← ClaudeAtlas

ai-storyboard-generatorlisted

AI storyboard generator in Claude Code and Claude with Seedream 5 Lite through Wireflow: six 16:9 frames, one character and one look. From a script, an ad brief or a pitch idea it breaks the story into six shots (framing, angle, action, setting), writes one character note and one visual style, quotes the credits and waits for a yes, then renders all six frames in one call (panel 1 first, panels 2 to 6 drawn from it so the hero and the style hold) and saves them to ./wireflow-outputs with a shot list. Use when someone asks to storyboard a video ad, a commercial, a client pitch, a TikTok or Reels concept, a shot list with pictures, frames to plan a shoot, or panels to brief an AI video model. Without the Wireflow connector it still writes the shot list and frame prompts. For finished static ads use ai-ad-creative-generator; for one image use ai-image-generation.
wireflowINC/skills · ★ 1 · AI & Automation · score 80
Install: claude install-skill wireflowINC/skills
# AI Storyboard Generator An agency, a brand team or a solo creator has a script or a rough idea for a short video and needs to show it before anything is shot or generated. You (Claude) turn that idea into six shots, one hero and one look; the Wireflow app `skill-ai-storyboard-generator` paints panel 1 with Seedream 5 Lite and then paints panels 2 to 6 with panel 1 as the reference, so the main character and the style carry through while the camera moves. ## App contract | Item | Value | |---|---| | App slug | `skill-ai-storyboard-generator` | | `style` | One paragraph for all six frames: medium (pencil sketch, ink and marker, digital painting, 3D, photoreal), palette, line and light, grain | | `character` | The hero as they look in every frame: age, face, hair, skin, build, glasses, the full outfit with colours | | `panel_1` | The opening shot. It sets the look for the rest, so make it a clear wide or medium shot with the hero's face visible | | `panel_2` to `panel_6` | One shot each: camera distance, angle, action, setting, light. Any second person is described in full every time they appear | | Fixed inside the app | Frames carry no text: no captions, numbers, arrows, speech bubbles, logos or borders. Panels 2 to 6 copy the hero and the style of panel 1 but get a new composition | | Output | Six landscape 16:9 JPGs, `frame-1` to `frame-6`. In our test panel 1 came back at 3072x1728 and panels 2 to 6 at 3416x1920 | | Price | 60 credits per run, 10 per frame (Seedream 5