diff --git a/skills/baoyu-cover-image/SKILL.md b/skills/baoyu-cover-image/SKILL.md
index 4718c02..1a4abce 100644
--- a/skills/baoyu-cover-image/SKILL.md
+++ b/skills/baoyu-cover-image/SKILL.md
@@ -159,6 +159,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }
 2. **Save source content** (if pasted, save to `source.md`)
 3. **Analyze content**: topic, tone, keywords, visual metaphors
 4. **Deep analyze references** ⚠️: Extract specific, concrete elements (see reference-images.md)
+   - If references contain **people** → set `usage: direct` so model sees reference image, describe character features for stylized preservation (see reference-images.md § Character Analysis)
 5. **Detect language**: Compare source, user input, EXTEND.md preference
 6. **Determine output directory**: Per File Structure rules
 
diff --git a/skills/baoyu-cover-image/references/base-prompt.md b/skills/baoyu-cover-image/references/base-prompt.md
index 5b71e31..d07212c 100644
--- a/skills/baoyu-cover-image/references/base-prompt.md
+++ b/skills/baoyu-cover-image/references/base-prompt.md
@@ -83,12 +83,17 @@ Full library: [references/visual-elements.md](visual-elements.md)
 
 ### Character Handling
 
-When people are needed:
+**Default (no reference with people)**:
 - Use simplified silhouettes or abstract stick figures
 - Symbolic representations (head + shoulders outline)
 - NO realistic faces, detailed anatomy, or photographic representations
 - Cartoon/icon style consistent with rendering choice
 
+**When reference images contain people**:
+- Reference image is passed to model (`usage: direct`) — model must visually reference it to preserve character likeness
+- Stylize to match chosen rendering (cartoon/vector), preserving distinctive features (hair, clothing, pose)
+- NEVER photorealistic
+
 ## Mood Application
 
 Apply mood adjustments to the base palette:
diff --git a/skills/baoyu-cover-image/references/workflow/prompt-template.md b/skills/baoyu-cover-image/references/workflow/prompt-template.md
index 5d0129b..0afde88 100644
--- a/skills/baoyu-cover-image/references/workflow/prompt-template.md
+++ b/skills/baoyu-cover-image/references/workflow/prompt-template.md
@@ -201,6 +201,12 @@ CRITICAL: The generated cover MUST visually reference the provided images. The c
 - [Typography]: [Specific treatment, e.g., "Uppercase text with wide letter-spacing"]
 - [Layout element]: [Specific spatial element, e.g., "Bottom banner strip in dark color"]
 
+## From Ref 1 ([filename]) — Characters (if people present):
+- **Character 1**: [Appearance, e.g., "Woman, long wavy blonde hair"] → MUST stylize: [e.g., "flat-vector, simplified face, keep blonde hair, label: 'Nicole Forsgren'"]
+- **Character 2**: [Appearance, e.g., "Man, short dark hair, stubble"] → MUST stylize: [e.g., "flat-vector, simplified face, keep dark hair, label: 'Gergely Orosz'"]
+- **Placement**: [e.g., "Right third, side by side, facing left toward main visual"]
+- **Style**: Match rendering style, NOT photorealistic
+
 ## From Ref 2 ([filename]) — REQUIRED elements:
 [Same detailed breakdown]
 
diff --git a/skills/baoyu-cover-image/references/workflow/reference-images.md b/skills/baoyu-cover-image/references/workflow/reference-images.md
index d1e57e7..f7147a9 100644
--- a/skills/baoyu-cover-image/references/workflow/reference-images.md
+++ b/skills/baoyu-cover-image/references/workflow/reference-images.md
@@ -31,8 +31,8 @@ usage: direct | style | palette
 
 | Usage | When to Use |
 |-------|-------------|
-| `direct` | Reference matches desired output closely |
-| `style` | Extract visual style characteristics only |
+| `direct` | Model sees reference image directly; required if people must appear in output |
+| `style` | Extract visual style only (not for people who must appear) |
 | `palette` | Extract color scheme only |
 
 ## Verbal Extraction (No File)
@@ -59,6 +59,19 @@ References are high-priority inputs. Extract **specific, concrete, reproducible*
 
 **Output format**: List each element as bullet that can be copy-pasted into prompt as mandatory instruction.
 
+### Character Analysis ⚠️ If Reference Contains People
+
+Use `usage: direct` so model sees the reference image. Additionally describe per character: **appearance**, **pose**, **clothing** → with **transformation rules** (stylize to match rendering).
+
+| Extract | Good | Bad |
+|---------|------|-----|
+| Appearance | "Woman: long wavy blonde hair, friendly smile" | "A woman" |
+| Pose | "Standing, facing camera, confident posture" | "Standing" |
+| Clothing | "Dark T-shirt, business casual" | "Formal" |
+| Transform | "Flat-vector cartoon, keep hair color & clothing" | "Make cartoon" |
+
+Use `usage: direct`. Output each character as MUST/REQUIRED prompt instruction.
+
 ## Verification Output
 
 **For saved files**: