omniailab-promo-video-deconstruct SKILL.md skillA
omniailab-promo-video-deconstruct from tomatoparkdao/omniailab-ai-director is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tomatoparkdao/omniailab-ai-director/omniailab-promo-video-deconstruct@v2.4.0Pins v2.4.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tomatoparkdao/omniailab-ai-director
- Path
references/promo/video-deconstruct/SKILL.md- Versions recorded
- 5
- Latest version
- v2.4.0, committed Oct 16, 2026
- First version recorded
- Sep 29, 2026
- Size
- 6,796 bytes
- Repository stars
- 65
- License
- MIT
视频拆解与逐镜复刻 —— 宣传片线方向之一：拆解用户提供的视频或关键帧，提取镜头顺序、运镜、光影与节奏证据，编译为逐镜复刻提示词。.
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
> **在本 skill 中的位置**：拆解用户提供的视频或关键帧，提取镜头顺序、运镜、光影与节奏证据，编译为逐镜复刻提示词。由**宣传片线总调度** `references/PROMO SKILL.md` 在判定为该方向后接入。 > **生成口径**：提示词编译完成后，统一在 **OmniAiLab 画布** 中选择 **MiniMax H3** 生成视频；图像与资产类提示词仍按主线层级执行（`references/LIRA SKILL.md`／`references/STYLE SKILL.md`／`references/ASSET-SYSTEM SKILL.md`／`references/PROMPT-DOCTRINE SKILL.md`）。 > **与主干的关系**：本文件是宣传片线的方向细则，**不改变 P0→P6 主干与确认门禁**；涉及资产、表演、情绪、站位与光学时照常调用主线对应层。 > **暂停点**：素材与文字确认 → 方向与风格确认 → 提示词确认 → 生成 → 验收；每一步都等创作者确认后再继续，**不得一次跑完**。 > **触发词**：视频复刻／结构保留重制／提示词反推／逐镜分析／视频拆解 # 视频拆解与逐镜复刻 以证据为先：先读视频和关键帧，再写结论与复刻合同。不要把“分析”当作直接生成的替代品，也不要把截图推测说成已读取的视频事实。 ## 输入与证据链 1. 用户上传视频时，先用 `媒体分析步骤` 读取元信息和语义；记录时长、画幅、分辨率、主体、场景、动作、镜头、光影、节奏和可听声音。 2. 语义分析失败、过粗，或用户要求精细复刻时，用 `媒体拼接步骤` 建立高密度关键帧拼图：15 秒内至少 10–12 帧；更长视频按可读的连续片段分拼图；快动作、转场密集时提高到约每秒一帧。拼图容量不得小于实际抽帧数。 3. 将关键帧拼图写入画布；完整 Markdown 报告也写入画布，并用 `来源节点关联` 关联关键帧。只有截图或文字描述时，明确标注哪些动作、声音或时序仅为推测。 4. 仅给 URL 时，不承诺下载外部视频；请用户上传视频、关键帧或足够的文字描述。 ## 拆解报告 用户未指定重点时，默认深拆角色/主体、剧情/动作、镜头/运镜、光影/风格与节奏；已指定时不重复问。报告包含： 1. 元信息、分析依据与一句话定性； 2. 关键帧数量、拼图数量和覆盖时间； 3. 角色与视觉锚点、场景、动作时间线、镜头、光影色彩、风格材质、剪辑节奏、声音； 4. 可复刻事实、不可确定项和风险（人脸、手部、多人身份、文字、快速运动或风格漂移）； 5. H3 复刻计划、统一约束和自检结论。 为每个主体保留同一名称与可见识别点；用可观察证据描述景别、机位、运镜、光源、材质和动作，不用“电影感”“高级”等空词代替分析。 …
Read the whole file at its exact version.
How to install
mdr add tomatoparkdao/omniailab-ai-director/omniailab-promo-video-deconstruct@sha256:02aa45fe037b44c9The line at the top of this page pins the label v2.4.0, 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_gomolwywtn3xtja3)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 29, 2026 and Oct 16, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.4.0 latest | 2026-10-16 | 5b75e76 | 6,796 B | A | view · diff |
| v2.3.0 | 2026-10-07 | ca746c2 | 6,796 B | A | view · diff |
| v2.2.1 | 2026-10-03 | 306476e | 6,796 B | A | view · diff |
| v2.0.35 | 2026-09-29 | 4da6627 | 6,797 B | A | view · diff |
| v2.0.34 | 2026-09-29 | 7636978 | 6,797 B | A | view |
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 (6796 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
tomatoparkdao/omniailab-ai-director · 65 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gomolwywtn3xtja3 GET https://markdownregistry.com/api/v1/resolve?ref=tomatoparkdao/omniailab-ai-director/omniailab-promo-video-deconstruct GET https://markdownregistry.com/api/v1/blob/02aa45fe037b44c9316d9f00b04c98a063c8324e6368fe3271e7ba9bdfbe2f72
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.