- Home
- Skills
- Image & Video
- Islamic Visual Safety for AI Images & Video
Works with the AI Agents you already use
Islamic Visual Safety for AI Images & Video
Rules for AI images, thumbnails and video in Islamic content: no depiction of prophets, angels, companions or named scholars; correct mosques and calligraphy; protect children's privacy.
Free
Islamic Visual Safety for AI Images & Video
Example session with this skill installed
Make an image prompt for a kids' story thumbnail: Prophet Musa splitting the sea with his staff.
- Read your context and instructions
- Compiled the islamic visual safety
Summary
I won't depict Prophet Musa (peace be upon him), not even as a silhouette or from behind. The story can still be shown through the scene itself.
Safe prompt
Children's book illustration, wide view of a calm sea parted into two tall walls of turquoise water with a dry sandy path between them, morning light, gentle clouds, no people, no text, soft watercolor style, warm and hopeful mood.
Why this works
| Element | Choice |
|---|---|
| Prophet | Not shown in any form |
| Followers | Not needed; the parted sea tells the story |
| Text in image | None; add the title later in your editor with a real font |
| Label | Add "Ilustrasi" in a corner |
Checklist before publishing
- No human figure that could be read as the prophet.
- No AI-generated Arabic letters.
- Title written with a real font by you, not by the model.
Next steps
- Generate 3 variations and pick the one with no accidental figures in the water or on the path.
Connects securely to your tools. The creator never sees your data.
About this skill
One wrong image can undo a whole post
Image models will happily draw a prophet, put fake Arabic on a mosque, or invent calligraphy that says nothing. For a Muslim audience that is offensive, not just inaccurate.
Islamic Visual Safety gives your agent hard rules and safe alternatives:
- No depiction of Allah, prophets, angels, companions or named scholars, in any form (including silhouettes, faceless or light figures)
- Generic characters labelled "Ilustrasi" when people are needed
- Correct mosques and the Ka'bah, no AI-generated Arabic text in images
- Prompt rules for image models and a pre-publish checklist
- Children's privacy: no identifiable faces without consent
Part of santri-skills, a free open-source pack of 9 skills for trustworthy Islamic content: https://github.com/Santrionlinecom/santri-skills
Licence: MIT (code) + CC BY 4.0 (text). Built by SantriOnline (https://santrionline.com).
Related resources
- SantriOnline: https://santrionline.com
- Open-source skill pack (santri-skills): https://github.com/Santrionlinecom/santri-skills
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.
Guides prompts and reviews; it cannot stop an image model from adding unwanted figures, so every image still needs a human look before publishing. It does not generate images itself.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
Permissions
No special permissions declared or detected