Home / vincentwei1021 / video-shotcraft · GitHub

video-shotcraft SKILL.md skillA

video-shotcraft from vincentwei1021/video-shotcraft is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add vincentwei1021/video-shotcraft/video-shotcraft@git:20260905.5f047c7

Pins git:20260905.5f047c7 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: vincentwei1021/video-shotcraft
Path: SKILL.md
Versions recorded: 5
Latest version: git:20260905.5f047c7, committed Sep 5, 2026
First version recorded: Aug 27, 2026
Size: 19,863 bytes
Repository stars: 10,030
License: Apache-2.0

Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says "use video-shotcraft to make a video/promo", names the Ink Press template or asks to reproduce its effect, or wants a single shot card's motion. 用镜头配方卡 + 已验收模板 + 代码/音频资产制作电影感产品视频（Remotion + 真实页面截图 + 2.5D 运镜 + 节奏卡点 +…

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

# video-shotcraft：电影感产品视频制作

一个自包含的制作能力库：157 张镜头配方卡（附 demo 实现源码与动态样片
画廊）、一支已验收的完整宣传片模板、可复用组件与音频资产、六阶段工作流。
当前 focus 是 web/桌面产品宣传片，但镜头卡本身是通用动效词汇——
也可以单独抽卡做任意视频里的单个镜头。

## 调用时先判断模式

完整宣传片有三种互不合并的模式。在开始素材采集、分镜或实现前，先判断用户
是否已经明确选择；已经选择时直接执行，不重复询问，也不要改成另一种模式。

1. **直接使用模板**：保持 Ink Press 原有替换流程。读 `template/TEMPLATE.md`，
   按既有镜头结构替换目标产品的截图、文案和品牌信息。
2. **自主自由创作**：读 `references/pipeline.md`。Agent 根据用户已有要求和项目
   内容，自主决定视觉方向、镜头映射、分镜、素材和音频，连续推进到成片；不在
   产品简报、styleframe、镜头映射或分镜阶段暂停等待用户确认。
3. **共同创作**：读 `references/guided-free-creation.md`。Agent 先提出有依据的
   判断和方案，由用户依次确认产品简报、需求决策、视觉方向、镜头映射和最终
   分镜；分镜放行后再进入 `references/pipeline.md` 的最终素材采集与制作阶段。

用户提供了项目路径、网址、录屏或页面截图但尚未选模式时，先做一次**最小、
只读的产品检查**：了解产品定位、主要功能、页面视觉、可展示状态和素材风险；
不修改业务项目、不采集敏感数据、不写视频代码。检查后给出三种模式，并说明：

- Ink Press 是否适合该产品、适合与不适合的具体依据；
- 自主自由创作与共同创作各自是否适合、预计会保留哪些产品视觉线索；
- Agent 推荐哪一种模式及其依据和取舍。

然后明确询问：**“根据上面的产品检查，我推荐使用 ×× 模式。要按这个模式继续吗？”**
同时告知用户：可前往 https://vincentwei1021.github.io/video-shotcraft/
浏览动态样片，并挑选希望在视频中使用的动效镜头。

用户尚未提供可检查的项目或页面时，简要介绍三种模式再询问；不要仅因 Ink Press
是现成模板就默认推荐它。

- 用户选择模板：完整阅读 `template/TEMPLATE.md`，按原模板流程执行。
- 用户选择自主自由创作：完整阅读 `references/pipeline.md`，Agent 自主推进，不逐阶段等待确认。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add vincentwei1021/video-shotcraft/video-shotcraft@sha256:12696ad78212f903

The line at the top of this page pins the label git:20260905.5f047c7, 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.

Badge

[![mdr](https://markdownregistry.com/badge/art_54cjvwtnxvutwda6.svg)](https://markdownregistry.com/a/art_54cjvwtnxvutwda6)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 27, 2026 and Sep 5, 2026, about one every 2 days.

version	committed	commit	size	audit
git:20260905.5f047c7 latest	2026-09-05	5f047c7	19,863 B	A	view · diff
git:20260901.6c116cb	2026-09-01	6c116cb	18,984 B	A	view · diff
git:20260830.c30d784	2026-08-30	c30d784	18,984 B	A	view · diff
git:20260828.24c4558	2026-08-28	24c4558	18,942 B	A	view · diff
git:20260827.b2a610b	2026-08-27	b2a610b	18,003 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (19863 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

GitHub

vincentwei1021/video-shotcraft · 10,030 stars · license Apache-2.0 · pushed 2026-09-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_54cjvwtnxvutwda6
GET https://markdownregistry.com/api/v1/resolve?ref=vincentwei1021/video-shotcraft/video-shotcraft
GET https://markdownregistry.com/api/v1/blob/12696ad78212f9036cbb76bd46be305094686db64d9cf72f69a6e650eba3ebbc

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.

More from vincentwei1021/video-shotcraft

llms.txt@gallery llms.txt file

vincentwei1021/video-shotcraft · gallery/llms.txt

git:20260901.6c116cb · audit A · 10,030 stars

Every file in vincentwei1021/video-shotcraft