veo-3.2-prompter

Name: veo-3.2-prompter
Author: pexoai

752stars37forks

How to install veo-3.2-prompter?

pexoai/pexo-skills/veo-3.2-prompter

$npx -y skills add pexoai/pexo-skills --skill veo-3.2-prompter

Installs into the current project.

Summary

Expert prompt engineering for Google Veo 3.2 (Artemis engine). Use when the user wants to generate a video with Veo 3.2, needs help crafting cinematic prompts, or mentions Veo, Google video generation, or Artemis engine.

Files · 1

View on GitHub

SKILL.md

1	# Veo 3.2 Prompt Designer Skill
2
3	This skill transforms a user's scattered multimodal assets (images, videos, audio) and creative intent into a structured, executable prompt for the Google Veo 3.2 video generation model (Artemis engine). It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.
4
5	## When to Use
6
7	- When the user provides assets (images, videos, audio) for video generation with Veo 3.2.
8	- When the user's request is complex and requires careful prompt construction for the Veo model.
9	- When using any Google Veo 3.x model for video generation.
10
11	## Core Function
12
13	This skill analyzes all user inputs and generates a single, optimized JSON object containing the final prompt and recommended parameters. The internal workflow (Recognition, Mapping, Construction) is handled automatically and should not be exposed to the user.
14
15	### Internal Workflow
16
17	1. Phase 1: Recognition — Analyze uploaded assets and user intent. Use the `atomic_element_mapping.md` to classify each asset into its atomic element role(s).
18	2. Phase 2: Mapping — For each atomic element, determine the optimal reference method (reference image, text prompt, or hybrid). Use the mapping table to decide.
19	3. Phase 3: Construction — Assemble the final prompt using the 5-Part Framework (Shot → Subject → Environment → Camera → Style) and attach reference images via the Gemini API's `RawReferenceImage` system.
20
21	## Usage Example
22
23	User Request: "Make a cinematic shot of this perfume bottle rotating on a dark surface, like a luxury commercial."
24	User uploads `perfume.png`
25
26	Agent using `veo-3.2-prompter`:
27	The agent internally processes the request and assets, then outputs the final JSON to the next skill in the chain.
28
29	Final Output (for internal use):
30	```json
31	{
32	"final_prompt": "Hero shot, a frosted glass perfume bottle with gold cap rotating slowly on a reflective dark surface, three-point studio lighting with soft key and rim light creating subtle caustics, smooth 180-degree arc, hyper-realistic luxury commercial style with shallow depth of field. Crystalline chime, soft ambient pad.",
33	"reference_images": [
34	{
35	"file": "perfume.png",
36	"reference_type": "SUBJECT"
37	}
38	],
39	"recommended_parameters": {
40	"model": "veo-3.2-generate",
41	"duration_seconds": 8,
42	"aspect_ratio": "16:9",
43	"resolution": "1080p",
44	"generate_audio": true
45	}
46	}
47	```
48
49	## Veo 3.2 Key Differentiators
50
51	\| Feature \| Capability \|
52	\|---\|---\|
53	\| Engine \| Artemis — world-model physics simulation (not pixel prediction) \|
54	\| Max duration \| ~30s native continuous generation \|
55	\| Audio \| Native dialogue + synchronized SFX \|
56	\| Reference images \| Up to 3 (`STYLE`, `SUBJECT`, `SUBJECT_FACE`) \|
57	\| Video extension \| Chain clips via previous video input \|
58	\| First/last frame \| Specify start and/or end keyframes \|
59	\| Resolutions \| 720p, 1080p, 4K (with upscaling) \|
60	\| Aspect ratios \| 16:9, 9:16 \|
61
62	## Knowledge Base
63
64	This skill relies on an internal knowledge base to make informed decisions. The agent MUST consult these files during execution.
65
66	- `references/atomic_element_mapping.md`: Core Knowledge. Contains the "Asset Type → Atomic Element" and "Atomic Element → Optimal Reference Method" mapping tables, adapted for Veo 3.2's reference image system.
67	- `references/veo_syntax_guide.md`: Veo 3.2 Gemini API syntax reference, covering `RawReferenceImage`, `GenerateVideosConfig`, video extension, and first/last frame specification.

People who liked this also viewed

6 picks

Type

veo-3.2-prompter

752stars37forks

View on GitHub

How to install veo-3.2-prompter?

pexoai/pexo-skills/veo-3.2-prompter

$npx -y skills add pexoai/pexo-skills --skill veo-3.2-prompter

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Veo 3.2 Prompt Designer Skill
2
3	This skill transforms a user's scattered multimodal assets (images, videos, audio) and creative intent into a structured, executable prompt for the Google Veo 3.2 video generation model (Artemis engine). It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.
4
5	## When to Use
6
7	- When the user provides assets (images, videos, audio) for video generation with Veo 3.2.
8	- When the user's request is complex and requires careful prompt construction for the Veo model.
9	- When using any Google Veo 3.x model for video generation.
10
11	## Core Function
12
13	This skill analyzes all user inputs and generates a single, optimized JSON object containing the final prompt and recommended parameters. The internal workflow (Recognition, Mapping, Construction) is handled automatically and should not be exposed to the user.
14
15	### Internal Workflow
16
17	1. Phase 1: Recognition — Analyze uploaded assets and user intent. Use the `atomic_element_mapping.md` to classify each asset into its atomic element role(s).
18	2. Phase 2: Mapping — For each atomic element, determine the optimal reference method (reference image, text prompt, or hybrid). Use the mapping table to decide.
19	3. Phase 3: Construction — Assemble the final prompt using the 5-Part Framework (Shot → Subject → Environment → Camera → Style) and attach reference images via the Gemini API's `RawReferenceImage` system.
20
21	## Usage Example
22
23	User Request: "Make a cinematic shot of this perfume bottle rotating on a dark surface, like a luxury commercial."
24	User uploads `perfume.png`
25
26	Agent using `veo-3.2-prompter`:
27	The agent internally processes the request and assets, then outputs the final JSON to the next skill in the chain.
28
29	Final Output (for internal use):
30	```json
31	{
32	"final_prompt": "Hero shot, a frosted glass perfume bottle with gold cap rotating slowly on a reflective dark surface, three-point studio lighting with soft key and rim light creating subtle caustics, smooth 180-degree arc, hyper-realistic luxury commercial style with shallow depth of field. Crystalline chime, soft ambient pad.",
33	"reference_images": [
34	{
35	"file": "perfume.png",
36	"reference_type": "SUBJECT"
37	}
38	],
39	"recommended_parameters": {
40	"model": "veo-3.2-generate",
41	"duration_seconds": 8,
42	"aspect_ratio": "16:9",
43	"resolution": "1080p",
44	"generate_audio": true
45	}
46	}
47	```
48
49	## Veo 3.2 Key Differentiators
50
51	\| Feature \| Capability \|
52	\|---\|---\|
53	\| Engine \| Artemis — world-model physics simulation (not pixel prediction) \|
54	\| Max duration \| ~30s native continuous generation \|
55	\| Audio \| Native dialogue + synchronized SFX \|
56	\| Reference images \| Up to 3 (`STYLE`, `SUBJECT`, `SUBJECT_FACE`) \|
57	\| Video extension \| Chain clips via previous video input \|
58	\| First/last frame \| Specify start and/or end keyframes \|
59	\| Resolutions \| 720p, 1080p, 4K (with upscaling) \|
60	\| Aspect ratios \| 16:9, 9:16 \|
61
62	## Knowledge Base
63
64	This skill relies on an internal knowledge base to make informed decisions. The agent MUST consult these files during execution.
65
66	- `references/atomic_element_mapping.md`: Core Knowledge. Contains the "Asset Type → Atomic Element" and "Atomic Element → Optimal Reference Method" mapping tables, adapted for Veo 3.2's reference image system.
67	- `references/veo_syntax_guide.md`: Veo 3.2 Gemini API syntax reference, covering `RawReferenceImage`, `GenerateVideosConfig`, video extension, and first/last frame specification.

People who liked this also viewed

6 picks

Type