$npx -y skills add Hainrixz/editor-pro-max --skill explainer-video-guideExplainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make
| 1 | # Explainer Video Guide |
| 2 | |
| 3 | Create explainer videos from script to final cut via [inference.sh](https://inference.sh) CLI. |
| 4 | |
| 5 | ## Quick Start |
| 6 | |
| 7 | > Requires inference.sh CLI (`infsh`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md) |
| 8 | |
| 9 | ```bash |
| 10 | infsh login |
| 11 | |
| 12 | # Generate a scene for an explainer |
| 13 | infsh app run google/veo-3-1-fast --input '{ |
| 14 | "prompt": "Clean motion graphics style animation, abstract data flowing between connected nodes, blue and white color scheme, professional corporate aesthetic, smooth transitions" |
| 15 | }' |
| 16 | ``` |
| 17 | |
| 18 | |
| 19 | ## Script Formulas |
| 20 | |
| 21 | ### Problem-Agitate-Solve (PAS) — 60 seconds |
| 22 | |
| 23 | | Section | Duration | Content | Word Count | |
| 24 | |---------|----------|---------|------------| |
| 25 | | **Problem** | 10s | State the pain point the viewer has | ~25 words | |
| 26 | | **Agitate** | 10s | Show why it's worse than they think | ~25 words | |
| 27 | | **Solution** | 15s | Introduce your product/idea | ~35 words | |
| 28 | | **How It Works** | 20s | Show 3 key steps or features | ~50 words | |
| 29 | | **CTA** | 5s | One clear next action | ~12 words | |
| 30 | |
| 31 | ### Before-After-Bridge (BAB) — 90 seconds |
| 32 | |
| 33 | | Section | Duration | Content | |
| 34 | |---------|----------|---------| |
| 35 | | **Before** | 15s | Show the current frustrating state | |
| 36 | | **After** | 15s | Show the ideal outcome | |
| 37 | | **Bridge** | 40s | Explain how your product gets them there | |
| 38 | | **Social Proof** | 10s | Quick stat or testimonial | |
| 39 | | **CTA** | 10s | Clear next step | |
| 40 | |
| 41 | ### Feature Spotlight — 30 seconds (social) |
| 42 | |
| 43 | | Section | Duration | Content | |
| 44 | |---------|----------|---------| |
| 45 | | **Hook** | 3s | Surprising fact or question | |
| 46 | | **Feature** | 15s | Show one feature solving one problem | |
| 47 | | **Result** | 7s | The outcome/benefit | |
| 48 | | **CTA** | 5s | Try it / Learn more | |
| 49 | |
| 50 | ## Pacing Rules |
| 51 | |
| 52 | | Content Type | Words Per Minute | Notes | |
| 53 | |-------------|-----------------|-------| |
| 54 | | Standard narration | 150 wpm | Conversational pace | |
| 55 | | Complex/technical | 120 wpm | Allow processing time | |
| 56 | | Energetic/social | 170 wpm | Faster for short-form | |
| 57 | | Children's content | 100 wpm | Clear and slow | |
| 58 | |
| 59 | **Key rule:** 1 scene per key message. Don't pack multiple ideas into one visual. |
| 60 | |
| 61 | ### Scene Duration Guidelines |
| 62 | |
| 63 | - Establishing shot: 3-5 seconds |
| 64 | - Feature demonstration: 5-8 seconds |
| 65 | - Text/stat on screen: 3-4 seconds (must be readable) |
| 66 | - Transition: 0.5-1 second |
| 67 | - CTA screen: 3-5 seconds |
| 68 | |
| 69 | ## Visual Production |
| 70 | |
| 71 | ### Scene Types |
| 72 | |
| 73 | ```bash |
| 74 | # Product in context |
| 75 | infsh app run google/veo-3-1-fast --input '{ |
| 76 | "prompt": "Clean product demonstration video, hands typing on a laptop showing a dashboard interface, bright modern office, soft natural lighting, professional" |
| 77 | }' |
| 78 | |
| 79 | # Abstract concept visualization |
| 80 | infsh app run bytedance/seedance-1-5-pro --input '{ |
| 81 | "prompt": "Abstract motion graphics, colorful data streams connecting floating geometric shapes, smooth fluid animation, dark background with glowing elements, tech aesthetic" |
| 82 | }' |
| 83 | |
| 84 | # Lifestyle/outcome shot |
| 85 | infsh app run google/veo-3-1-fast --input '{ |
| 86 | "prompt": "Happy person relaxing on couch with laptop, smiling at screen, bright airy living room, warm afternoon light, satisfied customer feeling, lifestyle commercial style" |
| 87 | }' |
| 88 | |
| 89 | # Before/after comparison |
| 90 | infsh app run falai/flux-dev-lora --input '{ |
| 91 | "prompt": "Split screen comparison, left side cluttered messy desk with papers and stress, right side clean organized minimalist workspace, dramatic difference, clean design" |
| 92 | }' |
| 93 | ``` |
| 94 | |
| 95 | ### Image-to-Video for Scenes |
| 96 | |
| 97 | ```bash |
| 98 | # Generate a still frame first |
| 99 | infsh app run falai/flux-dev-lora --input '{ |
| 100 | "prompt": "Professional workspace with glowing holographic interface, futuristic but clean, blue accent lighting" |
| 101 | }' |
| 102 | |
| 103 | # Animate it |
| 104 | infsh app run falai/wan-2-5-i2v --input '{ |
| 105 | "prompt": "Gentle camera push in, holographic elements subtly floating and rotating, soft ambient light shifts", |
| 106 | "image": "path/to/workspace-still.png" |
| 107 | }' |
| 108 | ``` |
| 109 | |
| 110 | ## Voiceover Production |
| 111 | |
| 112 | ### Script Writing Tips |
| 113 | |
| 114 | - Short sentences. Max 15 words per sentence. |
| 115 | - Active voice. "You can track your data" not "Your data can be tracked." |
| 116 | - Conversational tone. Read it aloud — if it sounds stiff, rewrite. |
| 117 | - One idea per sentence. One sentence per visual beat. |
| 118 | |
| 119 | ### Generating Voiceover |
| 120 | |
| 121 | ```bash |
| 122 | # Professional narration with Dia TTS |
| 123 | infsh app run falai/dia-tts --input '{ |
| 124 | "prompt": "[S1] Tired of spending hours on reports that nobody reads? There is a better way. Meet DataFlow. It turns your raw data into visual stories... in seconds. Just connect your sourc |