Sandgrouse/adobe-express-dev-skill / skills/adobe-express-document-manipulation
adobe-express-document-manipulation
VerifiedCreate and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.
Adobe Express Document Manipulation Skill
This skill guides you in planning and executing document operations in the document sandbox, from simple text insertion to complex multi-element layouts.
When to Use This Skill
- Planning what content to insert (shapes, text, images, audio, video)
- Sequencing multiple document operations safely
- Understanding Document SDK APIs and type signatures
- Designing insertion workflows triggered from UI actions
- Troubleshooting document operation failures
Quick Start
Common Document Operations
All operations run in document sandbox using Document SDK:
Text insertion:
- Query: "How do I create text with custom font size and color?"
- Relevant:
text.createText(),editor.context.insertionParent
Shape insertion:
- Query: "Create a filled rectangle at specific position"
- Relevant:
editor.createRectangle(), dimension and fill APIs
Image insertion (from iframe runtime):
- Query: "Insert image blob into current page"
- Relevant:
addOnUISdk.app.document.addImage(blob)
Audio/Video insertion (from iframe runtime):
- Query: "How do I add audio or video to the document?"
- Relevant:
addAudio()(title mandatory),addVideo()(title optional)
Sequence Operations Safely
- Identify insertion parent: Are you adding to current page or current selection?
- Plan async operations: Fetch resources before document edits
- Handle errors: Wrap in try-catch, provide user feedback
- Test ordering: Some operations depend on prior state
Query Official MCP for Details
When implementing, ask MCP:
- "What's the current signature for
editor.createRectangle()?" - "What properties does
RectangleNodeexpose?" - "What's the type of
editor.context.insertionParent?"
Document Operation Patterns
Insert Text
- Get insertion context:
editor.context.insertionParent - Create text node with
text.createText() - Set properties (fontSize, fill, transform, etc.)
- Append to parent with
children.append()
Insert Shape
- Create shape with
editor.createRectangle()(or other shape) - Set dimensions and position
- Set fill and stroke properties
- Append to parent
Insert Media
- (From iframe) Fetch blob from URL or user input
- Call
addOnUISdk.app.document.addImage/Audio/Video(blob, options) - For audio: title is mandatory
- For video: title is optional
Common Pitfalls
- No insertion parent: Check
editor.context.insertionParentexists - DOM access in sandbox: All DOM operations fail in sandbox; use iframe runtime instead
- Missing title on audio: Audio requires title parameter; video does not
- Async before append: Fetch data before editing to avoid race conditions
Skill Handoffs
Pass to other skills when:
- UI button that triggers insertion → adobe-express-spectrum-ui-ux
- Fetching media from OAuth provider → adobe-express-oauth-authentication
- Paid feature gating → adobe-express-monetization
- Manifest and runtime questions → adobe-express-core
References
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies. | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |
| meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要". | Stars: 108k | Updated | Claude CodeCodex | Verified | Install |