muapi-one-shot-video — Claude Code skill: one continuous take
Builds the prompt and fires off a single uncut cinematic shot: no transitions, camera motion, dramatic lighting.
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-one-shot-video -a claude-code
npx skills add SamurAIGPT/Generative-Media-Skills --skill one-shot-video -a claude-codeWhat muapi-one-shot-video does
The skill turns your scene into one continuous take. It appends "one continuous uncut shot, no transitions", camera movement, your style, film grain and 4K to the prompt, so the model does not chop the scene into edit points.
There is one step. Pass a reference_image and the call goes through muapi video generate with veo3.1-image-to-video; without one it uses veo3.1-text-to-video. Only scene is required — style, duration and aspect_ratio are optional. For 9:16 the skill suggests adding "vertical format, smartphone framing" to the prompt, and when a person is in frame it points at kling-v3.0-pro-image-to-video for better human motion.
You need MUAPI_API_KEY set and muapi auth configure run before the first call. No key, no render — that is the first thing to check. After the video comes back the skill offers a second angle of the same scene or ambient sound via mmaudio-v2-video-to-video.
What it helps with
- generate a video as one uncut continuous shot
- put camera motion and dramatic lighting into the prompt
- anchor a scene to a reference image
- produce a vertical 9:16 clip for phone framing
- add ambient sound to a finished clip
Example prompts for the agent
- Generate a one-shot video: a chef plating food in a moody Michelin-star kitchen, 10s, 16:9
- Make a continuous take from this reference image, noir style, handheld, golden hour
- Build a vertical one take in 9:16 and add ambient sound
How to install muapi-one-shot-video
1Skills CLI (Vercel)
npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-one-shot-video -a claude-codenpx skills add SamurAIGPT/Generative-Media-Skills --skill one-shot-video -a claude-code2Manually: put the files in place
~/.claude/skills/one-shot-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/one-shot-video/
1Skills CLI (Vercel)
npx skills add SamurAIGPT/Generative-Media-Skills --skill one-shot-video -a codex2Manually: put the files in place
.agents/skills/one-shot-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SamurAIGPT/Generative-Media-Skills --skill one-shot-video -a cursor2Manually: put the files in place
.cursor/skills/one-shot-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SamurAIGPT/Generative-Media-Skills one-shot-video2Manually: put the files in place
.github/skills/one-shot-video/SKILL.md1Skills CLI (Vercel)
npx skills add SamurAIGPT/Generative-Media-Skills --skill one-shot-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/SamurAIGPT/Generative-Media-Skills --path library/motion/one-shot-videoManually: put the files in place
.devin/skills/one-shot-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add SamurAIGPT/Generative-Media-Skills --skill one-shot-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about muapi-one-shot-video
How do I install muapi-one-shot-video in Claude?
Run npx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-one-shot-video -a claude-code. The skill lands at ~/.claude/skills/one-shot-video/SKILL.md.
What does muapi-one-shot-video do?
It assembles a prompt for a single continuous cinematic shot and runs the generation through muapi video generate. Camera motion, style, film grain and 4K go into the prompt.
What do I need before it works?
A MUAPI_API_KEY and muapi auth configure run once. Without the key the API calls will not go through.
Source text
SKILL.md · MIT
---
slug: muapi-one-shot-video
name: muapi-one-shot-video
version: "1.0.0"
description: Generate a single continuous cinematic shot video — no cuts, one seamless flowing scene with dramatic lighting and motion.
acceptLicenseTerms: true
---
# One-Shot Video
**Generate a single continuous cinematic shot video — no cuts, one seamless flowing scene with dramatic lighting and motion.**
## Inputs
| Name | Type | Required | Default | Description |
|:---|:---|:---|:---|:---|
| `scene` | text | yes | — | The scene to render (e.g. "a chef plating food in a moody Michelin-star kitchen"). |
| `style` | text | no | cinematic, anamorphic lens, shallow depth of field, dramatic lighting | Visual tone and style (e.g. "noir, handheld, golden hour"). |
| `duration` | text | no | 10s | Target duration (e.g. "5s", "10s"). |
| `aspect_ratio` | text | no | 16:9 | Output aspect ratio — "16:9", "9:16", or "1:1". |
| `reference_image` | image_url | no | — | Optional reference image for subject/scene anchoring. |
## Steps
### Phase A — Generate the One-Shot Video
Submit the plan with ONE step:
1. **One-shot video** — If `{{reference_image}}` is provided, use `muapi video generate` (model=`veo3.1-image-to-video`); otherwise use `muapi video generate` (model=`veo3.1-text-to-video`).
- Prompt: `{{scene}}, one continuous uncut shot, no transitions, camera slowly moves through scene, {{style}}, ultra cinematic, film grain, 4K quality`
- Aspect ratio: `{{aspect_ratio}}`
- Duration: `{{duration}}`
After generation, present the video and suggest:
- A second angle variation
- Adding ambient sound with `mmaudio-v2-video-to-video`
## Notes
- Emphasize "no cuts, no transitions" in the prompt for true one-shot feel.
- For portrait/vertical style (9:16), add "vertical format, smartphone framing" to the prompt.
- If the scene involves a person, suggest `kling-v3.0-pro-image-to-video` as an alternative for better human motion.
## Trigger Keywords
`one shot video`, `single take`, `continuous video`, `one take`, `cinematic shot`, `seamless video`
---
## Notes for the Executing Agent
- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.
© SamurAIGPT · MIT · SamurAIGPT/Generative-Media-Skills