MCP.Market

adobe-illustrator-integrations skill

by github·github/awesome-copilot·41k stars·MIT

Build, debug, package, and document Adobe Illustrator integrations: CEP extension panels, C++ SDK plug-ins (.aip), the coming UXP plugins, MCP servers that drive Illustrator, computer-use automation, and OS scripts (batch, PowerShell, bash, AppleScript) that run ExtendScript in Illustrator. Use when creating or fixing an Illustrator extension or plug-in, choosing between a script, extension, or plug-in, connecting an AI tool to Illustrator, automating Illustrator from the command line, or writing install and usage docs for an Illustrator tool someone will publish. Pairs with adobe-illustrator-scripting for the ExtendScript DOM.

A100/100content scan

Is the adobe-illustrator-integrations skill safe?

Clean: nothing in its files matched our rules. We read 5 files in the folder on 2026-11-05.

No findings.

Install the adobe-illustrator-integrations skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/github/awesome-copilot.git /tmp/awesome-copilot
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-copilot/skills/adobe-illustrator-integrations ~/.claude/skills/adobe-illustrator-integrations
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Adobe Illustrator Integrations

Guidance for everything that sits around an Illustrator script: the panel a user clicks, the native plug-in that adds a tool, the command line or AI agent that starts Illustrator work from outside, and the documentation that ships with it. For the Illustrator DOM itself (documents, layers, paths, colors, exports), use the adobe-illustrator-scripting skill.

When to Use This Skill

  • Choosing how to deliver an Illustrator feature: a script, a CEP extension, a C++ plug-in, a UXP plugin, an MCP server, or an OS automation script
  • Building or fixing a CEP extension panel (HTML, JavaScript, and an ExtendScript host)
  • Building or fixing a C++ plug-in (.aip) with the Illustrator SDK
  • Running .jsx scripts from batch, PowerShell, bash, Python, or AppleScript, including passing parameters and reading results
  • Building or reviewing an MCP server that lets an AI tool drive Illustrator
  • Working in Illustrator through a computer-use tool when no scripting route exists
  • Writing step-by-step instructions people follow by hand, or install and usage docs for an asset, script, extension, or plug-in someone will publish
  • Organizing the files of an Illustrator project (sources, linked assets, exports, docs) so automation can find them

Script, Extension, or Plug-in

Adobe's own terms:

  • A script is ExtendScript (.jsx), AppleScript, or VBScript run against Illustrator's scripting object model. It has no persistent UI beyond ScriptUI dialogs.
  • An extension is a CEP panel: an HTML and JavaScript UI hosted in Illustrator that calls ExtendScript through CSInterface.evalScript.
  • A plug-in is native code built with the Illustrator C++ SDK (.aip). In apps that already run UXP (Photoshop, InDesign, Premiere Pro), "plugin" also means a UXP plugin; Illustrator UXP plugins are not public yet.

Start with the lowest tier that meets the need. A script that works is the core of every higher tier: a CEP panel, an MCP tool, and an OS script all end up calling ExtendScript.

Extensibility Timeline

From Adobe's announcement "Investing in the future of Creative Cloud extensibility" (blog.developer.adobe.com, September 2026):

  • Illustrator UXP plugins: public beta by Spring 2027.
  • CEP in Illustrator, After Effects, and Media Encoder: the Adobe Marketplace stops accepting new CEP submissions in December 2028, and CEP is disabled by default from December 2028.
  • CEP leaves these apps from December 2029, with at least two years between each app's UXP public beta and CEP's removal from new versions.
  • ExtendScript is not affected by the transition.

So a CEP extension built today has a working life of a few years. Keep its logic in plain ExtendScript files the panel calls, which carry over to a UXP plugin or an MCP server unchanged.

Workflow

  1. Scope: what the user does, which Illustrator versions and OSes it must run on, and who installs it.
  2. Pick the tier from the table above.
  3. Write the ExtendScript core first with the adobe-illustrator-scripting skill, as functions that take a plain settings object and return a result string, so any front end can call them.
  4. Add the front end:
  • CEP panel: references/cep-extensions.md (folder layout, manifest, CSInterface, debug mode, signing, install)
  • C++ plug-in: references/cpp-plugins.md (SDK, build, PiPL, suites, notifiers, debugging)
  • Command line, MCP server, or computer use: references/automation-and-mcp.md (COM, AppleScript, parameters, results, MCP design, safety)
  1. Test inside Illustrator on a copy of a real document: run every option, export a PNG of the result, and compare it with the expected output.
  2. Package: a signed ZXP for CEP, a per-OS .aip for plug-ins, a versioned folder or package for scripts and servers.
  3. Document with references/publishing-docs.md: requirements, compatibility, install steps per OS, a walkthrough with screenshots, a GIF, troubleshooting, and a changelog.

Running a Script From Outside Illustrator

Pass parameters through a sidecar key=value file (no JSON parser or eval needed in ES3) and have the script write its result to a file, because arguments handling differs between launchers. The patterns are in references/automation-and-mcp.md.

Instructions People Follow by Hand

When the deliverable is a set of steps rather than code (for a complex graphic, or for an asset someone downloads):

  • Name the Illustrator version the steps were checked on, and give menu paths exactly as they appear (Object > Path > Offset Path).
  • One action per step, with the panel and the value to set (Stroke panel: Weight 2 pt, Align Stroke to Inside).
  • Show the expected result after each group of steps, with a screenshot or a small PNG.
  • Mark the steps that differ on Windows and macOS (shortcuts, file dialogs, font paths).
  • Offer the scripted route next to the manual one when a script exists.

Guardrails

  • Work on copies of user documents; never overwrite an original without a backup.
  • Ask before writing into Adobe's install folders, the system CEP folder, or the registry.
  • Development mode (PlayerDebugMode) belongs on development machines only. Ship signed ZXPs to users.
  • Never commit signing certificates, certificate passwords, API keys, or tokens. Read secrets from environment variables.
  • Prefer scripting, COM, or AppleScript over clicking through the UI; use computer use only for what has no scripting route.
  • Never automate around sign-in, licensing, or account dialogs.
  • Fonts from Adobe Fonts cannot be bundled in a plug-in or extension; document them as a requirement instead.
  • Version-specific details (CEP version, SDK version, menu names) change; say which version you checked and point to Adobe's docs.

References

  • references/cep-extensions.md: CEP panels from folder layout to signed ZXP
  • references/cpp-plugins.md: C++ plug-ins with the Illustrator SDK
  • references/automation-and-mcp.md: command-line runs, MCP servers, and computer use
  • references/publishing-docs.md: install and usage docs for a published Illustrator tool
  • Adobe CEP Resources (CEP 12 cookbook, CSInterface.js, ZXPSignCMD): Adobe-CEP/CEP-Resources
  • Adobe CEP getting-started guides (packaging, signing, distribution): Adobe-CEP/Getting-Started-guides
  • UXP and CEP timeline: Investing in the future of Creative Cloud extensibility

More skills from github/awesome-copilot

  • Aacquire-codebase-knowledgeUse this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
  • Aacreadiness-assessRun the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.
  • Aacreadiness-generate-instructionsGenerate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
  • Aacreadiness-policyHelp the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.
  • Aad-campaign-analyzerUse this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like "analyze my ad campaigns", "where am I wasting ad spend", "reallocate my ad budget", "which ads are actually working", or "ROAS analysis". Do not trigger for campaign planning or creative generation without performance data.
  • Aadd-educational-commentsAdd educational comments to the file specified, or prompt asking for file to comment if one is not provided.
  • Aadobe-illustrator-scriptingWrite, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.
  • Aagent-architectureDesign AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code review.
  • Aagent-governancePatterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
  • Aagent-owasp-complianceCheck any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
  • Aagent-skill-stackFind, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has low Skill recall, wants indirect helpers such as humanizers or compliance checks, or wants a project-specific Skill Stack with controlled installation. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit, safety, and overlap. Do not use for locating one known or common Skill; use the generic find-skills workflow.
  • Aagent-supply-chainVerify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when: - Generating SHA-256 integrity manifests for agent plugins or tool packages - Verifying that installed plugins match their published manifests - Detecting tampered, modified, or untracked files in agent tool directories - Auditing dependency pinning and version policies for agent components - Building provenance chains for agent plugin promotion (dev → staging → production) - Any request like "verify plugin integrity", "generate manifest", "check supply chain", or "sign this plugin"

All agent skills → · MCP servers