media-router
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMedia Router
媒体路由
Follow shared release-shell rules in:
- release-shell rules
postplus-shared
Use this skill when the user wants to do something with:
- audio
- video
- transcripts
- subtitles
- A-roll / B-roll edit prep
This skill is a routing layer.
It should decide:
- what the actual task is
- what output shape is required
- whether the job is rough, subtitle-ready, or edit-ready
- whether cost or quality should dominate
- which downstream skill or skill chain should execute
This skill should not pretend every request is "just transcription".
请遵循以下共享发布规则:
- 发布规则
postplus-shared
当用户需要处理以下内容时,可使用此Skill:
- 音频
- 视频
- 转录文本
- 字幕
- A-roll / B-roll 编辑准备
此Skill是一个路由层。
它需要决定:
- 实际任务是什么
- 需要的输出形式
- 任务是粗略处理、字幕就绪还是可编辑就绪
- 应优先考虑成本还是质量
- 应执行哪个下游Skill或Skill链
此Skill不应将所有请求都当作“只是转录”来处理。
Use For
使用场景
- deciding whether to call audio STT or video STT
- deciding when timestamps are required
- deciding when subtitle packaging is enough
- deciding when semantic video understanding must be added
- deciding when editing-decision-engine should run
- deciding whether a batch workflow should be used
- 决定调用音频STT还是视频STT
- 决定是否需要时间戳
- 决定是否仅需字幕打包即可
- 决定是否必须添加语义视频理解
- 决定是否应运行编辑决策引擎
- 决定是否应使用批处理工作流
Read These References
参考文档
references/brief-schema.mdreferences/routing-modes.md
references/brief-schema.mdreferences/routing-modes.md
Core Rule
核心规则
Route by job intent, not by input file type alone.
A video input may still be:
- plain transcription
- subtitle generation
- transcript plus semantic understanding
- edit-beat planning
The route should be chosen from five dimensions:
- input type
- output goal
- required precision
- scale
- cost mode
根据任务意图进行路由,而非仅根据输入文件类型。
视频输入可能对应以下任务:
- 纯转录
- 字幕生成
- 转录文本加语义理解
- 编辑节拍规划
路由需从五个维度选择:
- 输入类型
- 输出目标
- 所需精度
- 规模
- 成本模式
Default Routing Logic
默认路由逻辑
audio -> transcript
audio -> transcriptaudio -> transcript
audio -> transcriptUse .
skills/40-creative/audio-transcription使用 。
skills/40-creative/audio-transcriptionvideo -> transcript/subtitles
video -> transcript/subtitlesvideo -> transcript/subtitles
video -> transcript/subtitlesUse .
skills/40-creative/video-transcription使用 。
skills/40-creative/video-transcriptiontranscript with timestamps -> subtitle files
transcript with timestamps -> subtitle filestranscript with timestamps -> subtitle files
transcript with timestamps -> subtitle filesUse .
skills/40-creative/subtitle-packager使用 。
skills/40-creative/subtitle-packagertranscript + assets -> cut logic / B-roll plan
transcript + assets -> cut logic / B-roll plantranscript + assets -> cut logic / B-roll plan
transcript + assets -> cut logic / B-roll planUse .
skills/40-creative/editing-decision-engine使用 。
skills/40-creative/editing-decision-enginevideo -> edit-ready plan
video -> edit-ready planvideo -> edit-ready plan
video -> edit-ready planChain:
video-transcription- if subtitle files are needed
subtitle-packager - if visual-proof snapshots are needed
frame-extraction editing-decision-engine
链式流程:
video-transcription- 若需要字幕文件则调用
subtitle-packager - 若需要视觉验证快照则调用
frame-extraction editing-decision-engine
Quality Thresholds
质量阈值
rough
roughrough
(粗略处理)
roughGood enough for:
- search
- quick review
- rough logging
- candidate beat spotting
Prefer:
- cheaper models
- fewer enrichments
适用于:
- 搜索
- 快速审核
- 粗略日志记录
- 候选节拍识别
优先选择:
- 低成本模型
- 更少的增强处理
subtitle-ready
subtitle-readysubtitle-ready
(字幕就绪)
subtitle-readyGood enough for:
- human-readable captions
- SRT / VTT generation
- reliable sentence or word timestamps
Prefer:
- Whisper with timestamps
适用于:
- 人类可读字幕
- SRT / VTT 生成
- 可靠的句子或单词级时间戳
优先选择:
- 带时间戳的Whisper模型
edit-ready
edit-readyedit-ready
(可编辑就绪)
edit-readyGood enough for:
- A-roll/B-roll decision making
- cutaway placement
- beat-level planning
Prefer:
- Whisper with timestamps
- semantic video understanding when proof footage matters
- editing-decision-engine downstream
适用于:
- A-roll/B-roll决策
- 切换镜头放置
- 节拍级规划
优先选择:
- 带时间戳的Whisper模型
- 当需要验证素材时使用语义视频理解
- 下游调用编辑决策引擎
User-Facing Explanation Rule
用户端说明规则
Do not expose internal route labels unless the user is explicitly designing the system.
Normal user-facing language should say:
- what will be extracted first
- what will be aligned second
- what editing decisions become possible afterward
除非用户明确在设计系统,否则不要暴露内部路由标签。
面向普通用户的语言应说明:
- 首先将提取什么内容
- 接下来将对齐什么内容
- 之后可实现哪些编辑决策
Default Output
默认输出
Return:
- chosen route
- why it fits the task
- primary skill
- supporting skills
- model plan
- expected output artifacts
- whether timestamps are mandatory
返回:
- 选定的路由
- 该路由适配任务的原因
- 主Skill
- 辅助Skill
- 模型方案
- 预期输出产物
- 是否必须包含时间戳