Image edit
Connector-first Claude Code pack for graphic designers: Figma, Canva, Adobe Firefly, Nano Banana, Higgsfield, Unsplash, Brand.dev + skills, design guardrails (contrast/licensing/asset hygiene), loops & review agents.
npx -y skills add m-binimran/design-pack --skill image-editAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Edit or retouch an existing image with a connector - background removal, generative fill/expand, cleanup, recolor, or compositing. Use when modifying a photo or asset rather than generating from scratch.
SKILL.md
1.3 KB, as published. Nobody here has run it
image-edit
Non-destructive, disclosed, and licensed editing via the right connector.
Pick the connector
- Adobe Express / Firefly: background removal, generative fill/expand, object cleanup, colour adjustments.
- Nano Banana (Gemini): prompt-based edits and multi-image compositing (blend references).
(See
mcp/CONNECTORS.md.)
Process
- State the edit precisely (remove background, extend canvas to 16:9, remove the trash can, warm the tone).
- Run it through the connector; confirm the result returned.
- Check it didn't misrepresent a real subject (for product/real-estate/editorial, don't alter material facts).
- Disclose AI editing where required (the
ai/license rules), and keep the original. - Export at the right format/size/colour profile (hand to
asset-export).
Output
- The edited image (confirmed from the connector), what changed, and a disclosure/license note.
Guardrails
- Don't claim an edit happened if the connector didn't run it.
- Disclose AI alteration when it matters; don't edit away material truth in documentary/product imagery.