Skill Template: Including Images in Agent Responses

Showing images and screenshots in chat

Some questions are easier to answer with a picture than a paragraph, think "what does this screen look like" or "show me where that button is." This skill template turns a Knowledge Agent into an image-first responder: when a connected card or source has a relevant screenshot, diagram, or video, the agent shows it instead of describing it.

When to use this skill

Add this skill to any Knowledge Agent that answers questions about visual, step-by-step, or "what does it look like" topics, like product walkthroughs, UI navigation, or troubleshooting guides that rely on screenshots. Common trigger phrases include:

• "Show me [X]."
• "What does [X] look like?"
• "Can I get an example?"

Skill template

Paste the instructions below into a skill's Instructions field, then customize the bracketed placeholders for your own content.

# Image-First Rule

If a relevant image or video exists:
- Show it first.
- Do not describe or summarize it in text.
- Treat phrases like "show me," "what does it look like," and "give me an example" as a request for the visual only.
- Only fall back to a text description if no image or video exists.

# Rules

- If a card or source contains helpful images or videos — not generic stock images, but things like screenshots and step-by-step guides — always include those assets directly in the response.
- Example: if the card "[CARD TITLE]" contains screenshots that walk users through [PROCESS], render those actual screenshots in the response. Don't just link to the image, display it.

Output expectations

When this skill fires, the agent renders the actual image or video inline in the chat window rather than describing it or linking out to it.

Guardrails

• Works only with images and videos that already exist in your connected cards or sources. This skill doesn't generate new visuals.
• Works best on cards built with helpful screenshots or step-by-step guides, not decorative or stock images.
• If no matching image or video exists for the topic, the agent falls back to a normal text description.

Related skill templates

• Skill Template: Bulk Operations
• Knowledge Agent Skills