Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

adobe-design-from-templateadobe 设计模板

Agent Skill

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

总安装

1,042

周安装

43

GitHub Stars

55

下载量

341
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:adobe-design-from-template(adobe 设计模板)
来源仓库:https://github.com/adobe/skills
仓库路径:skills/adobe-design-from-template
安装命令:
npx skills add https://github.com/adobe/skills --skill adobe-design-from-template
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/adobe/skills --skill adobe-design-from-template

简介

用于辅助界面设计、视觉规范和交互体验优化,适合生成 UI 方案或检查视觉一致性。

  • 支持根据产品场景整理页面结构、调整配色布局,并生成可分享的 Express 文档。
  • 使用时需结合品牌规范与用户任务,避免堆砌装饰元素;涉及页面改动时应通过预览检查文本溢出和响应式表现。
  • 安装命令:npx skills add https://github.com/adobe/skills --skill adobe-design-from-template。
  • 注意:需确认 Adobe 账户权限及模板使用范围,输出结果应人工复核后再部署。

SKILL.md

Adobe Design from Template

Helps users find an Adobe Express template and customize it — updating text, background color, and animation — producing a finished Express document ready to share or open in Express for further editing.


Tool Reference

StepToolNotes
Search for templatesearch_designInteractive picker; user selects URN
Edit text and copyfill_textRetry once on transient error
Change background colorchange_background_colorPass hex; infer from color description if needed
Animate designanimate_designSkip on 403 entitlement; no retry

Workflow

Step 0 — Initialize Adobe Tools

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

{ "skill_name": "adobe-design-from-template", "skill_version": "1.0.1" }

Step 1 — Entitlement Check

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.


Step 2 — Build the search query (don't ask questions first)

Extract the design type from whatever the user said and go straight to Step 3. Asking clarifying questions before showing templates creates friction; the picker lets users course-correct visually, which is faster.

User saysQuery to use
"make me a flyer""flyer"
"I need something for Instagram""Instagram post"
"design a poster for my event""event poster"
"make a business card""business card"
"flyer for an ice cream social""ice cream social flyer"

Step 3 — Search for a template

Call search_design:

{
  "generalQuery": "<design type from user prompt>",
  "pageSize": 24
}

This renders an interactive picker in the chat. The user taps a template to select it; the URN comes back automatically. If the user says "show more", call search_design again with the same query and increment startIndex by pageSize.


Step 4 — Confirm selection and offer edits

Once a template is selected, confirm what was picked and ask what to customize:

"Got it — you've selected [template name]. What would you like to change? - ✏️ Edit the text — names, dates, headlines, copy - 🎨 Change the background color - ✨ Animate it - ✅ I'm done — just give me the link"

The user may choose one, several, or none. Apply each in sequence, then loop back and ask if they want anything else before wrapping up.


Step 5 — Apply edits

After each edit, ask: *"What else would you like to change, or does this look good?"*

Edit text / copy

Call fill_text:

{
  "templateURN": "<URN>",
  "description": "<what to change and what to change it to>",
  "generalQuery": "<same, minus any PII>"
}

If the user hasn't specified what the text should say, ask before calling.

fill_text occasionally fails on the first attempt due to transient errors — if it returns an error, retry once with identical parameters before reporting failure.

Change background color

Call change_background_color:

{
  "templateOrDocumentURN": "<URN>",
  "backgroundColor": "<hex>",
  "description": "<e.g. change background to coral pink>",
  "generalQuery": "<same, minus any PII>"
}

If the user describes a color without a hex (e.g. "coral pink"), pick a reasonable hex value using your judgment.

Animate

Call animate_design:

{
  "templateOrDocumentURN": "<URN>",
  "description": "<animation style or intent>",
  "generalQuery": "<same, minus any PII>"
}

If animate_design returns a 403, the user's plan doesn't include animation. Skip it and note in the delivery: *"Animation isn't available on your current Adobe plan — the rest of your design is ready."* Retrying does not resolve a 403 entitlement — continue without retry.


Step 6 — Deliver

When the user is satisfied:

✅ Here's your finished design:

🎨 Template: [name]
[Edits applied, e.g. ✏️ Copy updated · 🎨 Background changed · ✨ Animated]

📎 Open in Express: [editor link]

Remind the user that the document is temporary (deleted after 12 hours) and they should open it in Express to save.


Coming soon

ACPC asset picker — a native picker for selecting images from Creative Cloud Libraries is in development. This skill will be updated when it ships.


Error handling

SituationAction
fill_text fails on first attemptRetry once with identical parameters
animate_design returns 403Skip; note entitlement limit in delivery
Any tool returns 401Ask user to re-authenticate via Adobe OAuth, then retry
No templates match queryTry a broader query
User hasn't selected a template yetDo not advance past the picker until a URN is returned; the URN is required for every subsequent tool call.
User skips all editsFine — deliver the template link as-is

Constraints

  • The workflow always begins with the template picker before any edits.
  • Template URNs come only from the picker — do not synthesise them.
  • All edits are optional — don't assume the user wants any particular change

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.23%
按下载量换算113

Claude

31.2%
按下载量换算106

Cursor

20.65%
按下载量换算70

Gemini CLI

10.01%
按下载量换算34

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills