Gardening & plant growth video generation
A seed in soil, roots reaching down, cotyledons breaking the surface, stems stretching day by day, buds swelling, a flower opening in sun—ten seconds can hold a whole life cycle; that’s the magic of timelapse. Bunny with strawberries, bear with succulents, cat with balcony tomatoes: growth is the plot.
Dependencies: scripts/video_gen.js in this directory + WERYAI_API_KEY + Node.js 18+. No dependency on other Cursor skills.
Prerequisites
- -
WERYAI_API_KEY must be set in the environment before running video_gen.js. - Node.js 18+ is required. Image inputs must be public
https URLs (no local file paths). - Each successful
wait run consumes WeryAI credits; re-running creates new paid tasks.
Security, secrets, and API hosts
- -
WERYAI_API_KEY: Treat as a secret. Only configure it if you trust this skill's source; it is listed in OpenClaw metadata as requires.env / primaryEnv so installers know it is mandatory at runtime (never commit it inside the skill package). - Optional URL overrides (
WERYAI_BASE_URL, WERYAI_MODELS_BASE_URL): video_gen.js defaults to https://api.weryai.com and https://api-growth-agent.weryai.com. Overrides are intended for testing or approved alternate endpoints. If these variables are set in your environment, confirm they point to hosts you trust—otherwise prompts, images, and your bearer token could be sent elsewhere. - Higher assurance: Run generation in a short-lived or isolated environment (separate account or container), and review
scripts/video_gen.js (HTTPS submit + poll loop) before production use.
Prompt expansion (mandatory)
INLINECODE15 does not expand prompts. Before every wait --json, turn the user's short or vague brief into a full English production prompt.
When: The user gives only keywords, one line, or loose intent—or asks for richer video language. Exception: They paste a finished long prompt within the model's prompt_length_limit and ask you not to rewrite; still show the full text in the confirmation table.
Always add (video language): shot scale and angle; camera move or lock-off; light quality and motivation; subject action paced to duration; one clear payoff for this niche; state 9:16 vertical when this skill defaults to vertical.
Length: Obey prompt_length_limit for the chosen model_key when this doc lists it; trim filler adjectives before removing core action, lens, or light clauses.
Confirmation: The pre-submit table must include the full expanded prompt (never a one-line summary). Wait for confirm or edits.
Niche checklist
- - Time language: time-lapse, visible days/weeks compression, light angle or shadow drift for elapsed time.
- Beats: seed/sprout/leaf/flower/fruit as applicable; hands or paws optional; terracotta, soil, glass root views.
- Payoff: harvest, full bloom, or filled planter clearer than start.
### Example prompts at the top of this file are short triggers only—always expand from the user's actual request.
Workflow
- 1. Confirm the user request matches this skill's scenario (text-to-video and/or image-to-video as documented).
- Collect the user's brief, optional image URL(s), tier (best / good / fast) or an explicit
model key. - Expand prompt (mandatory): Unless the user supplied a finished long prompt and explicitly asked not to rewrite it, expand the brief into a full English production
prompt using ## Prompt expansion (mandatory) below. Do not call the API with only the user's minimal words. - Check the expanded
prompt against the selected model's prompt_length_limit in the frozen tables in this document (when present); shorten if needed. - Verify
duration, aspect_ratio, resolution, generate_audio, negative_prompt, and other fields against the frozen tables and API notes in this SKILL.md. - Show the pre-submit parameter table including the full expanded
prompt; wait for confirm or edits. - After confirmation, run
node {baseDir}/scripts/video_gen.js wait --json '...' with the expanded prompt. - Parse stdout JSON and return video URLs; on failure, surface
errorCode / errorMessage and suggest parameter fixes.
CLI reference
CODEBLOCK0
Definition of done
Done when the user receives at least one playable video URL from the API response, or a clear failure explanation with next steps. All parameters used must fall within the selected model's allowed sets in this document. The submitted prompt must be the expanded production prompt unless the user explicitly supplied a finished long prompt and asked not to rewrite it.
Boundaries (out of scope)
- - Does not review platform compliance, copyright, or portrait rights; does not guarantee commercial usability of outputs.
- Does not provide non-WeryAI offline rendering, traditional edit timelines, or API field combinations not documented here.
- Does not hard-code absolute paths in the skill doc;
{baseDir} means the skill package root (same level as SKILL.md).
Example prompts
- - INLINECODE41
- INLINECODE42
- INLINECODE43
- INLINECODE44
Default parameters
| Field | Value |
|---|
| Model | KLINGV30_PRO |
| Aspect ratio |
9:16 (fixed) |
| Duration | 10 seconds (
duration: 10—full growth arc) |
| Audio | Off |
| Visual style | Front medium or top-down; natural light (window sun); timelapse feel; light direction shifts over “days”; simple background (soil, terracotta, wood) |
API validity (default KLING_V3_0_PRO): Text-to-video duration only 5 / 10 / 15; aspect_ratio only 9:16, 1:1, 16:9. Image-to-video aspect_ratio only 9:16, 16:9, 1:1. No resolution field—do not send it. For fast tier with VEO: text-to-video VEO_3_1_FAST, image-to-video CHATBOT_VEO_3_1_FAST, with duration fixed at 8, aspect_ratio only 9:16 or 16:9. When switching model_key, follow the allowed sets in this section’s model/API constraints and the API validity note above; do not send resolution to models that do not support it.
Seed to sprout to flower and fruit
Purpose: Time-compressed growth from planting through a satisfying harvest or bloom. Hero beats: breaking soil and the final flower or fruit moment.
Describe the character and plant—no extra form:
e.g. “bunny grows strawberries” or “cat grows balcony tomatoes”—the skill fills in the full growth arc and visual detail.
Show parameters before generate:
Generating with the parameters below—reply confirm or say what to change:
- - model: KLINGV30PRO
- aspectratio: 9:16
- duration: 10
- generate_audio: false
- Loop seam: No (reply loop to enable; appends
seamless loop to the prompt)
Expanded prompt: Compose at generation time per ## Prompt expansion (mandatory) from the user's actual brief—do not reuse fixed sample paragraphs.
Parameter configuration:
| Field | Value |
|---|
| model | KLINGV30PRO |
| aspectratio |
9:16 |
| duration | 10 |
| generate_audio | false |
Expected outcome: Clear time advance; sprouting and bloom/fruit as peaks; light cycles or angle shifts sell the passage of time; ending feels like a payoff.
Microscopic growth close-ups
Single-plant life at extreme detail: roots in a clear vessel, bud-to-full-bloom timelapse, mushroom from spore stage to pickable—no long story, one magnified process.
Name the plant and stage; then generate:
You must show all parameters in a table and wait for explicit user confirmation before submitting:
> 📋 Ready to generate—please confirm:
>
> | Parameter | This run | Notes |
> |-----------|----------|-------|
> | model | KLING_V3_0_PRO | Best default; say “cheap / draft / fast” → KLING_V3_0_STA; say “balanced” → WAN_2_6; or name a model |
> | aspect_ratio | 9:16 | Default KLING: 9:16, 1:1, 16:9 |
> | duration | 10s | KLING: 5 / 10 / 15; VEO fast: 8 only |
> | generate_audio | false | Whether to auto-generate audio |
> | prompt | Full expanded English prompt (entire text for this run) | Revise before confirm |
> | Loop seam | No | Reply “loop” for seamless loop |
>
> Reply “confirm” to start, or list what to change.
Expanded prompt: Compose at generation time per ## Prompt expansion (mandatory) from the user's actual brief—do not reuse fixed sample paragraphs.
Prompt tips
Timelapse feel: time-lapse compression, days visible in seconds, light cycles through the sequence, INLINECODE75
Life beats: seedling breaks through soil surface, root tip emerges driven by gravity, flower petals open in slow motion, INLINECODE79
Texture: terracotta pot texture, soil granularity visible, glass-sided container reveals root system, INLINECODE83
Note: Say time-lapse explicitly or the model may output a static plant instead of growth. Adding light cycling or shadow angle changing strengthens the sense of elapsed time.
园艺与植物生长视频生成
土壤中的种子,根系向下延伸,子叶破土而出,茎干日复一日地伸展,花蕾膨胀,花朵在阳光下绽放——十秒钟就能呈现完整的生命周期;这就是延时摄影的魔力。兔子与草莓,熊与多肉植物,猫与阳台番茄:成长本身就是故事。
依赖项:本目录下的 scripts/videogen.js + WERYAIAPI_KEY + Node.js 18+。不依赖其他Cursor技能。
前置条件
- - 运行 videogen.js 前,必须在环境中设置 WERYAIAPI_KEY。
- 需要 Node.js 18+ 版本。图片输入必须是公开的 https URL(不支持本地文件路径)。
- 每次成功的 wait 运行都会消耗WeryAI积分;重新运行会创建新的付费任务。
安全、密钥与API主机
- - WERYAIAPIKEY:视为机密信息。仅在你信任此技能来源时进行配置;它在OpenClaw元数据中被列为 requires.env / primaryEnv,因此安装程序知道它在运行时是必需的(切勿将其提交到技能包内)。
- 可选URL覆盖(WERYAIBASEURL、WERYAIMODELSBASEURL):videogen.js 默认使用 https://api.weryai.com 和 https://api-growth-agent.weryai.com。覆盖设置仅用于测试或经批准的备用端点。如果在环境中设置了这些变量,请确认它们指向你信任的主机——否则提示词、图片和你的bearer令牌可能被发送到其他地方。
- 更高保障:在短期或隔离环境(独立账户或容器)中运行生成,并在生产使用前审查 scripts/video_gen.js(HTTPS提交+轮询循环)。
提示词扩展(必需)
video_gen.js 不会扩展提示词。每次执行 wait --json 前,将用户的简短或模糊需求转化为完整的英文制作 prompt。
何时扩展: 用户只提供关键词、一行描述或模糊意图——或要求更丰富的视频语言。例外情况: 用户粘贴了符合模型 promptlengthlimit 的完整长提示词,并要求你不要重写;但仍需在确认表中展示完整文本。
始终添加(视频语言): 镜头景别和角度;相机运动或固定;光线质量和动机;主体动作与 duration 匹配;一个明确的该细分领域的亮点;当此技能默认竖屏时,注明 9:16 竖屏。
长度: 当本文档列出所选 modelkey 的 promptlength_limit 时,遵守该限制;在删除核心动作、镜头或光线从句之前,先修剪多余的形容词。
确认: 提交前表格必须包含完整的扩展 prompt(绝不能是一行摘要)。等待确认或修改。
细分领域检查清单
- - 时间语言: 延时摄影,可见的天/周压缩,光线角度或阴影漂移以显示时间流逝。
- 节奏: 种子/发芽/叶片/花朵/果实(如适用);可选手或爪子;陶土、土壤、玻璃根视图。
- 亮点: 收获、盛开或填满的花盆比开始更清晰。
### 示例提示词 位于本文件顶部,仅为简短触发词——始终根据用户的实际请求进行扩展。
工作流程
- 1. 确认用户请求符合此技能的场景(如文档所述的文本转视频和/或图片转视频)。
- 收集用户的简要需求、可选的图片URL、等级(最佳 / 良好 / 快速)或明确的 model 键。
- 扩展提示词(必需): 除非用户提供了完整的提示词并明确要求不要重写,否则使用下方的 ## 提示词扩展(必需) 将简要需求扩展为完整的英文制作 prompt。不要仅用用户的简短词语调用API。
- 对照本文档冻结表格中选定模型的 promptlengthlimit(如有)检查扩展后的 prompt;如有需要则缩短。
- 对照此SKILL.md中的冻结表格和API说明,验证 duration、aspectratio、resolution、generateaudio、negativeprompt 及其他字段。
- 显示提交前参数表,包括完整的扩展 prompt;等待确认或修改。
- 确认后,使用扩展后的提示词运行 node {baseDir}/scripts/videogen.js wait --json ...。
- 解析stdout JSON并返回视频URL;失败时,显示 errorCode / errorMessage 并建议参数修复。
CLI参考
sh
node {baseDir}/scripts/videogen.js wait --json {model:…,prompt:…,duration:5,aspectratio:9:16}
node {baseDir}/scripts/video_gen.js wait --json … --dry-run
node {baseDir}/scripts/video_gen.js status --task-id
完成标准
当用户从API响应中收到至少一个可播放的视频URL,或收到明确的失败说明及后续步骤时,视为完成。使用的所有参数必须在本文档所选模型的允许范围内。提交的 prompt 必须是扩展后的制作提示词,除非用户明确提供了完整的提示词并要求不要重写。
边界(范围外)
- - 不审查平台合规性、版权或肖像权;不保证输出的商业可用性。
- 不提供非WeryAI的离线渲染、传统编辑时间线或本文档未记录的API字段组合。
- 不在技能文档中硬编码绝对路径;{baseDir} 表示技能包根目录(与 SKILL.md 同级)。
示例提示词
- - 兔子在阳台种番茄:种子到藤上红果,竖屏延时生长
- 使用这张多肉盆栽图片:叶片在数天内变得饱满且颜色加深
- 蘑菇从菌包到收获,治愈自然光
- 舒适的植物生长延时 9:16,窗边阳光,可爱动物园丁
默认参数
9:16(固定) |
| 时长 | 10秒(duration: 10——完整生长弧线) |
| 音频 | 关闭 |
| 视觉风格 | 正面中景或俯拍;自然光(窗边阳光);延时摄影感;光线方向随天数变化;简单背景(土壤、陶土、木材) |
API有效性(默认 KLINGV30PRO): 文本转视频 duration 仅 5 / 10 / 15;aspectratio 仅 9:16, 1:1, 16:9。图片转视频 aspectratio 仅 9:16, 16:9, 1:1。无 resolution 字段——请勿发送。 对于使用VEO的快速等级:文本转视频 VEO31FAST,图片转视频 CHATBOTVEO31FAST,duration 固定为8,aspectratio 仅 9:16 或 16:9。切换 modelkey 时,遵循本节模型/API约束中的允许集合及上述API有效性说明;不要向不支持 resolution 的模型发送该字段。
从种子到发芽到开花结果
目的: 从种植到令人满意的收获或开花的时间压缩生长。关键节点:破土而出和最终的花朵或果实时刻。
描述角色和植物——无需额外形式:
例如:兔子种草莓或猫种阳台番茄——技能会自动填充完整的生长弧线和视觉细节。
生成前显示参数:
使用以下参数生成——回复确认或说明要更改的内容:
- - 模型:KLINGV30_PRO
- 宽高比:9:16
- 时长:10
- 生成音频:false
- 循环接缝:否(回复 loop 启用;在提示词后追加 seamless loop)
扩展提示词: 根据 ## 提示词扩展(必需) 在生成时根据用户的实际简要需求编写——不要重复使用固定的示例段落。
参数配置:
9:16 |
| 时长 | 10 |
| 生成音频 | false |
预期结果: 清晰的时间推进;发芽和开花/结果作为高潮