ai-video/skills/ai-video-storyboard/SKILL.md
Use when planning a multi-shot AI video (TikTok Reel, Instagram Ad, YouTube Shorts, product explainer) where the target duration exceeds what a single AI generation can produce (>15s), and you need a coordinated shot list with visually consistent prompts for each segment
npx skillsauth add bernatmv/ai-rules ai-video-storyboardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
AI video generators produce 5–15 second clips. Real-world videos are longer: 30s TikToks, 60s ads, 90s explainers. This skill bridges that gap by producing a complete shot-list storyboard — a coordinated sequence of per-shot prompts with shared visual language, so the assembled final video looks like one intentional piece of work rather than six disconnected clips.
Core insight: Visual consistency across shots matters more than any single shot being perfect. A mediocre but consistent set of shots edits together; six gorgeous but mismatched shots do not.
Do NOT use for:
Ask the user these questions in a single message. Accept short answers:
If user already provided some of these, skip those questions and confirm the rest.
Based on duration and platform, divide the timeline into shots of ~5 seconds each (the sweet spot for AI video generators).
Standard cadences:
| Platform | Duration | Shots | Pacing | |---|---|---|---| | TikTok Hook | 15s | 3 | Fast cuts, single idea | | TikTok Reel | 30s | 6 | Hook → Build → Payoff → CTA | | Instagram Ad | 15s | 3 | Hook → Product → CTA | | Instagram Ad | 30s | 6 | Hook → Problem → Product → Benefit → Social proof → CTA | | YouTube Short | 60s | 12 | Hook → 3-act structure → CTA | | Product Explainer | 90s | 18 | Problem → Solution → How it works → Results → CTA | | Brand Story | 60s | 10-12 | Atmosphere-driven, longer shot holds |
Before writing any shot, lock in the shared visual language. This is what makes shots edit together:
Write these as a Visual Theme block at the top of the output. Every shot's prompt must respect this block.
For each shot, produce this structure:
## Shot N (START-ENDs) — [Purpose label: Hook / Setting / Action / Detail / Reveal / CTA]
**Composition:** [shot type + angle, e.g., "Extreme close-up, overhead"]
**Camera move:** [locked / slow dolly in / tracking / crane up / etc.]
**Lighting:** [from the Visual Theme, applied to this scene]
**Subject:** [what is in frame]
**Action:** [what is happening]
**Prompt to copy:**
> [Complete, cinematic-quality prompt, 40-80 words, including: subject + action + environment + camera + lighting + style + technical spec (duration, aspect ratio, resolution). Always ends with "cinematic 1080p, synchronized audio"]
**Audio direction:** [what the synchronized audio should sound like — ambient sounds, music beat position, voice-over line]
Critical rules for shot prompts:
references/shot-types.md for the full vocabulary.The sequence of shots must have a story arc, not a random list. Use one of these patterns:
Pattern A — Hook / Build / Payoff / CTA (TikTok default)
Pattern B — Problem / Solution / Proof / CTA (Ad default)
Pattern C — Atmosphere → Climax (Brand story)
Close with actionable post-production notes:
## Post-Production Checklist
- [ ] Generate all N shots with your preferred AI video tool
- [ ] Stitch in [CapCut / Descript / DaVinci Resolve / Premiere]
- [ ] Apply [specific LUT or color grade] for consistency
- [ ] Add [transition type and duration] between shots
- [ ] Layer BGM: [genre / BPM / mood]
- [ ] Add text overlays for [hook / CTA / captions]
- [ ] Export [platform spec: 9:16 1080x1920 30fps for TikTok, etc.]
Close with a "Why this works" block explaining the creative decisions. This educates the user and differentiates your output from generic prompt lists. Reference:
The final output is a single Markdown document containing:
See examples/ for four complete sample outputs:
tiktok-reel-30s-coffee.md — Coffee shop opening TikTokreferences/shot-types.md — Cinematography vocabulary (ECU, CU, MS, WS, OTS, POV, angles)references/camera-moves.md — Camera movement vocabulary (dolly, crane, pan, tilt, tracking)references/lighting.md — Lighting terminology (golden hour, rim, motivated, practical)references/genre-templates.md — Pre-built templates for common genres (food, fashion, tech, travel, SaaS)MIT — use freely, commercial or personal.
development
Keyword research and validation with real search-demand data — never ship keywords from intuition alone. Probes Google Autocomplete per language (free, no account) to prove demand and discover the exact phrasing people type, checks SERPs for winnability, and uses Keyword Planner/Ahrefs/Semrush exports when the user has access. Activates when: choosing or reviewing SEO keywords, meta keywords, page titles, article topics or slugs, landing page copy targeting search, App Store/ASO keyword fields, multilingual keyword sets, 'what should we rank for', 'keyword analysis', or auditing why a page doesn't rank. Also invoke it as a validation pass whenever another skill or task produces a keyword list.
development
Automate YooAsset hot-update and asset bundles — build bundles, run Editor simulate builds, manage Collector groups, analyze BuildReport, and validate runtime. Use when building or simulating YooAsset bundles, configuring collectors, or validating hot-update assets, even if the user just says "热更" or "打AB包". 自动化 YooAsset 热更新与资源包(构建 bundle、编辑器模拟构建、管理 Collector 分组、分析 BuildReport、运行时校验);当用户要构建或模拟 YooAsset 资源包、配置 collector、或校验热更资源时使用。
development
Source-anchored design rules for YooAsset v2.3.18 — initialization, default-package shortcuts, play modes, asset handles, loading, updates, filesystem, build, and pitfalls. Use when writing or reviewing YooAsset code, initializing packages, loading assets via handles, setting up hot-update/download, or choosing a play mode, even if the user just says "热更" or "资源包". 为 YooAsset v2.3.18 提供源码锚定的设计规则(初始化、默认包快捷方式、运行模式、资源句柄、加载、更新、文件系统、构建、陷阱);当用户要编写或审查 YooAsset 代码、初始化 package、用句柄加载资源、配置热更/下载、或选择运行模式时使用。
data-ai
Last-resort guidance for safely hand-editing Unity serialized YAML (.unity/.prefab/.asset/.meta/ProjectSettings) — reference/fileID repair, GUID safety, and merge-conflict fixes. Use when REST cannot reach the change and YAML must be hand-edited — fixing m_Script GUIDs, broken fileID references, .meta files, or merge conflicts, even if the user just says "场景文件打不开" or "引用丢了". 安全手编 Unity 序列化 YAML(.unity/.prefab/.asset/.meta/ProjectSettings)的最后手段(引用/fileID 修复、GUID 安全、合并冲突修复);当 REST 无法触达、必须手编 YAML 时使用——修复 m_Script GUID、断裂 fileID 引用、.meta 文件或合并冲突。