kling-studio

Name: kling-studio
Author: wells1137

12installs1forks

How to install kling-studio?

wells1137/media-skills/kling-studio

$npx -y skills add wells1137/media-skills --skill kling-studio

Installs into the current project.

Summary

Full-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base mode), video reference (feature mode), multi-shot generation, and audio-synced video. Includes validated API constraint rules and prompt engineering guide.

Files · 1

View on GitHub

SKILL.md

1	# Kling 3.0 Omni Video Generator
2
3	This skill enables the generation and manipulation of videos using the Kling 3.0 Omni model. It provides a structured workflow for constructing API requests based on user intent, ensuring compliance with the model's complex parameter constraints.
4
5	## Reference Files
6
7	This skill includes the following reference files:
8
9	- `references/api_reference.md` — Complete official API parameter reference, including all fields, types, constraints, mutual exclusion rules (R1–R10), capability matrix, and invocation examples. Read this file before constructing any API call.
10	- `references/prompt_guide.md` — Kling 3.0 Omni prompt writing principles, official formula, template syntax, and few-shot examples for all major scenarios.
11	- `scripts/kling_api.py` — Python utility class for JWT authentication, task creation, and polling.
12
13	---
14
15	## Core Capabilities
16
17	- Text-to-Video: Generate a video from a textual description.
18	- Image-to-Video: Animate a static image with a descriptive prompt.
19	- Video-to-Video (Editing): Modify an existing video based on a prompt (e.g., change subject, style).
20	- Video-to-Video (Reference): Use an existing video as a reference for camera movement and style.
21	- Multi-shot Generation: Create a video with multiple distinct scenes or shots.
22	- Audio Generation: Generate video with synchronized audio, including speech and sound effects.
23
24	---
25
26	## Workflow: From User Intent to API Call
27
28	To correctly use the Kling API, you MUST follow this decision-making workflow to construct the API payload. The process is divided into two main stages: Prompt Design and Parameter Construction.
29
30	### Stage 1: Prompt Design
31
32	Before constructing the API call, you must first design the prompt(s) based on the user's request. The quality of the prompt is the single most important factor for a good result.
33
34	1. Consult the Prompting Guide: Read `/home/ubuntu/skills/kling-studio/references/prompt_guide.md` to understand the core principles, official formula, and few-shot examples for writing effective prompts.
35
36	2. Identify the Scenario: Determine which of the following scenarios the user is requesting:
37	- Single-shot video (from text, image, or video)
38	- Multi-shot video (storyboard with multiple scenes)
39
40	3. Write the Prompt(s):
41	- For single-shot, write a single, detailed prompt following the guide's formula.
42	- For multi-shot, write a separate prompt for each shot/scene.
43	- Use Template Syntax: If the user provides reference images, elements, or videos, you MUST use the `<<<image_1>>>`, `<<<element_1>>>`, `<<<video_1>>>` template syntax in the prompt to explicitly reference them. This is a core feature of the Omni model.
44
45	### Stage 2: Parameter Construction
46
47	Once the prompt(s) are ready, construct the final API request payload by following this decision tree. This ensures all parameter constraints and interdependencies, discovered through extensive testing, are respected.
48
49	```mermaid
50	graph TD
51	A[Start] --> B{Multi-shot or Single-shot?};
52	B -- Multi-shot --> C[Set `multi_shot: true`];
53	B -- Single-shot --> D[Set `multi_shot: false`];
54
55	C --> E{Set `shot_type: "customize"`};
56	E --> F[Construct `multi_prompt` array from prompts];
57	F --> G[Calculate total duration from `multi_prompt`];
58	G --> H[Set top-level `duration`];
59	H --> Z[Final Payload];
60
61	D --> I{Video input provided?};
62	I -- Yes --> J{Editing or Reference?};
63	I -- No --> K[Text/Image-to-Video Path];
64
65	J -- Editing --> L[Set `refer_type: "base"`];
66	J -- Reference --> M[Set `refer_type: "feature"`];
67
68	L --> N[Ignore `duration` parameter];
69	M --> O[Set `aspect_ratio`];
70	N --> P{Audio handling};
71	O --> P;
72
73	K --> Q{Audio handling};
74	P --> R{Audio handling};
75
76	subgraph R [Audio Handling]
77	direction LR
78	R1{Want audio output?} -- Yes --> R2[Set `sound: "on"`];
79	R1 -- No --> R3[Set `sound: "off"`];
80	R2 --> R4{Video input exists?};
81	R4 -- Yes --> R5[ERROR: `sound:on` is incompatible with video input];
82	R4 -- No --> R6[OK];
83	end
84
85	Q --> Z;
86	R6 --> Z;
87	R3 --> Z;
88	R5 --> Stop([Stop/Error]);
89	```
90
91	#### Key Parameter Rules (from testin

People who liked this also viewed

6 picks

Type

kling-studio

12installs1forks

View on GitHub

How to install kling-studio?

wells1137/media-skills/kling-studio

$npx -y skills add wells1137/media-skills --skill kling-studio

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Kling 3.0 Omni Video Generator
2
3	This skill enables the generation and manipulation of videos using the Kling 3.0 Omni model. It provides a structured workflow for constructing API requests based on user intent, ensuring compliance with the model's complex parameter constraints.
4
5	## Reference Files
6
7	This skill includes the following reference files:
8
9	- `references/api_reference.md` — Complete official API parameter reference, including all fields, types, constraints, mutual exclusion rules (R1–R10), capability matrix, and invocation examples. Read this file before constructing any API call.
10	- `references/prompt_guide.md` — Kling 3.0 Omni prompt writing principles, official formula, template syntax, and few-shot examples for all major scenarios.
11	- `scripts/kling_api.py` — Python utility class for JWT authentication, task creation, and polling.
12
13	---
14
15	## Core Capabilities
16
17	- Text-to-Video: Generate a video from a textual description.
18	- Image-to-Video: Animate a static image with a descriptive prompt.
19	- Video-to-Video (Editing): Modify an existing video based on a prompt (e.g., change subject, style).
20	- Video-to-Video (Reference): Use an existing video as a reference for camera movement and style.
21	- Multi-shot Generation: Create a video with multiple distinct scenes or shots.
22	- Audio Generation: Generate video with synchronized audio, including speech and sound effects.
23
24	---
25
26	## Workflow: From User Intent to API Call
27
28	To correctly use the Kling API, you MUST follow this decision-making workflow to construct the API payload. The process is divided into two main stages: Prompt Design and Parameter Construction.
29
30	### Stage 1: Prompt Design
31
32	Before constructing the API call, you must first design the prompt(s) based on the user's request. The quality of the prompt is the single most important factor for a good result.
33
34	1. Consult the Prompting Guide: Read `/home/ubuntu/skills/kling-studio/references/prompt_guide.md` to understand the core principles, official formula, and few-shot examples for writing effective prompts.
35
36	2. Identify the Scenario: Determine which of the following scenarios the user is requesting:
37	- Single-shot video (from text, image, or video)
38	- Multi-shot video (storyboard with multiple scenes)
39
40	3. Write the Prompt(s):
41	- For single-shot, write a single, detailed prompt following the guide's formula.
42	- For multi-shot, write a separate prompt for each shot/scene.
43	- Use Template Syntax: If the user provides reference images, elements, or videos, you MUST use the `<<<image_1>>>`, `<<<element_1>>>`, `<<<video_1>>>` template syntax in the prompt to explicitly reference them. This is a core feature of the Omni model.
44
45	### Stage 2: Parameter Construction
46
47	Once the prompt(s) are ready, construct the final API request payload by following this decision tree. This ensures all parameter constraints and interdependencies, discovered through extensive testing, are respected.
48
49	```mermaid
50	graph TD
51	A[Start] --> B{Multi-shot or Single-shot?};
52	B -- Multi-shot --> C[Set `multi_shot: true`];
53	B -- Single-shot --> D[Set `multi_shot: false`];
54
55	C --> E{Set `shot_type: "customize"`};
56	E --> F[Construct `multi_prompt` array from prompts];
57	F --> G[Calculate total duration from `multi_prompt`];
58	G --> H[Set top-level `duration`];
59	H --> Z[Final Payload];
60
61	D --> I{Video input provided?};
62	I -- Yes --> J{Editing or Reference?};
63	I -- No --> K[Text/Image-to-Video Path];
64
65	J -- Editing --> L[Set `refer_type: "base"`];
66	J -- Reference --> M[Set `refer_type: "feature"`];
67
68	L --> N[Ignore `duration` parameter];
69	M --> O[Set `aspect_ratio`];
70	N --> P{Audio handling};
71	O --> P;
72
73	K --> Q{Audio handling};
74	P --> R{Audio handling};
75
76	subgraph R [Audio Handling]
77	direction LR
78	R1{Want audio output?} -- Yes --> R2[Set `sound: "on"`];
79	R1 -- No --> R3[Set `sound: "off"`];
80	R2 --> R4{Video input exists?};
81	R4 -- Yes --> R5[ERROR: `sound:on` is incompatible with video input];
82	R4 -- No --> R6[OK];
83	end
84
85	Q --> Z;
86	R6 --> Z;
87	R3 --> Z;
88	R5 --> Stop([Stop/Error]);
89	```
90
91	#### Key Parameter Rules (from testin

People who liked this also viewed

6 picks

Type