diff --git a/skills/design-explore/SKILL.md b/skills/design-explore/SKILL.md
index 52d5dc7..ad8ff7a 100644
--- a/skills/design-explore/SKILL.md
+++ b/skills/design-explore/SKILL.md
@@ -77,12 +77,24 @@ Agent(
 
 The image-maker will generate images via OpenRouter's image models.
 
-### Step 5: Show images inline
+### Step 5: Show images inline (REQUIRED)
 
-When images are generated:
-1. Save them to `/tmp/design-explore-<N>.png`
-2. Use the `read` tool to display them — images appear inline in the pi conversation
-3. Present them to the user: "Here are 3 design concepts. Which direction do you like?"
+After images are generated, you MUST display them inline. Do NOT just save files and report paths.
+
+1. Save each image to `/tmp/design-explore-<N>.png`
+2. **Call `read` on each saved image file** — pi displays images as inline attachments
+3. Present to user: "Here are the design concepts. Which direction?"
+
+Example:
+```bash
+# After image-maker generates images, save them
+# Then READ them so they appear inline:
+read("/tmp/design-explore-1.png")
+read("/tmp/design-explore-2.png")
+read("/tmp/design-explore-3.png")
+```
+
+The user should see the images in the conversation, not have to open files manually.
 
 ### Step 6: Iterate