Skip to content

armgit / hypit

Public Imported from GitHub
0

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

docs: clarify automatic agent production

rpone2e737e9aba8e
diff --git a/docs/quickstart.md b/docs/quickstart.md
index 11c53b95..7530b410 100644
--- a/docs/quickstart.md
+++ b/docs/quickstart.md
@@ -3,39 +3,24 @@ title: Quickstart for Agent users
description: Create, review and ship Hypit videos from a Coding Agent without writing SVML or SVS by hand.
---
-You do not need to know SVML, SVS, JavaScript or the command line to make a video with Hypit.
-You describe the result you want to a Coding Agent in ordinary language. The Agent uses the
-`/hypit` skill to prepare the project, inspect the available components, create or reconstruct the
-video program, and show you a reviewable Studio mock before anything billable is built.
-
-This page is for people who want to direct a video, not implement its source code. Hypit keeps the
-source editable and reproducible, but the Agent is responsible for writing and checking it. If you
-want to author SVML or SVS yourself, begin with the second page, [Script](./quickstart/script.md),
-after you understand the Agent workflow below.
+You do not need to know SVML, SVS, JavaScript or the command line. Describe your video in ordinary
+language; the Agent uses the `/hypit` skill to create or reconstruct it and provides a Studio mock
+for review before any paid Build.
## What you need
- A Coding Agent that can use skills, such as Claude Code or Codex.
-- A folder where the Agent can create your video project.
-- A reference video or your creative brief, if you are making an original video.
-
-You do not need to clone the Hypit repository. Install the reusable `/hypit` skill with the command
-in Step 1; the Agent can then prepare the Hypit Distribution for you. When a setup command is
-necessary, the Agent explains what it does and runs it in the project directory.
+- A reference video or a creative brief.
## 1. Install the Hypit skill
-Start a conversation with your Coding Agent in the folder where you want the project to live. Install
-the Hypit skill once with:
+Install the Hypit skill:
```bash
npx skills add hypit-ai/hypit -g
```
-The `-g` option makes the skill available to new Agent sessions in any project folder. You do not
-need to clone the Hypit repository or understand the files this command installs. Once the skill is
-available, start a new Agent conversation in your video project folder and continue with the steps
-below.
+Then start a Coding Agent anywhere; the Hypit skill is available globally.
## 2. Describe the video you want
@@ -73,10 +58,9 @@ and CapCut. Give each competitor a fair, concise summary of its strengths and we
result clear, energetic and suitable for a short social video.
```
-You can add any constraints that matter to you: target audience, duration, language, tone, brand
-colors, presenter, platform or aspect ratio. You do not need to decide which package, model,
-caption system or animation primitive implements those choices. The Agent turns the brief into a
-complete plan and asks follow-up questions only when a creative decision cannot be inferred safely.
+You can add constraints such as audience, duration, language, tone, brand colors, presenter, platform
+or aspect ratio. The Agent turns the brief into a complete plan and fills in production details from
+the information you provide.
## 3. Provide credentials when the Agent asks
@@ -96,17 +80,17 @@ the configured secure credential store.
## 4. Let the Agent do the production work
-After you approve the brief, the Agent works through the project without requiring you to write
-source code. The exact sequence depends on the video, but it generally includes:
+Once you submit the brief, the Agent works through the project automatically without requiring you to
+write source code. It does not ask questions during production; wait for the Studio mock. The exact
+sequence depends on the video, but it generally includes:
1. **Breaking the request into shots.** The Agent identifies the spoken sections, visual beats,
transitions, captions, B-roll opportunities and any persistent elements such as a ranking board.
2. **Analyzing the reference or brief.** For a clone, it uses Gemini and the available media tools to
inspect timing, composition, text, speakers and visual continuity. For an original, it resolves
the same questions from your description and the selected creative direction.
-3. **Asking narrow questions.** Instead of making you fill out a long form, it asks small,
- answerable questions such as which language to use, whether a product should appear on screen,
- or which host style to prefer.
+3. **Resolving details.** The Agent uses the reference, brief and observation results to settle
+ timing, language, product placement and host treatment automatically.
4. **Reading existing package declarations.** Before inventing an implementation, it checks the
components already available in the project and in Hypit's official packages. This lets it reuse
a caption, ranking, presenter, B-roll or rendering component when one already fits.
@@ -119,10 +103,6 @@ source code. The exact sequence depends on the video, but it generally includes:
composition in Studio, compares what it sees with the reference or brief, and repairs issues such
as incorrect timing, hierarchy, cropping, captions or visual density.
-This is why the workflow can feel like directing a small production team: the Agent handles shot
-cuts, Gemini analysis, package discovery, source authoring, mock comparison and repairs. You are
-not expected to open an editor, write a component, or run a sequence of build commands yourself.
-
## 5. Review the mock Studio
When the first pass is ready, the Agent opens a Studio mock for you. A mock is a review version: it
@@ -139,8 +119,7 @@ The board appears too late, the captions are too small on a phone, and the B-rol
while she is speaking. Please fix those issues and show me the mock again.
```
-The Agent edits the source, reruns the relevant checks and returns an updated mock. You review the
-result again; you do not need to locate the corresponding SVML line.
+The Agent edits the source, reruns the relevant checks and returns an updated mock.
## 6. Approve and submit the paid Build
diff --git a/docs/zh/quickstart.md b/docs/zh/quickstart.md
index ea46eaab..a7f54e84 100644
--- a/docs/zh/quickstart.md
+++ b/docs/zh/quickstart.md
@@ -3,27 +3,22 @@ title: 面向 Agent 使用者的快速开始
description: 无需手写 SVML 或 SVS,通过 Coding Agent 创建、审阅并交付 Hypit 视频。
---
-你不需要了解 SVML、SVS、JavaScript 或命令行,也可以使用 Hypit 制作视频。你只需用日常语言向 Coding Agent 描述想要的结果;Agent 会通过 `/hypit` skill 准备项目、检查可用组件、创作或复刻视频,并在任何需要付费的 Build 之前,为你打开一个可以审阅的 Studio mock。
-
-本页面向希望“指导视频创作”而不是亲自编写源码的用户。Hypit 生成的源码仍然可以编辑、复现和继续开发,但源码的编写与检查由 Agent 负责。如果你希望亲自编写 SVML 或 SVS,请先了解下面的 Agent 工作流,然后从第二个页面 [Script](./quickstart/script.md) 开始。
+你不需要了解 SVML、SVS、JavaScript 或命令行。用日常语言向 Coding Agent 描述视频,Agent 会通过 `/hypit` skill 完成创作或复刻,并在付费 Build 前提供 Studio mock 供你审阅。
## 你需要准备什么
- 一个能够使用 skill 的 Coding Agent,例如 Claude Code 或 Codex;
-- 一个允许 Agent 创建视频项目的文件夹;
-- 一条用于复刻的视频,或一份用于原创视频的创意简报;
-
-你不需要克隆 Hypit 仓库。先按第一步的命令安装可复用的 `/hypit` skill;之后 Agent 可以替你准备 Hypit Distribution。需要执行其他安装命令时,Agent 会先解释命令的作用,再在项目目录中完成操作。
+- 一条用于复刻的视频,或一份用于原创视频的创意简报。
## 第一步:安装 Hypit skill
-在准备存放项目的文件夹中打开 Coding Agent,然后先安装 Hypit skill:
+先安装 Hypit skill:
```bash
npx skills add hypit-ai/hypit -g
```
-`-g` 选项会让 skill 对任何项目文件夹中的新 Agent 会话都可用。你不需要克隆 Hypit 仓库,也不需要理解这条命令安装了哪些文件。skill 可用后,在视频项目文件夹中开启新的 Agent 对话,然后继续下面的步骤。
+然后在任意处启动 Coding Agent,Hypit skill 将全局可用。
## 第二步:描述你想制作的视频
@@ -54,7 +49,7 @@ npx skills add hypit-ai/hypit -g
请制作一条 ranking 视频。视频中有一个 ranking 板子,包含五行:左侧是 S、A、B、C、D 五个等级,每个等级使用不同的颜色;右侧用于摆放对应等级的图标。把 Hypit 排到 S 级,并解释它的优势;同时加入 Arcads、Higgsfield、Seedance 和 CapCut,对每个竞品给出公平而简洁的优点与缺点说明。整体要清晰、有活力,适合短视频平台。
```
-你还可以补充目标受众、时长、语言、语气、品牌色、主持人、发布平台或画幅比例等要求。你不需要决定这些要求由哪个 package、模型、字幕系统或动画原语实现。Agent 会把 brief 转换成完整计划;只有在某个创意决定无法安全推断时,才会提出简短的补充问题。
+你还可以补充目标受众、时长、语言、语气、品牌色、主持人、发布平台或画幅比例等要求。Agent 会把 brief 转换成完整计划,并自行补全制作所需的细节。
## 第三步:按 Agent 提示提供凭据
@@ -67,18 +62,16 @@ npx skills add hypit-ai/hypit -g
## 第四步:让 Agent 完成制作
-你确认 brief 后,Agent 会在不要求你编写源码的情况下推进项目。具体顺序会因视频而不同,但通常包括:
+收到 brief 后,Agent 会在不要求你编写源码的情况下自动推进项目。制作过程中不会询问任何问题,你只需等待 Studio mock。具体顺序会因视频而不同,但通常包括:
1. **拆分镜头。** Agent 识别口播段落、视觉节拍、转场、字幕、B-roll 机会,以及 ranking 板等需要持续保持的元素。
2. **分析参考视频或 brief。** 复刻路线会使用 Gemini 和可用的媒体工具检查节奏、构图、文字、说话人和视觉连续性;原创路线则根据你的描述和确定的创作方向回答同样的问题。
-3. **提出窄问题。** Agent 不会让你填写一张很长的表格,而是逐个询问容易回答的小问题,例如使用哪种语言、产品是否要出现在画面中,或更倾向哪一种主持人风格。
+3. **自行确定细节。** Agent 会根据参考视频、brief 和观察结果自动确定时机、语言、产品位置和主持人处理方式。
4. **读取现有 package 声明。** 在自行发明实现之前,Agent 会检查项目和 Hypit 官方 package 中已有的组件。如果已有合适的字幕、ranking、主持人、B-roll 或渲染组件,就直接复用。
5. **必要时编写新 package。** 如果确实缺少所需的视觉行为,Agent 会创建一个足够小、可复用的新组件,并记录它的使用方式。你不需要自行设计 package 接口。
6. **编写并检查源码。** Agent 会写出 SVML/SVS 源码,创建所需的 Run 配置,编译视频图,并修复发现的类型或布局问题。
7. **与 mock 对比。** 对尚未真正生成的素材使用 mock,随后在 Studio 中渲染完整构图;Agent 会把看到的结果与参考视频或 brief 对比,修复时机、层级、裁切、字幕和画面密度等问题。
-因此,这个流程更像是在指导一支小型制作团队:切分 shot、Gemini 分析、提出窄问题、查找 package、写源码、生成 mock、进行比对并修复,全部由 Agent 完成。你不需要打开编辑器、编写组件,也不需要自己执行一连串 Build 命令。
-
## 第五步:查看 mock Studio
第一版完成后,Agent 会为你打开 Studio mock。Mock 是审阅版本:尚未生成的媒体会使用确定性的临时素材代替,但真实的时序、布局、字幕、转场和 Track 关系都会保留。它要回答的是“这支视频是否成立”,而不是在你确认之前悄悄执行付费生成或最终渲染。
@@ -89,7 +82,7 @@ npx skills add hypit-ai/hypit -g
ranking 板出现得太晚,手机上字幕太小,而且主持人说话时被 B-roll 盖住了。请修复这些问题,再给我看一次 mock。
```
-Agent 会修改源码,重新执行相关检查,并返回更新后的 mock。你只需再次审阅,不需要自己寻找对应的 SVML 行。
+Agent 会修改源码、重新检查并返回更新后的 mock。
## 第六步:确认后提交付费 Build