adobe-resize-photos-and-videos

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Adobe Resize Photos and Videos

Adobe 照片与视频调整大小

Resizes images or videos to user-specified dimensions, aspect ratio, or named size. For social media platform sets (Instagram, TikTok, etc.) → use the

adobe-create-social-variations

skill instead.

将图像或视频调整为用户指定的尺寸、宽高比或命名尺寸。如需针对社交媒体平台套装（Instagram、TikTok等）调整，请使用

adobe-create-social-variations

技能。

Tool Reference

工具参考

Step	Tool	Notes
Open file picker	`asset_add_file`	Returns `presignedAssetUrl` , `assetId` , and `mediaType`
Find asset in CC	`asset_search`	Re-stage result via `asset_add_file` for image; use `id` directly for video
Render PSD/AI	`document_render_vector`	Converts to JPEG before resize
Resize image	`image_crop_and_resize`	One call per dimension; `reframe` by default
Preview outputs	`asset_preview_file`	All outputs in a single call
Upload to CC (start)	`asset_initialize_file_upload`	First call in block upload pipeline
Upload to CC (finish)	`asset_finalize_file_upload`	Second call; returns presigned CC URL for board
Create Firefly board	`create_firefly_board`	Pass `import_adobe_storage` with finalize URL
Resize video	`video_resize`	Returns `statusId` for polling
Poll video resize	`resizeVideoPoll`	Deferred tool — load before calling

步骤	工具	说明
打开文件选择器	`asset_add_file`	返回 `presignedAssetUrl` 、 `assetId` 和 `mediaType`
在Creative Cloud中查找资源	`asset_search`	图片需通过 `asset_add_file` 重新托管结果；视频可直接使用 `id`
渲染PSD/AI文件	`document_render_vector`	调整大小前转换为JPEG格式
调整图片大小	`image_crop_and_resize`	每个尺寸调用一次；默认使用 `reframe` 模式
预览输出内容	`asset_preview_file`	单次调用即可预览所有输出
上传至Creative Cloud（开始）	`asset_initialize_file_upload`	分块上传流程中的首次调用
上传至Creative Cloud（完成）	`asset_finalize_file_upload`	第二次调用；返回用于面板的预签名Creative Cloud链接
创建Firefly面板	`create_firefly_board`	传入包含完成链接的 `import_adobe_storage` 参数
调整视频大小	`video_resize`	返回用于轮询的 `statusId`
轮询视频调整状态	`resizeVideoPoll`	延迟工具——调用前需先加载

Workflow

工作流程

Step 0 — Initialize Adobe Tools

步骤0 — 初始化Adobe工具

Call

adobe_mandatory_init

first. This returns file handling rules and tool routing guidance required for the rest of the workflow.

json

{ "skill_name": "adobe-resize-photos-and-videos", "skill_version": "1.0.1" }

首先调用

adobe_mandatory_init

。此调用会返回文件处理规则和工具路由指南，为后续工作流程提供必要支持。

json

{ "skill_name": "adobe-resize-photos-and-videos", "skill_version": "1.0.1" }

Step 1 — Entitlement Check

步骤1 — 权限检查

Now that

adobe_mandatory_init

confirmed that the "Adobe for creativity" connector is live, check which tools are available through the "Adobe for creativity" connector by cross checking against the Tool Reference table above.

在

adobe_mandatory_init

确认“Adobe for creativity”连接器已激活后，通过与上方工具参考表交叉核对，检查该连接器可使用的工具。

IMMEDIATE ACTION REQUIRED

需立即执行的操作

Step 1: If parameters are missing or ambiguous → run the multi-step intake (Step 2 below). Step 2: If no file is uploaded, run Step 3 (

asset_add_file({})

). Step 3: Detect image vs. video and route to the correct workflow (Step 5 Image/Video).

步骤1： 如果参数缺失或不明确 → 运行多步骤收集流程（下方步骤2）。 步骤2： 如果未上传文件，运行步骤3（

asset_add_file({})

）。 步骤3： 检测文件类型为图片还是视频，并路由至对应的工作流程（步骤5的图片/视频流程）。

Step 2 — Multi-Step Intake

步骤2 — 多步骤参数收集

Run this when the user hasn't provided complete parameters (type + dimensions + fit mode). Skip entirely if the user's message already contains all three.

Use

AskUserQuestion

to collect parameters step by step.

当用户未提供完整参数（类型+尺寸+适配模式）时运行此流程。如果用户消息中已包含全部三个参数，则可直接跳过。

使用

AskUserQuestion

逐步收集参数。

Step 2a — Type

步骤2a — 文件类型

AskUserQuestion([{
  question: "Photo or video?",
  type: "single_select",
  options: ["Photo", "Video"]
}])

AskUserQuestion([{
  question: "照片还是视频？",
  type: "single_select",
  options: ["照片", "视频"]
}])

Step 2b — Dimensions

步骤2b — 尺寸

If Photo (

multi_select

— user can pick one or more):

AskUserQuestion([{
  question: "Dimensions — select all you need",
  type: "multi_select",
  options: [
    "1080 × 1080 — Instagram square",
    "1080 × 1350 — Instagram portrait",
    "1080 × 1920 — Stories / Reels",
    "1920 × 1080 — YouTube / landscape",
    "1280 × 720 — YouTube thumbnail",
    "1200 × 675 — X / Twitter post",
    "1200 × 630 — Facebook / OG image",
    "1080 × 566 — LinkedIn post",
    "2560 × 1440 — YouTube banner",
    "3840 × 2160 — 4K / UHD",
    "400 × 400 — Profile / avatar",
    "2480 × 3508 — A4 print (300 dpi)",
    "Custom — I'll type it"
  ]
}])

If user includes "Custom" → follow up: "Enter your custom dimensions (e.g. 1500×800):"

If user selects multiple presets → run

image_crop_and_resize

once per dimension, using the same source URI and parameters each time. Preview all outputs together at the end.

If Video (

multi_select

— user can pick one or more):

AskUserQuestion([{
  question: "Dimensions — select all you need",
  type: "multi_select",
  options: [
    "1080 × 1920 — Reels / TikTok / Stories",
    "1920 × 1080 — YouTube / landscape",
    "1080 × 1080 — Square post",
    "1280 × 720 — YouTube 720p",
    "3840 × 2160 — 4K / UHD",
    "854 × 480 — SD / 480p",
    "Custom — I'll type it"
  ]
}])

If user selects multiple video presets → submit a separate

video_resize

job per dimension, poll each to completion, preview all outputs together.

如果是照片（

multi_select

——用户可选择一个或多个）：

AskUserQuestion([{
  question: "尺寸——选择所有需要的选项",
  type: "multi_select",
  options: [
    "1080 × 1080 — Instagram正方形",
    "1080 × 1350 — Instagram竖版",
    "1080 × 1920 — 快拍/短视频",
    "1920 × 1080 — YouTube/横版",
    "1280 × 720 — YouTube缩略图",
    "1200 × 675 — X/Twitter帖子",
    "1200 × 630 — Facebook/OG图片",
    "1080 × 566 — LinkedIn帖子",
    "2560 × 1440 — YouTube横幅",
    "3840 × 2160 — 4K/UHD",
    "400 × 400 — 头像/个人资料图",
    "2480 × 3508 — A4打印（300 dpi）",
    "自定义——我将手动输入"
  ]
}])

如果用户选择“自定义” → 跟进提问：“输入你的自定义尺寸（例如1500×800）：”

如果用户选择多个预设尺寸 → 针对每个尺寸调用一次

image_crop_and_resize

，每次使用相同的源URI和参数。最后统一预览所有输出内容。

如果是视频（

multi_select

——用户可选择一个或多个）：

AskUserQuestion([{
  question: "尺寸——选择所有需要的选项",
  type: "multi_select",
  options: [
    "1080 × 1920 — 短视频/TikTok/快拍",
    "1920 × 1080 — YouTube/横版",
    "1080 × 1080 — 正方形帖子",
    "1280 × 720 — YouTube 720p",
    "3840 × 2160 — 4K/UHD",
    "854 × 480 — 标清/480p",
    "自定义——我将手动输入"
  ]
}])

如果用户选择多个视频预设尺寸 → 针对每个尺寸提交单独的

video_resize

任务，轮询每个任务直至完成，最后统一预览所有输出内容。

Step 2c — Fit mode

步骤2c — 适配模式

If Photo (

single_select

AskUserQuestion([{
  question: "Fit mode",
  type: "single_select",
  options: [
    "Reframe — crop to fill",
    "Pad — letterbox, no crop",
    "Extract — isolate subject"
  ]
}])

If Video (

single_select

AskUserQuestion([{
  question: "Fit mode",
  type: "single_select",
  options: [
    "Letterbox — preserve ratio",
    "Crop — fill, no bars",
    "Stretch — force exact (distort)"
  ]
}])

如果是照片（

single_select

）：

AskUserQuestion([{
  question: "适配模式",
  type: "single_select",
  options: [
    "重新构图——裁剪填充",
    "添加黑边——留边不裁剪",
    "提取主体——隔离主体"
  ]
}])

如果是视频（

single_select

）：

AskUserQuestion([{
  question: "适配模式",
  type: "single_select",
  options: [
    "留边——保持比例",
    "裁剪——填充无黑边",
    "拉伸——强制适配（会变形）"
  ]
}])

Step 2d — Smart focus (Photo only)

步骤2d — 智能对焦（仅照片）

AskUserQuestion([{
  question: "Smart focus — where should the crop center?",
  type: "single_select",
  options: [
    "Subject",
    "Face / portrait",
    "Upper body",
    "Center (geometric)",
    "Named object — I'll describe it"
  ]
}])

If user selects "Named object" → follow up: "Describe the object (e.g. 'the red car', 'the logo'):"

AskUserQuestion([{
  question: "智能对焦——裁剪应聚焦于何处？",
  type: "single_select",
  options: [
    "主体",
    "人脸/肖像",
    "上半身",
    "中心（几何中心）",
    "指定对象——我将描述它"
  ]
}])

如果用户选择“指定对象” → 跟进提问：“描述该对象（例如‘红色汽车’、‘标志’）：”

Step 2e — Options (Photo only)

步骤2e — 附加选项（仅照片）

AskUserQuestion([{
  question: "Any additional options?",
  type: "multi_select",
  options: [
    "Batch — multiple images",
    "Output: JPEG",
    "Output: PNG"
  ]
}])

AskUserQuestion([{
  question: "是否有其他附加选项？",
  type: "multi_select",
  options: [
    "批量处理——多张图片",
    "输出格式：JPEG",
    "输出格式：PNG"
  ]
}])

Step 2f — Source (Video only)

步骤2f — 来源（仅视频）

AskUserQuestion([{
  question: "Where is the video?",
  type: "single_select",
  options: [
    "Upload from device",
    "From Creative Cloud"
  ]
}])

AskUserQuestion([{
  question: "视频来自何处？",
  type: "single_select",
  options: [
    "从设备上传",
    "来自Creative Cloud"
  ]
}])

Step 3 — Get the Source File

步骤3 — 获取源文件

Critical —
/mnt/user-data/uploads/
paths are NOT usable URLs. Even when the user has attached a file and it appears in context at a

/mnt/user-data/uploads/

path, you cannot pass this path to any Adobe tool. Call

asset_add_file()

to stage the file —

/mnt/user-data/uploads/

paths are not fetchable by Adobe tools.

WRONG  ❌  imageURI: "/mnt/user-data/uploads/photo.jpg"
WRONG  ❌  imageURI: "file:///mnt/user-data/uploads/photo.jpg"
CORRECT ✅  call asset_add_file() → use presignedAssetUrl from picker context

No file yet → open the picker immediately:

javascript

asset_add_file()

Detect type from returned

mediaType

```
image/*
```
→ IMAGE WORKFLOW
```
video/*
```
→ VIDEO WORKFLOW

重要提示 —
/mnt/user-data/uploads/
路径不可用作URL。即使用户已附加文件且在上下文显示为

/mnt/user-data/uploads/

路径，也不能将此路径传递给任何Adobe工具。请调用

asset_add_file()

托管文件——Adobe工具无法获取

/mnt/user-data/uploads/

路径的文件。

错误 ❌  imageURI: "/mnt/user-data/uploads/photo.jpg"
错误 ❌  imageURI: "file:///mnt/user-data/uploads/photo.jpg"
正确 ✅  调用asset_add_file() → 使用选择器上下文返回的presignedAssetUrl

尚未上传文件 → 立即打开选择器：

javascript

asset_add_file()

从返回的

mediaType

检测文件类型：

```
image/*
```
→ 图片工作流程
```
video/*
```
→ 视频工作流程

Step 4 — Resolve Target Dimensions

步骤4 — 解析目标尺寸

User says	Resolve to
`1920×1080` , `1920x1080`	width: 1920, height: 1080
`4K`	3840 × 2160
`HD` , `1080p`	1920 × 1080
`720p`	1280 × 720
`480p`	854 × 480
`A4` print	2480 × 3508 (300 DPI portrait)
`Letter` print	2550 × 3300 (300 DPI portrait)
`16:9` , `1:1` , `4:5` , `9:16`	ratio string → pass as `output: "16:9"`
`square`	`output: "1:1"`
Width only ( `800px wide` )	width: 800, use ratio string to maintain aspect

If no target was specified in the form AND none in the user's message → ask:

"What dimensions do you need? (e.g. 1920×1080, A4, 16:9)"

用户表述	解析结果
`1920×1080` , `1920x1080`	宽度: 1920, 高度: 1080
`4K`	3840 × 2160
`HD` , `1080p`	1920 × 1080
`720p`	1280 × 720
`480p`	854 × 480
`A4` 打印	2480 × 3508 (300 DPI竖版)
`Letter` 打印	2550 × 3300 (300 DPI竖版)
`16:9` , `1:1` , `4:5` , `9:16`	比例字符串 → 作为 `output: "16:9"` 传递
`square` （正方形）	`output: "1:1"`
仅指定宽度（ `800px宽` ）	宽度: 800, 使用比例字符串保持宽高比

如果表单中未指定目标尺寸且用户消息中也未提及 → 提问：

"你需要什么尺寸？（例如1920×1080、A4、16:9）"

IMAGE WORKFLOW

图片工作流程

Step 5 (Image) — Valid URI Sources

步骤5（图片）—— 有效URI来源

Only these work as

imageURI

```
presignedAssetUrl
```
from
```
asset_add_file()
```
✅
```
outputUrl
```
from a prior tool call ✅
Public HTTPS URL provided by user ✅

Not usable as

imageURI

```
/mnt/user-data/uploads/
```
paths ❌
```
renditionURL
```
from
```
asset_search
```
directly ❌
```
file://
```
URIs ❌

Source	Resolution
Uploaded file	`asset_add_file()` → `presignedAssetUrl`
CC storage asset	`asset_search` → re-stage via `asset_add_file()` → `presignedAssetUrl`
Prior tool output	Use `outputUrl` directly
PSD / AI file	`document_render_vector` (JPEG, 300 DPI) → `outputPresignedUrl`

仅以下来源可作为

imageURI

：

```
asset_add_file()
```
返回的
```
presignedAssetUrl
```
✅
之前工具调用返回的
```
outputUrl
```
✅
用户提供的公开HTTPS URL ✅

不可用作

imageURI

的来源：

```
/mnt/user-data/uploads/
```
路径 ❌
```
asset_search
```
直接返回的
```
renditionURL
```
❌
```
file://
```
URI ❌

来源	处理方式
上传的文件	`asset_add_file()` → `presignedAssetUrl`
Creative Cloud存储资源	`asset_search` → 通过 `asset_add_file()` 重新托管 → `presignedAssetUrl`
之前工具输出	直接使用 `outputUrl`
PSD / AI文件	`document_render_vector` （JPEG，300 DPI） → `outputPresignedUrl`

Step 6 (Image) — Fit Mode

步骤6（图片）—— 适配模式

Intent	Mode	Notes
"resize to WxH" / default	`reframe`	Largest crop at target ratio, centered — no distortion
"no cropping", "letterbox", "fit inside"	`pad`	Fills empty space with white
"isolate subject", "tight crop"	`extract`	Tight crop around detected region

Default:
reframe
. Change only when user is explicit.

⛔
fit: "extract"
is incompatible with an explicit
{ width, height }
— it stretches the image. Use a ratio string or omit
output
.

用户意图	模式	说明
"调整为宽×高" / 默认	`reframe`	目标比例下最大裁剪范围，居中——无变形
"不裁剪"、"留边"、"适配内部"	`pad`	空白区域填充白色
"隔离主体"、"紧密裁剪"	`extract`	围绕检测到的区域进行紧密裁剪

默认值：
reframe
。仅当用户明确要求时才更改。

⛔
fit: "extract"
与明确的
{ width, height }
参数不兼容——会导致图像拉伸。请使用比例字符串或省略
output
参数。

Step 7 (Image) — Call

image_crop_and_resize

步骤7（图片）—— 调用

image_crop_and_resize

javascript

image_crop_and_resize({
  imageURI: presignedAssetUrl,
  options: {
    output: { width: 1920, height: 1080 },  // or "16:9"
    fit: "reframe",
    focus: "subject",  // or "face", "upper_body", { prompt: "the car" }, { x:0.5, y:0.5 }
    quality: 7
  },
  outputFileType: "jpeg"  // or "png" if transparency needed
})
// result.outputUrl → use for preview or chaining

Focus guide:

```
"subject"
```
— default; full-body detection, landscapes, objects
```
"face"
```
— portraits, headshots
```
"upper_body"
```
— chest-up crops
```
{ prompt: "the logo" }
```
— named object from user's form input
```
{ x: 0.5, y: 0.5 }
```
— geometric center (no clear subject)

javascript

image_crop_and_resize({
  imageURI: presignedAssetUrl,
  options: {
    output: { width: 1920, height: 1080 },  // 或"16:9"
    fit: "reframe",
    focus: "subject",  // 或"face"、"upper_body"、{ prompt: "the car" }、{ x:0.5, y:0.5 }
    quality: 7
  },
  outputFileType: "jpeg"  // 如需透明背景则使用"png"
})
// result.outputUrl → 用于预览或链式调用

对焦指南：

```
"subject"
```
— 默认值；检测全身、风景、物体
```
"face"
```
— 肖像、头像
```
"upper_body"
```
— 胸部以上裁剪
```
{ prompt: "the logo" }
```
— 用户表单输入的指定对象
```
{ x: 0.5, y: 0.5 }
```
— 几何中心（无明确主体时）

Step 8 (Image) — Batch

步骤8（图片）—— 批量处理

If batch was selected in the form OR the user provided multiple files:

Call
```
asset_add_file()
```
for each file to get individual presigned URLs
Call
```
image_crop_and_resize
```
for each with the same parameters
Collect all
```
outputUrl
```
values
Call
```
asset_preview_file
```
with all outputs in a single call

Calls run sequentially in this environment. For >10 images, confirm with the user before starting.

Pagination across turns (batches >20): For large batches, the conversation context may fill before all images are processed, causing Claude to pause mid-batch. This is expected — not an error. When it happens:

State how many have been completed and how many remain (e.g. "20 / 24 done — say 'continue' for the rest")
Wait for the user to confirm before resuming
On resume, pick up from the next unprocessed image and continue to the end
Preview all outputs together only after the final image completes

如果表单中选择了批量处理，或用户提供了多个文件：

为每个文件调用
```
asset_add_file()
```
获取单独的预签名URL
为每个文件调用
```
image_crop_and_resize
```
，使用相同的参数
收集所有
```
outputUrl
```
值
单次调用
```
asset_preview_file
```
预览所有输出内容

在此环境中调用会按顺序执行。如果图片数量超过10张，请在开始前与用户确认。

跨轮次分页（批量超过20张）： 对于大规模批量处理，对话上下文可能在所有图片处理完成前就被填满，导致Claude在批量处理中途暂停。这是正常现象——并非错误。发生这种情况时：

告知用户已完成数量和剩余数量（例如“已完成20/24张——输入‘继续’以处理剩余部分”）
等待用户确认后再继续
继续处理时，从下一张未处理的图片开始，直至完成
仅在所有图片处理完成后统一预览所有输出内容

Step 9 (Image) — Preview + Deliver + Firefly Board

步骤9（图片）—— 预览 + 交付 + Firefly面板

javascript

asset_preview_file({
  assets: [
    { name: "photo_1920x1080.jpg", presignedAssetUrl: result.outputUrl },
    // all successful outputs
  ]
})

javascript

asset_preview_file({
  assets: [
    { name: "photo_1920x1080.jpg", presignedAssetUrl: result.outputUrl },
    // 所有成功的输出内容
  ]
})

Save to CC + Create Firefly Board

保存至Creative Cloud + 创建Firefly面板

After preview, upload each output to CC storage using the block upload pipeline (

asset_initialize_file_upload

→ PUT chunk →

asset_finalize_file_upload

Then call the firefly board tool with the final output urls:

javascript

create_firefly_board({
  import_adobe_storage: [
    final_output_url_1,
    final_output_url_2,
    // ...
  ]
})

✅ Confirmed working (Stage):
import_adobe_storage
with presigned URLs from
asset_finalize_file_upload
successfully populates boards.
❌ Does not work:
import_generic_assets
with CC URNs (
urn:aaid:sc:US:...
) — USS indexing lag causes blank boards.
If board creation fails or the URL is malformed, omit the board link (retrying does not help).

Post the completion summary after the board step:

✅ Done! [N] image(s) resized and ready.

📥 Download:
• resized_1920x1080.jpg → <cc_storage_url>
[list individually if N ≤ 3, or single folder link if N > 3]

🎨 View in Firefly Board → <board_url>   ← omit if board creation failed

预览后，使用分块上传流程（

asset_initialize_file_upload

→ PUT分块 →

asset_finalize_file_upload

）将每个输出内容上传至Creative Cloud存储。

然后调用Firefly面板工具，传入最终输出链接：

javascript

create_firefly_board({
  import_adobe_storage: [
    final_output_url_1,
    final_output_url_2,
    // ...
  ]
})

✅ 已确认可正常工作（测试阶段）： 使用
asset_finalize_file_upload
返回的预签名URL传入
import_adobe_storage
可成功填充面板。
❌ 无法工作： 使用Creative Cloud URN（
urn:aaid:sc:US:...
）传入
import_generic_assets
——USS索引延迟会导致面板空白。
如果面板创建失败或链接格式错误，请省略面板链接（重试无济于事）。

完成面板步骤后发布完成总结：

✅ 完成！已调整[N]张图片大小，可随时使用。

📥 下载：
• resized_1920x1080.jpg → <cc_storage_url>
[N≤3时逐个列出，N>3时提供单个文件夹链接]

🎨 在Firefly面板中查看 → <board_url>   ← 面板创建失败时省略

VIDEO WORKFLOW

视频工作流程

Step 5 (Video) — Get Asset ID

步骤5（视频）—— 获取Asset ID

Video tools require

assetId

, not a URL.

Source	How
Upload via `asset_add_file`	Use returned `assetId`
CC storage	`asset_search` with `filters.mediaType: "video/mp4"` → use asset `id`

视频工具需要

assetId

，而非URL。

来源	操作方式
通过 `asset_add_file` 上传	使用返回的 `assetId`
Creative Cloud存储	使用 `asset_search` 并设置 `filters.mediaType: "video/mp4"` → 使用资源 `id`

Step 6 (Video) — Common Targets

步骤6（视频）—— 常见目标尺寸

Name	Dimensions
4K / UHD	3840 × 2160
1080p / HD	1920 × 1080
720p	1280 × 720
480p	854 × 480
Vertical 9:16	1080 × 1920
Square 1:1	1080 × 1080

名称	尺寸
4K / UHD	3840 × 2160
1080p / HD	1920 × 1080
720p	1280 × 720
480p	854 × 480
竖版9:16	1080 × 1920
正方形1:1	1080 × 1080

Step 7 (Video) — Call

video_resize

步骤7（视频）—— 调用

video_resize

⚠️
resizeVideoPoll
is a deferred tool — load it first before attempting to poll. Direct calls without loading will fail with "not loaded" error.

javascript

video_resize({
  assetId: videoAssetId,
  width: targetW,
  height: targetH,
  mode: "letterbox"  // default; see mode table below
})
// Returns { jobStatus: "pending", statusId }

Mode — use exact API values (not user-facing labels):

User says	API value	Behavior
"fit", "preserve ratio", "letterbox"	`"letterbox"`	Preserves ratio, adds black bars (default)
"fill", "crop to fill", "no bars"	`"crop"`	Crops edges to fill target exactly
"stretch", "force exact"	`"stretch"`	Distorts to exact target

ℹ️ Auto-reframe for video is not available in Claude yet, but new tools are being added all the time. If you need more control, try using Adobe Premiere.

Polling: load the deferred tool

resizeVideoPoll

before calling it — direct calls fail with "not loaded".

javascript

// Step 1: load the deferred tool resizeVideoPoll
// Step 2: poll until complete
resizeVideoPoll({ statusId })
// Repeat until jobStatus === "completed"
// Show progress % to user while waiting

⚠️
resizeVideoPoll
是延迟工具——调用前需先加载。未加载直接调用会返回“未加载”错误。

javascript

video_resize({
  assetId: videoAssetId,
  width: targetW,
  height: targetH,
  mode: "letterbox"  // 默认值；见下方模式表
})
// 返回 { jobStatus: "pending", statusId }

模式——使用精确的API值（而非用户友好标签）：

用户表述	API值	行为
"适配"、"保持比例"、"留边"	`"letterbox"`	保持比例，添加黑边（默认值）
"填充"、"裁剪填充"、"无黑边"	`"crop"`	裁剪边缘以完全适配目标尺寸
"拉伸"、"强制适配"	`"stretch"`	变形以完全适配目标尺寸

ℹ️ 目前Claude中暂不支持视频自动重新构图，但新工具正在持续添加中。如需更多控制，请尝试使用Adobe Premiere。

轮询： 调用前先加载延迟工具

resizeVideoPoll

——直接调用会返回“未加载”错误。

javascript

// 步骤1：加载延迟工具resizeVideoPoll
// 步骤2：轮询直至完成
resizeVideoPoll({ statusId })
// 重复调用直至jobStatus === "completed"
// 等待期间向用户显示进度百分比

Step 8 (Video) — Preview + Deliver + Firefly Board

步骤8（视频）—— 预览 + 交付 + Firefly面板

If polling succeeds and returns

outputUrl

, upload to CC storage via the block upload pipeline (

asset_initialize_file_upload

→ PUT →

asset_finalize_file_upload

) to get a presigned URL, then:

javascript

asset_preview_file({
  assets: [{ name: "resized_video.mp4", presignedAssetUrl: result.outputUrl }]
})

create_firefly_board({
  import_adobe_storage: [ presignedAssetUrl_from_finalize ]
})

✅ Pass
import_adobe_storage
with the finalize presigned URL. If board creation fails, omit the link.

✅ Done! Video resized to [WxH].

📥 Download → <cc_storage_url>

🎨 View in Firefly Board → <board_url>   ← omit if board creation failed

If polling is unavailable → skip preview, deliver the CC storage fallback message from Step 7.

如果轮询成功并返回

outputUrl

，通过分块上传流程（

asset_initialize_file_upload

→ PUT →

asset_finalize_file_upload

）上传至Creative Cloud存储以获取预签名URL，然后：

javascript

asset_preview_file({
  assets: [{ name: "resized_video.mp4", presignedAssetUrl: result.outputUrl }]
})

create_firefly_board({
  import_adobe_storage: [ presignedAssetUrl_from_finalize ]
})

✅ 将
import_adobe_storage
与完成步骤的预签名URL一起传递。如果面板创建失败，请省略链接。

✅ 完成！视频已调整为[宽×高]。

📥 下载 → <cc_storage_url>

🎨 在Firefly面板中查看 → <board_url>   ← 面板创建失败时省略

如果轮询不可用 → 跳过预览，使用步骤7中的Creative Cloud存储备用消息交付。

Error Handling

错误处理

Error	Action
`/mnt/user-data/uploads/` or `file://` passed as URI	Stop. Call `asset_add_file()` first.
Image too large after resize	Re-run with `quality: 5`
Video `assetId` not found	Re-upload via `asset_add_file`
Source too small for target	Warn user upscaling won't add detail; proceed if confirmed
Invalid `video_resize` mode	API only accepts `"letterbox"` , `"crop"` , or `"stretch"` — `"fit"` and `"fill"` will be rejected.
`extract` + `{W,H}` → stretching	Switch to `reframe`
No dimensions given	Render form or ask explicitly before calling any tool
Unsupported format	Ask user to export as JPG/PNG (images) or MP4 (video)
`resizeVideoPoll` not loaded / unavailable	Known gap in current connector. Skip polling. Tell user to check CC Files for output.

错误	操作
将 `/mnt/user-data/uploads/` 或 `file://` 作为URI传递	停止操作。先调用 `asset_add_file()` 。
调整大小后图片过大	使用 `quality: 5` 重新运行
未找到视频 `assetId`	通过 `asset_add_file` 重新上传
源文件尺寸小于目标尺寸	警告用户放大不会增加细节；用户确认后再继续
`video_resize` 模式无效	API仅接受 `"letterbox"` 、 `"crop"` 或 `"stretch"` —— `"fit"` 和 `"fill"` 会被拒绝。
`extract` + `{宽,高}` → 拉伸	切换为 `reframe` 模式
未提供尺寸	在调用任何工具前，渲染表单或明确提问
不支持的格式	请用户导出为JPG/PNG（图片）或MP4（视频）
`resizeVideoPoll` 未加载/不可用	当前连接器的已知问题。跳过轮询。告知用户查看Creative Cloud文件获取输出内容。

Common Dimension Reference

常见尺寸参考

Use Case	Dimensions
Full HD / web hero	1920 × 1080
4K	3840 × 2160
Web thumbnail	1280 × 720
Square	1080 × 1080
A4 print (300 DPI)	2480 × 3508
US Letter print (300 DPI)	2550 × 3300
Blog featured image	1200 × 630
Email header	600 × 200
Avatar / profile	400 × 400
Instagram portrait	1080 × 1350
Stories / Vertical	1080 × 1920

使用场景	尺寸
全高清/网页横幅	1920 × 1080
4K	3840 × 2160
网页缩略图	1280 × 720
正方形	1080 × 1080
A4打印（300 DPI）	2480 × 3508
US Letter打印（300 DPI）	2550 × 3300
博客特色图片	1200 × 630
邮件标题	600 × 200
头像/个人资料	400 × 400
Instagram竖版	1080 × 1350
快拍/竖版	1080 × 1920

Assets

资源

assets/intake-form.html

— Interactive intake form for resize parameters. Render at the start of any resize workflow where parameters are missing or ambiguous. Covers photo (target size, fit mode, smart focus, batch, output format) and video (target size, fit mode, source).

assets/intake-form.html

— 用于调整大小参数的交互式收集表单。当调整大小工作流程中参数缺失或不明确时，在开始时渲染此表单。涵盖照片（目标尺寸、适配模式、智能对焦、批量处理、输出格式）和视频（目标尺寸、适配模式、来源）的参数收集。

adobe-resize-photos-and-videos

Original

Translation

Adobe Resize Photos and Videos

Adobe 照片与视频调整大小

Tool Reference

工具参考

Workflow

工作流程

Step 0 — Initialize Adobe Tools

步骤0 — 初始化Adobe工具

Step 1 — Entitlement Check

步骤1 — 权限检查

IMMEDIATE ACTION REQUIRED

需立即执行的操作

Step 2 — Multi-Step Intake

步骤2 — 多步骤参数收集

Step 2a — Type

步骤2a — 文件类型

Step 2b — Dimensions

步骤2b — 尺寸

Step 2c — Fit mode

步骤2c — 适配模式

Step 2d — Smart focus (Photo only)

步骤2d — 智能对焦（仅照片）

Step 2e — Options (Photo only)

步骤2e — 附加选项（仅照片）

Step 2f — Source (Video only)

步骤2f — 来源（仅视频）

Step 3 — Get the Source File

步骤3 — 获取源文件

Step 4 — Resolve Target Dimensions

步骤4 — 解析目标尺寸

IMAGE WORKFLOW

图片工作流程

Step 5 (Image) — Valid URI Sources

步骤5（图片）—— 有效URI来源

Step 6 (Image) — Fit Mode

步骤6（图片）—— 适配模式

Step 7 (Image) — Call image_crop_and_resize

步骤7（图片）—— 调用image_crop_and_resize

Step 8 (Image) — Batch

步骤8（图片）—— 批量处理

Step 9 (Image) — Preview + Deliver + Firefly Board

步骤9（图片）—— 预览 + 交付 + Firefly面板

Save to CC + Create Firefly Board

保存至Creative Cloud + 创建Firefly面板

VIDEO WORKFLOW

视频工作流程

Step 5 (Video) — Get Asset ID

步骤5（视频）—— 获取Asset ID

Step 6 (Video) — Common Targets

步骤6（视频）—— 常见目标尺寸

Step 7 (Video) — Call video_resize

步骤7（视频）—— 调用video_resize

Step 8 (Video) — Preview + Deliver + Firefly Board

步骤8（视频）—— 预览 + 交付 + Firefly面板

Error Handling

错误处理

Common Dimension Reference

常见尺寸参考

Assets

资源

Step 7 (Image) — Call
`image_crop_and_resize`

步骤7（图片）—— 调用
`image_crop_and_resize`

Step 7 (Video) — Call
`video_resize`

步骤7（视频）—— 调用
`video_resize`