photoshop-automator
Professional Adobe Photoshop automation via COM/ExtendScript bridge. Supports text updates, filters, and action playback.
Install
npx skills add https://github.com/abdul-karim-mia/photoshop-automator --skill photoshop-automatorSKILL.md
Photoshop Automator Skill (v1.2.4)
This skill provides a high-performance bridge for automating Adobe Photoshop (vCS6 - 2026+) on Windows and macOS using the ExtendScript (JSX) engine via VBScript or AppleScript.
Commands
- runScript: Executes raw ExtendScript (ES3) code. Use this for complex document manipulation.
- updateText: Target a specific text layer by name and update its contents instantly.
- createLayer: Create new art layers with custom opacity and blending modes.
- applyFilter: Apply a professional Gaussian Blur filter to the active layer.
- playAction: Play recorded Photoshop actions (.atn) by name and set.
- export: Save the active document as a high-quality PNG or JPEG.
🛠 AI Protocol
1. Technical Constraints (Strict)
- ES3 Syntax Only: Photoshop's ExtendScript engine uses ECMAScript 3 (ES3).
- ❌ DO NOT USE:
const,let, arrow functions() => {}, template literals`${}`, orMap/Set. - ✅ USE: Only
var, standardfunctiondeclarations, and string concatenation ('a' + b).
- ❌ DO NOT USE:
- Assume Active Document: Commands operate on the active document. If none is open, scripts will fail unless they call
app.documents.add().
2. Security & Side Effects
- Filesystem Access: The
runScriptcommand allows execution of arbitrary ExtendScript. This engine has direct access to the host filesystem. - Side Effects: Scripts can create, modify, or delete files on the local machine via the
FileandFolderobjects. - Verification: Always review dynamically generated scripts before execution to prevent unintended document or filesystem modifications.
3. Error Handling
- GUI Blocks: If Photoshop has a modal dialog open (e.g., Save As window, error popup), COM operations will hang or fail. Direct the user to close any open dialogs.
- Layer Presence: If
updateTextfails, ensure the layer name provided matches exactly (case-sensitive) with the layer in the PSD.
Setup
Ensure Adobe Photoshop is installed on the host system. The skill automatically uses the registered COM server.
Developed for the OpenClaw community by Abdul Karim Mia.
Related skills
ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper
