Scarcest thing isn’t money (tease options → reveal)
Template (assume duration 10 unless scaled): 0–3s THE SCARCEST THING ISN’T MONEY; 3–8s two or three quick option teases on screen—e.g. 3–5 ATTENTION?, 5–6.5 TRUST?, 6.5–8 TIME? (user can swap candidates); 8–10s reveal line naming the one answer they want (e.g. IT’S ATTENTION—must be ≤6 words). English subtitles with exact windows. Default duration is 10 when unspecified.
Dependencies: WERYAI_API_KEY + Node.js 18+. scripts/video_gen.js + WERYAI_VIDEO_API.md. No other Cursor skills required.
Prerequisites
- -
WERYAI_API_KEY must be set; Node 18+. Prefer public https image URLs; if the assembled scripts/video_gen.js supports local file paths, review/verify the script and explicitly consent before local read-and-upload to WeryAI. - Non-empty
model.
Security, secrets, and API hosts
- -
WERYAI_API_KEY: Secret; requires.env / primaryEnv. - API hosts fixed in
video_gen.js. - Local image handling disclosure: Prefer public
https image URLs. If the assembled scripts/video_gen.js supports local file paths, it may read a local image and upload it to WeryAI to obtain a public URL; require review / verification and explicit consent before using that path. - Higher assurance: Prefer a short-lived or isolated environment; review
scripts/video_gen.js before production use. Verify whether the runtime can read local image files and upload them to WeryAI, and obtain explicit consent before using that path.
Prompt expansion (mandatory)
- - Duration: Default 10; 5 or 15 when allowed and requested.
- Timeline scaling: Rescale 0–3 / 3–8 / 8–10 and internal tease splits proportionally; keep thesis → teases → reveal order.
Visuals: Coins dissolving to sand, hourglass, eye macro, handshake silhouette, clock abstraction—luxury grade, warm gold accents optional; morphs every ~1.5s.
Typography: Bold sans, outline, lower third; question marks on tease lines.
Audio: Soft tick + reveal sting if generate_audio true.
Negatives (Kling): illegible text, watermark.
User must confirm the final reveal word before submit if you inferred it.
Confirmation: Full expanded prompt.
Niche checklist
- - Teases should be distinct concepts, not synonyms.
- Reveal should feel earned—visual points at the answer as it appears.
Workflow
- 1. Text / image / multi-image (SEEDANCE20, ≤3).
- Collect candidate list + final answer (or you propose both for approval).
- Expand → validate → confirm →
wait. [Video](url).
CLI reference
~~~sh
node scripts/videogen.js wait --json '{"model":"KLINGV30PRO","prompt":"…","duration":10,"aspectratio":"9:16","generateaudio":true,"negative_prompt":"illegible text, watermark, garbled captions"}'
node scripts/videogen.js wait --json '{"model":"SEEDANCE20","prompt":"…","duration":10,"aspectratio":"9:16","resolution":"720p","generate_audio":true}'
~~~
Full reference: WERYAI_VIDEO_API.md.
Definition of done
Video or error; prompt includes scaled second ranges for thesis, tease block (with sub-splits), and reveal.
Boundaries (out of scope)
- - Not a finance or therapy authority—hook content only.
resources/WERYAI_VIDEO_API.md for CLI; no negative_prompt on Seedance.- Multi-image only SEEDANCE20, max 3.
Example prompts
- - INLINECODE24
- INLINECODE25
- INLINECODE26
- INLINECODE27
Model and API constraints (frozen for this skill)
Text-to-video
| modelkey | durations | aspectratios | resolutions | audio | negativeprompt | prompt limit |
|---|
| KLINGV30PRO | 5, 10, 15 | 9:16, 1:1, 16:9 | (omit) | yes | yes | 2000 |
| KLINGV30_STA |
5, 10, 15 | 9:16, 1:1, 16:9 |
(omit) | yes | yes | 2000 |
| SEEDANCE
20 | 5, 10, 15 | 9:16, 1:1, 16:9 | 480p, 720p | yes | no | 2000 |
Image-to-video
| modelkey | durations | aspectratios | resolutions | audio | negativeprompt | image slots |
|---|
| KLINGV30PRO | 5, 10, 15 | 9:16, 16:9, 1:1 | (omit) | yes | yes | single INLINECODE28 |
| KLINGV30_STA |
5, 10, 15 | 9:16, 16:9, 1:1 |
(omit) | yes | yes | single
image |
| SEEDANCE
20 | 5, 10, 15 | 9:16, 1:1, 16:9 | 480p, 720p | yes | no | up to
3 images |
Recommended models
| Tier | modelkey | Default duration |
|---|
| ⭐ Best | KLINGV30PRO | 10 |
| 👍 Good |
KLING
V30_STA | 10 |
| ⚡ Fast | SEEDANCE
20 | 10 (
resolution:
720p) |
Default parameters
| Field | Value |
|---|
| aspect_ratio | 9:16 |
| duration |
10 |
| generate_audio | true |
| resolution | 720p (Seedance) |
| negative_prompt | Kling:
illegible text, garbled captions, watermark |
Text-to-video (primary)
Agree teases + reveal → timed captions → wait.
Image-to-video (optional)
Object still → symbol morph under same windows.
Tips
- - Series: end with NEXT EP? only if user wants; default is clean reveal.
- Translate Chinese brief to English on-screen lines unless user opts out.
Packaged as scarcest-not-money-video-gen.
最稀缺的不是金钱(选项预告→揭示)
模板(假设duration为10,除非缩放): 0–3秒 最稀缺的不是金钱;3–8秒 屏幕上显示两到三个快速选项预告——例如3–5秒 注意力?,5–6.5秒 信任?,6.5–8秒 时间?(用户可替换候选词);8–10秒 揭示行,命名他们想要的一个答案(例如是注意力——必须 ≤6个词)。英文字幕需精确时间窗口。未指定时默认duration为10。
依赖项: WERYAIAPIKEY + Node.js 18+。scripts/videogen.js + WERYAIVIDEOAPI.md。无需其他Cursor技能。
前置条件
- - WERYAIAPIKEY 必须设置;Node 18+。优先使用公开https图片URL;如果组合的scripts/video_gen.js支持本地文件路径,请先审查/验证脚本,并在本地读取并上传至WeryAI前明确同意。
- 非空model。
安全、密钥和API主机
- - WERYAIAPIKEY:密钥;requires.env / primaryEnv。
- API主机固定于videogen.js中。
- 本地图片处理披露:优先使用公开https图片URL。如果组合的scripts/videogen.js支持本地文件路径,它可能读取本地图片并上传至WeryAI以获取公开URL;使用该路径前需审查/验证并明确同意。
- 更高保障:优先使用短期或隔离环境;生产使用前审查scripts/video_gen.js。验证运行时是否能读取本地图片文件并上传至WeryAI,并在使用该路径前获得明确同意。
提示词扩展(强制)
- - 时长: 默认10;允许且被要求时可设为5或15。
- 时间线缩放: 按比例重新调整0–3 / 3–8 / 8–10及内部预告分割;保持论点→预告→揭示顺序。
视觉: 硬币溶解成沙粒、沙漏、眼睛特写、握手剪影、时钟抽象——奢华级别,可选暖金色点缀;每约1.5秒 变形。
排版: 粗体无衬线、轮廓、下三分之一;预告行带问号。
音频: 轻柔滴答声 + 揭示音效(若generate_audio为true)。
负面提示(Kling): 文字模糊、水印。
用户必须在提交前确认最终的揭示词(如果你推断出的话)。
确认: 完整的扩展prompt。
细分清单
- - 预告应为不同概念,而非同义词。
- 揭示应让人感觉实至名归——视觉上指向出现时的答案。
工作流程
- 1. 文本/图片/多图片(SEEDANCE20,≤3张)。
- 收集候选列表 + 最终答案(或你提出两者供批准)。
- 扩展→验证→确认→wait。
- 视频。
CLI参考
~~~sh
node scripts/videogen.js wait --json {model:KLINGV30PRO,prompt:…,duration:10,aspectratio:9:16,generateaudio:true,negative_prompt:illegible text, watermark, garbled captions}
node scripts/videogen.js wait --json {model:SEEDANCE20,prompt:…,duration:10,aspectratio:9:16,resolution:720p,generate_audio:true}
~~~
完整参考: WERYAIVIDEO_API.md。
完成标准
视频 或错误;prompt包含论点、预告块(含子分割)和揭示的缩放秒数范围。
边界(范围外)
- - 非金融或治疗权威——仅钩子内容。
- CLI参考resources/WERYAIVIDEOAPI.md;Seedance无negativeprompt。
- 多图片仅SEEDANCE2_0,最多3张。
示例提示词
- - 预告注意力信任时间—揭示注意力
- 预告睡眠纪律专注—揭示纪律
- 金币静物URL → 变形序列,相同字幕节奏
- 预告睡眠、专注、精力—揭示纪律为最稀缺资源
模型与API约束(本技能固定)
文本转视频
| modelkey | 时长 | 宽高比 | 分辨率 | 音频 | 负面提示 | 提示词限制 |
|---|
| KLINGV30PRO | 5, 10, 15 | 9:16, 1:1, 16:9 | (省略) | 是 | 是 | 2000 |
| KLINGV30_STA |
5, 10, 15 | 9:16, 1:1, 16:9 |
(省略) | 是 | 是 | 2000 |
| SEEDANCE
20 | 5, 10, 15 | 9:16, 1:1, 16:9 | 480p, 720p | 是 | 否 | 2000 |
图片转视频
| modelkey | 时长 | 宽高比 | 分辨率 | 音频 | 负面提示 | 图片槽位 |
|---|
| KLINGV30PRO | 5, 10, 15 | 9:16, 16:9, 1:1 | (省略) | 是 | 是 | 单张image |
| KLINGV30_STA |
5, 10, 15 | 9:16, 16:9, 1:1 |
(省略) | 是 | 是 | 单张image |
| SEEDANCE
20 | 5, 10, 15 | 9:16, 1:1, 16:9 | 480p, 720p | 是 | 否 | 最多
3张images |
推荐模型
| 层级 | modelkey | 默认时长 |
|---|
| ⭐ 最佳 | KLINGV30PRO | 10 |
| 👍 良好 |
KLING
V30_STA | 10 |
| ⚡ 快速 | SEEDANCE
20 | 10(resolution:
720p) |
默认参数
| 字段 | 值 |
|---|
| aspect_ratio | 9:16 |
| duration |
10 |
| generate_audio | true |
| resolution | 720p(Seedance) |
| negative_prompt | Kling:illegible text, garbled captions, watermark |
文本转视频(主要)
同意预告+揭示 → 定时字幕 → wait。
图片转视频(可选)
物体静物 → 相同时间窗口下的符号变形。
提示
- - 系列: 仅当用户要求时以下集?结尾;默认为干净揭示。
- 翻译中文简称为英文屏幕文字,除非用户选择退出。
打包为scarcest-not-money-video-gen。