``` ## Shot Type Prompts ### Extreme Wide Shot (EWS) ``` vast landscape with tiny silhouetted figure, establishing shot, epic scale, environmental storytelling, cinematic composition, golden hour lighting, anamorphic lens flare --ar 2.39:1 ``` ### Wide Shot (WS) ``` full body shot of [character] standing in [environment], environmental context visible, subject in lower third, motivated practical lighting, cinematic atmosphere --ar 16:9 ``` ### Medium Shot (MS) ``` medium shot of [character] from waist up, [action/pose], [background environment], shallow depth of field, three-point lighting setup, film grain --ar 16:9 ``` ### Close-Up (CU) ``` close-up portrait of [character], [expression], face fills frame, soft key light, dramatic shadows, intimate composition, emotional intensity, 85mm lens --ar 16:9 ``` ### Extreme Close-Up (ECU) ``` extreme close-up of [detail/feature], macro detail, selective focus, dramatic lighting, texture emphasis, cinematic tension, tight framing --ar 16:9 ``` ## Lighting Prompts ### Natural Light ``` golden hour sunlight, warm tones, long shadows, natural window light, overcast diffusion, magic hour, practical sun ``` ### Studio/Artificial ``` three-point lighting, rim light, motivated light, practical lamps, neon glow, fluorescent overhead, spotlight, volumetric light ``` ### Mood Lighting ``` chiaroscuro, high contrast, low key, high key, silhouette, backlit, lens flare, god rays, atmospheric haze, dusty light beams ``` ## Composition Prompts ### Framing ``` rule of thirds, centered composition, symmetrical frame, off-center subject, negative space, frame within frame, leading lines, diagonal composition, Dutch angle ``` ### Depth ``` foreground elements, layered composition, deep focus, shallow depth of field, background blur bokeh, environmental depth, atmospheric perspective ``` ## Storyboard Frame Template ```markdown ## Frame [ID]: [Beat Description] ### Scene Context - **Scene:** [Number and title] - **Shot:** [Size and angle] - **Action:** [What's happening] ### Visual Specifications - **Composition:** [Framing details] - **Lighting:** [Light sources and mood] - **Characters:** [Who's in frame, expressions] - **Environment:** [Setting details] ### Image Prompts **Midjourney:** ``` [Full prompt with parameters] ``` **DALL-E:** ``` [Natural language prompt] ``` **Stable Diffusion:** ``` Positive: [prompt] Negative: [negative prompt] ``` ### Frame Notes - **Dialogue:** "[Any dialogue]" - **Duration:** [Estimated seconds] - **Movement:** [Camera or subject movement] ``` ## Style Reference Library ### Film Noir ``` high contrast black and white, dramatic shadows, venetian blind shadows, rain-slicked streets, cigarette smoke, fedoras, low-key lighting ``` ### Sci-Fi ``` neon lights, holographic displays, lens flares, futuristic architecture, chrome surfaces, volumetric lighting, blue and orange color grade ``` ### Horror ``` underexposed, deep shadows, obscured faces, practical effects, desaturated colors, fog, dutch angles, motivated darkness ``` ### Romance ``` soft focus, warm lighting, golden hour, lens flare, shallow depth of field, intimate framing, natural expressions ``` ## Quality Checklist - [ ] Shot size and angle specified - [ ] Lighting direction and quality described - [ ] Mood/atmosphere conveyed - [ ] Character positioning clear - [ ] Environment context included - [ ] Style reference appropriate - [ ] Technical specs match project - [ ] Aspect ratio specified - [ ] Platform optimized
© a5c-ai · MIT · a5c-ai/babysitter