laohu-video-voice SKILL.md skillA
laohu-video-voice from laohuad/laohu-creative-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add laohuad/laohu-creative-skills/laohu-video-voice@git:20261106.42593f7Pins git:20261106.42593f7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- laohuad/laohu-creative-skills
- Path
.agents/skills/laohu-video/skills/laohu-video-voice/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261106.42593f7, committed Nov 6, 2026
- Size
- 3,002 bytes
- Repository stars
- 7
- License
- a license file GitHub does not identify
当对白、旁白或人物发声会影响表演、理解或时长时，为锁定原句设计具体发声与停连方式。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
由 Video 主 Skill 第七步按发声需要加载。没有人声，且声音设计无需语音表现时不触发。输入为逐字台词、说话对象、行动意图、剧本括注、前后回应、镜头预算，以及 Assets 已建立的稳定声音身份与本轮真实声音素材职责。先继承已绑定的说话人/稳定声线和用户锁定项，再设计当句表现；不得因情绪、耳语或音量变化重选角色音色。 ## 发声方法 1. 保持锁定台词逐字不变，先确认说话者想对谁完成什么行动：安抚、试探、拒绝、掩饰、逼问、请求或其他已成立意图。原文语病、方言、称谓和标点按保真要求保留。 2. 依句意确定句内重音、轻重和转折落点；只强调会改变对象、态度或话语行动的词，不按标点机械重读。 3. 在继承的稳定声音身份锚点内，按实际意图调节当句音量、相对音高、气息、咬字、语速与必要的临时质感；保护已绑定的稳定音色，不逐句重选声音身份。细节与人物身体状态、距离、环境及声场相容；不以抽象“有感情地说”替代发声过程。 4. 标清停连的位置、时长影响及原因：气口、犹豫、受抑、抢接、打断、拖音或被环境压住。按刺激实际到达并被听者察觉的时刻安排反应；听者可以在说话者尚未说完时已听见并开始反应，也可以依据源稿在句中抢接或打断，不把台词结束设为通用反应门槛。 5. 让发声动作与表演/身体状态协调，区分谁在说、谁在听、观众听到什么。新增停顿、抢接或反应改变时间时，把实际顺序与重叠返回 timing 核算；不把雨声等持续底层环境重复计时。 语气、重音、音量、停顿与身体动作写在台词引号外，台词本身不重写、不润色、不把导演解释塞进引号。若本任务是格式整理，保留原有说法与时长，只整理位置。 稳定身份如只有文字设定，就沿已知锚点设计当句变化并说明真实声音参考尚未提供；有已完成对白音轨时按其实际授权安排既有音轨，不把音轨再当待生成台词，也不因临场表演而改写锁定对白。返回逐句发声意图、继承的身份锚点、重音/转折、声音参数、明确停连或抢接位置及对表演/预算的影响，交主 Skill 第七步与同一镜头描述；performance 接收其身体状态，sound 接收声源和空间层次，timing 只核算真实新增时间。 本地取法参考 RADA Voice Workshop 关于气息、音高、音量、共鸣与咬字等发声维度的训练内容，按本项目的导演提示需要改写为可观察、可聆听的指令；不把训练维度当成固定表演配方，也不以单一“自然口语”覆盖用户锁定的声口。
Read the whole file at its exact version.
How to install
mdr add laohuad/laohu-creative-skills/laohu-video-voice@sha256:7d0b7670bf780c34The line at the top of this page pins the label git:20261106.42593f7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_uazyffqguowzyhnb)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Nov 6, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3002 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
laohuad/laohu-creative-skills · 7 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uazyffqguowzyhnb GET https://markdownregistry.com/api/v1/resolve?ref=laohuad/laohu-creative-skills/laohu-video-voice GET https://markdownregistry.com/api/v1/blob/7d0b7670bf780c343be96fd1d026e9b9345fb27557dcedd51ab93558ab44b9c3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.