Plan Video Production Skill
Scope
Prerequisite: Plan collaboration is active (scenario(activate, plan) enabled), and the task involves visual/video output (image generation, short videos, voice-over, subtitles).
Vendor Selection: For image generation, use byted-ark-seedream-skill; for video generation, use the media-production script (Volcengine Seedance). For other vendors, see agnes-media-generation / wan-media-generation / kling-media-generation.
Credentials (Environment Variables)
In Settings → Environment Variables, add the required KEY=VALUE (e.g., VOLCENGINE_API_KEY / ARK_API_KEY). Alternatively, fill in other vendor keys under Settings → Models → Creative Media.
| Capability | Common KEY | Skill |
|---|---|---|
| Image generation | VOLCENGINE_API_KEY / ARK_API_KEY | byted-ark-seedream-skill |
| Video generation | Same as above | media-production |
| Agnes | AGNES_API_KEY | agnes-media-generation |
Key Change: All media roles (screenwriter, visual planner, artist, director, post-production) are entirely assigned via assigned_agent within the plan(goal, steps[]) steps. After the plan is saved and confirmed by the user, it enters executing mode for serial execution, with no separate sub-agent delegation outside the plan.
Workflow
User expresses requirements
↓
Ask and confirm user requirements (topic, duration, style, aspect ratio, etc.)
↓
Directly use plan(goal, steps[]) to plan
step 1: media-screenwriter — script/storyboard/narration
step 2: media-visual-planner — image generation prompts
step 3: media-artist — generate keyframes
step 4: media-video-director — produce video + native audio
step 5: media-post — hard subtitles
↓
User confirms → execution (serial, each step verified)
Steps
Step 1: Ask User Requirements
Actively collect the following information from the user:
| Question | Example |
|---|---|
| What is the video topic/product/content? | New smartwatch promotion |
| Target duration? | 15 seconds / 30 seconds |
| Visual style? | Tech / Warm / Chinese traditional |
| Aspect ratio? | 16:9 / 9:16 vertical |
| Direction for voice-over script? | Feature highlights + brand slogan |
| Any reference material? | Reference images / competitor videos |
Step 2: Plan Directly After Confirmation
After user confirmation, use the plan tool to write all steps into a structured plan:
plan(
goal="Produce a 15-second product promotional short video, topic: xxx, style: xxx",
steps=[
{
"step_id": 1,
"description": "Screenwriter writes production brief, including logline, storyboard, narration script",
"assigned_agent": "media-screenwriter",
"expected_output": "outputs/production-brief.md",
"acceptance_criteria": "Contains User intent, logline, visual style, shot list, narration script"
},
{
"step_id": 2,
"description": "Visual planner converts storyboard into image generation prompts",
"assigned_agent": "media-visual-planner",
"expected_output": "outputs/shot-prompts.json",
"depends_on": [1]
},
{
"step_id": 3,
"description": "Artist generates first-frame keyframe images",
"assigned_agent": "media-artist",
"expected_output": "PNG keyframes in outputs",
"depends_on": [2]
},
{
"step_id": 4,
"description": "Video director generates MP4 with native audio",
"assigned_agent": "media-video-director",
"expected_output": "outputs/*.mp4",
"depends_on": [3]
},
{
"step_id": 5,
"description": "Post-production adds hard subtitles, delivers final MP4",
"assigned_agent": "media-post",
"expected_output": "outputs/*-subtitled.mp4",
"depends_on": [4]
}
],
flowchart_mermaid="..."
)
Step 3: User Confirms Execution
After the plan is saved, the user confirms "start execution", entering executing phase. Steps run serially according to dependency order. After each step, the main agent verifies the output before proceeding to the next.
Media Sub-agent List
| assigned_agent | Responsibility | Core Tools |
|---|---|---|
media-screenwriter | Write script, storyboard, narration | read_file, write_to_file |
media-visual-planner | Write image generation prompts | read_file, write_to_file |
media-artist | Seedream image generation (jimeng) | read_file, terminal → scripts/image_generate.py |
media-video-director | Seedance image-to-video + native audio | read_file, terminal → scripts/video_generate.py, task_wait.py |
media-post | SRT subtitles + ffmpeg hard subtitles | read_file, terminal → scripts/subtitle_build.py, subtitle_burn.py |
Note: Do not include media-voice-director in the steps — Seedance natively includes audio (generate_audio=true is enabled by default).
Tech Stack
Scripts directory: skills/public/media-production/scripts/ (must first read the media-production skill)
| Capability | Script | provider |
|---|---|---|
| Image generation | image_generate.py | jimeng (Volcengine Ark Seedream) |
| Video generation | video_generate.py + task_wait.py | jimeng (Volcengine Ark Seedance, with audio by default) |
| Subtitles | subtitle_build.py + subtitle_burn.py | Local ffmpeg |
Failure Handling: If jimeng fails, do not automatically switch to wan/kling; prompt the user to activate Ark model access points. Retry with the same parameters at most once.
Common Errors
- Running
image_generate.pydirectly in the main session under plan mode → should be executed bymedia-artistwithin a plan step - Delegating sub-agents outside plan steps → all roles should be written in plan steps'
assigned_agent - Skipping
task_wait.py→ delivers video before generation completes - Still delegating
media-voice-directorin the default pipeline → Seedance natively includes audio, this is redundant