release: merge develop into main for v0.18.0

Author: DavidsonGomes

.claude/agents/canvas-designer.md

@@ -7,6 +7,7 @@ memory: project
 skills:
   - dev-verify
   - dev-visual-verdict
+  - ai-image-creator
 ---
 
 You are **Canvas** — the designer-developer. You build production-grade UIs with intentional aesthetic. You commit to a direction BEFORE coding, you pick distinctive typography, you avoid AI-slop generic patterns. The output must look like it was designed, not generated. Derived from oh-my-claudecode (MIT, Yeachan Heo).
@@ -104,6 +105,10 @@ Your **artifact folder** for design specs and decisions: `workspace/development/
 - `dev-verify` — confirm the UI renders without errors
 - `dev-visual-verdict` — visual regression testing (capture before/after screenshots and compare)
 
+## Image Generation
+
+Canvas can use `/ai-image-creator` to generate images when implementing UI — icons, hero images, product shots, app mockup assets, and background textures. Use it when the design requires visual assets that do not already exist in the project.
+
 ## Handoffs
 
 - → `@bolt-executor` — when wiring up logic the design needs (forms, API calls)

.claude/agents/clawdia-assistant.md

@@ -18,6 +18,7 @@ skills:
   - gog-followups
   - gog-tasks
   - int-fathom
+  - workspace-share
   - int-sync-meetings
   - int-todoist
   - schedule-task

.claude/agents/oracle.md

@@ -20,6 +20,7 @@ skills:
   - create-agent
   - create-command
   - create-routine
+  - workspace-share
 ---
 
 You are **Oracle** — the single entry point to EvoNexus and a business consultant. Your job is to make sure a user never gets lost: you run the initial setup, understand their business, show them what the workspace can do for them, and hand them a concrete implementation plan. You orchestrate other agents to do the heavy lifting but you keep the conversation with the human in a single, consistent voice.

.claude/agents/pixel-social-media.md

@@ -27,6 +27,7 @@ skills:
   - int-youtube
   - social-x-longform
   - social-yt-competitive
+  - ai-image-creator
 ---
 
 You are **Pixel**, a specialist in social media and digital marketing with deep knowledge in content creation, social media strategy, and community engagement.
@@ -115,6 +116,10 @@ When creating posts, always include:
 - Verify the content is relevant to the target audience.
 - Suggest A/B variations when it makes sense.
 
+## Image Generation
+
+Pixel can use `/ai-image-creator` to generate images for social media content — thumbnails, banners, carousel visuals, story backgrounds, and post artwork. Use it when the content plan requires original imagery not available from existing assets.
+
 ## Reference
 
 Check the social media working folder and daily logs for additional context and content history (see CLAUDE.md for paths).

.claude/skills/ai-image-creator/SKILL.md

@@ -0,0 +1,89 @@
+# Image Analysis Reference
+
+Advanced prompt patterns for `--analyze` mode. Only read this file when the user needs structured, comparative, or targeted image analysis beyond a simple description.
+
+## Analysis Prompt Patterns
+
+### Plain Text Description
+
+Default behavior — no custom prompt needed. The built-in default covers subject, style, colors, composition, mood, and visible text.
+
+```bash
+uv run python ${CLAUDE_SKILL_DIR}/scripts/generate-image.py --analyze -r "image.png"
+```
+
+### JSON Structured Output
+
+Ask the model to return structured data:
+
+```
+Analyze this image and return a JSON object with these fields:
+- image_type: the type/medium of the image (photo, illustration, screenshot, etc.)
+- subjects: array of objects with {name, position, description}
+- colors: dominant color palette as hex codes
+- text_content: any visible text in the image
+- style: artistic style or visual treatment
+- mood: emotional tone
+- composition: layout and framing description
+```
+
+### Plain Text + JSON Combined
+
+```
+Describe this image in two sections:
+1. PLAIN TEXT: A natural-language paragraph describing what the image shows
+2. JSON: A structured JSON object with fields: image_type, subjects, colors, style, mood, composition, text_content
+```
+
+### Comparison (Multiple Images)
+
+Use multiple `-r` flags to compare images:
+
+```bash
+uv run python ${CLAUDE_SKILL_DIR}/scripts/generate-image.py \
+  --analyze -r "v1.png" -r "v2.png" \
+  -p "Compare these two images. Describe the differences in composition, color, and style. Which is more suitable for a professional website hero banner?"
+```
+
+### Targeted Analysis
+
+Focus the model on specific aspects:
+
+| Focus | Prompt Pattern |
+|-------|---------------|
+| Accessibility | "Evaluate this UI screenshot for accessibility: contrast ratios, text readability, color-blind friendliness" |
+| Brand consistency | "Does this image match a modern tech brand aesthetic? Evaluate color palette, typography, and visual style" |
+| Text extraction | "Extract all visible text from this image, preserving layout and hierarchy" |
+| Technical specs | "Describe the technical properties: estimated resolution, aspect ratio, color space, compression artifacts" |
+| Content moderation | "Describe the content of this image objectively. Flag any potentially sensitive content" |
+| UI/UX review | "Analyze this UI screenshot: layout, visual hierarchy, spacing, typography, and potential usability issues" |
+
+### Batch Analysis Workflow
+
+To analyze multiple images individually (not comparing), loop in the skill:
+
+```bash
+for img in screenshots/*.png; do
+  echo "=== $img ===" >&2
+  uv run python ${CLAUDE_SKILL_DIR}/scripts/generate-image.py \
+    --analyze -r "$img" -p "Describe this screenshot in one paragraph"
+done
+```
+
+## Model Recommendations
+
+| Model | Best For |
+|-------|----------|
+| `gemini` (default) | General analysis, fast and cost-effective. Good at text extraction and structured output |
+| `gpt5` | Nuanced descriptions, creative interpretation, detailed comparisons |
+
+## Output Handling
+
+The `--analyze` flag outputs JSON to stdout. The `analysis` field contains the model's text response. To extract just the analysis text in a script:
+
+```bash
+uv run python ${CLAUDE_SKILL_DIR}/scripts/generate-image.py \
+  --analyze -r "image.png" | python -c "import sys,json; print(json.load(sys.stdin)['analysis'])"
+```
+
+Status messages go to stderr, so piping stdout gives clean JSON.