create-video

Name: create-video
Author: calesthio

330installs4.9kforks

How to install create-video?

calesthio/openmontage/create-video

$npx -y skills add calesthio/OpenMontage --skill create-video

Installs into the current project.

Summary

Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video proto

Files · 1

View on GitHub

SKILL.md

1	# Create Video
2
3	Generate complete videos from a text prompt. Describe what you want and the AI handles script writing, avatar selection, visuals, voiceover, pacing, and captions automatically.
4
5	## Authentication
6
7	All requests require the `X-Api-Key` header. Set the `HEYGEN_API_KEY` environment variable.
8
9	```bash
10	curl -X POST "https://api.heygen.com/v1/video_agent/generate" \
11	-H "X-Api-Key: $HEYGEN_API_KEY" \
12	-H "Content-Type: application/json" \
13	-d '{"prompt": "Create a 60-second product demo video."}'
14	```
15
16	## Tool Selection
17
18	If HeyGen MCP tools are available (`mcp__heygen__`), prefer them* over direct HTTP API calls — they handle authentication and request formatting automatically.
19
20	\| Task \| MCP Tool \| Fallback (Direct API) \|
21	\|------\|----------\|----------------------\|
22	\| Generate video from prompt \| `mcp__heygen__generate_video_agent` \| `POST /v1/video_agent/generate` \|
23	\| Check video status / get URL \| `mcp__heygen__get_video` \| `GET /v2/videos/{video_id}` \|
24	\| List account videos \| `mcp__heygen__list_videos` \| `GET /v2/videos` \|
25	\| Delete a video \| `mcp__heygen__delete_video` \| `DELETE /v2/videos/{video_id}` \|
26
27	If no HeyGen MCP tools are available, use direct HTTP API calls as documented in the reference files.
28
29	## Default Workflow
30
31	Always use [prompt-optimizer.md](references/prompt-optimizer.md) guidelines to structure prompts with scenes, timing, and visual styles.
32
33	With MCP tools:
34	1. Write an optimized prompt using [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md)
35	2. Call `mcp__heygen__generate_video_agent` with prompt and config (duration_sec, orientation, avatar_id)
36	3. Call `mcp__heygen__get_video` with the returned video_id to poll status and get the download URL
37
38	Without MCP tools (direct API):
39	1. Write an optimized prompt using [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md)
40	2. `POST /v1/video_agent/generate` — see [video-agent.md](references/video-agent.md)
41	3. `GET /v2/videos/<id>` — see [video-status.md](references/video-status.md)
42
43	## Quick Reference
44
45	\| Task \| MCP Tool \| Read \|
46	\|------\|----------\|------\|
47	\| Generate video from prompt \| `mcp__heygen__generate_video_agent` \| [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md) → [video-agent.md](references/video-agent.md) \|
48	\| Check video status / get download URL \| `mcp__heygen__get_video` \| [video-status.md](references/video-status.md) \|
49	\| Upload reference files for prompt \| — \| [assets.md](references/assets.md) \|
50
51	## When to Use This Skill vs Avatar Video
52
53	This skill is for prompt-based video creation — describe what you want, and the AI handles the rest.
54
55	If the user needs precise control over specific avatars, exact scripts, per-scene voice/background configuration, or multi-scene composition, use the avatar-video skill instead.
56
57	\| User Says \| This Skill \| Avatar Video Skill \|
58	\|-----------\|:----------:\|:------------------:\|
59	\| "Make me a video about X" \| ✓ \| \|
60	\| "Create a product demo" \| ✓ \| \|
61	\| "I want avatar Y to say exactly Z" \| \| ✓ \|
62	\| "Multi-scene video with different backgrounds" \| \| ✓ \|
63	\| "Transparent WebM for compositing" \| \| ✓ \|
64
65	## Reference Files
66
67	### Core Workflow
68	- [references/prompt-optimizer.md](references/prompt-optimizer.md) - Writing effective prompts (core workflow + rules)
69	- [references/visual-styles.md](references/visual-styles.md) - 20 named visual styles with full specs
70	- [references/prompt-examples.md](references/prompt-examples.md) - Full production prompt example + ready-to-use templates
71	- [references/video-agent.md](references/video-agent.md) - Video Agent API endpoint details
72
73	### Foundation
74	- [references/video-status.md](references/video-status.md) - Polling patterns and download URLs
75	- [references/webhooks.md](references/webhooks.md) - Webhook endpoints and events
76	- [references/assets.md](references/assets.md) - Uploading images, videos, audio as references
77	- [references/dimensions.md](references/dimensions.md) - Resolution and aspect ratios
78	- [references/quota.md](references/quota.md) - Credit system and usage limits
79
80	## Best Practices
81
82	1. Optimize your prompt — The difference between mediocre and professional results depends entirely on prompt quality. Always use the prompt optimizer
83	2. **Speci

People who liked this also viewed

6 picks

Type

create-video

330installs4.9kforks

View on GitHub

How to install create-video?

calesthio/openmontage/create-video

$npx -y skills add calesthio/OpenMontage --skill create-video

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Create Video
2
3	Generate complete videos from a text prompt. Describe what you want and the AI handles script writing, avatar selection, visuals, voiceover, pacing, and captions automatically.
4
5	## Authentication
6
7	All requests require the `X-Api-Key` header. Set the `HEYGEN_API_KEY` environment variable.
8
9	```bash
10	curl -X POST "https://api.heygen.com/v1/video_agent/generate" \
11	-H "X-Api-Key: $HEYGEN_API_KEY" \
12	-H "Content-Type: application/json" \
13	-d '{"prompt": "Create a 60-second product demo video."}'
14	```
15
16	## Tool Selection
17
18	If HeyGen MCP tools are available (`mcp__heygen__`), prefer them* over direct HTTP API calls — they handle authentication and request formatting automatically.
19
20	\| Task \| MCP Tool \| Fallback (Direct API) \|
21	\|------\|----------\|----------------------\|
22	\| Generate video from prompt \| `mcp__heygen__generate_video_agent` \| `POST /v1/video_agent/generate` \|
23	\| Check video status / get URL \| `mcp__heygen__get_video` \| `GET /v2/videos/{video_id}` \|
24	\| List account videos \| `mcp__heygen__list_videos` \| `GET /v2/videos` \|
25	\| Delete a video \| `mcp__heygen__delete_video` \| `DELETE /v2/videos/{video_id}` \|
26
27	If no HeyGen MCP tools are available, use direct HTTP API calls as documented in the reference files.
28
29	## Default Workflow
30
31	Always use [prompt-optimizer.md](references/prompt-optimizer.md) guidelines to structure prompts with scenes, timing, and visual styles.
32
33	With MCP tools:
34	1. Write an optimized prompt using [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md)
35	2. Call `mcp__heygen__generate_video_agent` with prompt and config (duration_sec, orientation, avatar_id)
36	3. Call `mcp__heygen__get_video` with the returned video_id to poll status and get the download URL
37
38	Without MCP tools (direct API):
39	1. Write an optimized prompt using [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md)
40	2. `POST /v1/video_agent/generate` — see [video-agent.md](references/video-agent.md)
41	3. `GET /v2/videos/<id>` — see [video-status.md](references/video-status.md)
42
43	## Quick Reference
44
45	\| Task \| MCP Tool \| Read \|
46	\|------\|----------\|------\|
47	\| Generate video from prompt \| `mcp__heygen__generate_video_agent` \| [prompt-optimizer.md](references/prompt-optimizer.md) → [visual-styles.md](references/visual-styles.md) → [video-agent.md](references/video-agent.md) \|
48	\| Check video status / get download URL \| `mcp__heygen__get_video` \| [video-status.md](references/video-status.md) \|
49	\| Upload reference files for prompt \| — \| [assets.md](references/assets.md) \|
50
51	## When to Use This Skill vs Avatar Video
52
53	This skill is for prompt-based video creation — describe what you want, and the AI handles the rest.
54
55	If the user needs precise control over specific avatars, exact scripts, per-scene voice/background configuration, or multi-scene composition, use the avatar-video skill instead.
56
57	\| User Says \| This Skill \| Avatar Video Skill \|
58	\|-----------\|:----------:\|:------------------:\|
59	\| "Make me a video about X" \| ✓ \| \|
60	\| "Create a product demo" \| ✓ \| \|
61	\| "I want avatar Y to say exactly Z" \| \| ✓ \|
62	\| "Multi-scene video with different backgrounds" \| \| ✓ \|
63	\| "Transparent WebM for compositing" \| \| ✓ \|
64
65	## Reference Files
66
67	### Core Workflow
68	- [references/prompt-optimizer.md](references/prompt-optimizer.md) - Writing effective prompts (core workflow + rules)
69	- [references/visual-styles.md](references/visual-styles.md) - 20 named visual styles with full specs
70	- [references/prompt-examples.md](references/prompt-examples.md) - Full production prompt example + ready-to-use templates
71	- [references/video-agent.md](references/video-agent.md) - Video Agent API endpoint details
72
73	### Foundation
74	- [references/video-status.md](references/video-status.md) - Polling patterns and download URLs
75	- [references/webhooks.md](references/webhooks.md) - Webhook endpoints and events
76	- [references/assets.md](references/assets.md) - Uploading images, videos, audio as references
77	- [references/dimensions.md](references/dimensions.md) - Resolution and aspect ratios
78	- [references/quota.md](references/quota.md) - Credit system and usage limits
79
80	## Best Practices
81
82	1. Optimize your prompt — The difference between mediocre and professional results depends entirely on prompt quality. Always use the prompt optimizer
83	2. **Speci

People who liked this also viewed

6 picks

Type