resolve-mcp: Skill for Claude Code

/color-assist — AI Color Grading

Look at the current frame, analyze the color, and make adjustments directly in the Resolve Color page node graph.

Why sRGB

Multimodal LLMs (Claude, Gemini, GPT-4V) are trained on sRGB imagery. Even if the project is graded in DaVinci Wide Gamut, ACES, Rec.2020, or HDR PQ — the exported frame MUST be converted to sRGB before analysis. This gives the AI the most accurate color perception regardless of the working color space.

Arguments

• No arguments: analyze current frame, suggest and apply corrections
• shadows warmer: specific instruction for what to adjust
• more contrast: push contrast
• match [style]: aim for a specific look (e.g., "match teal and orange", "match film noir")
• just analyze: look at the frame and describe what you see, don't make changes
• undo: reset the last node to neutral

Workflow

1. Switch to Color page

Use resolve_switch_page("color") to ensure we're on the Color page with a clip selected.

2. Export current frame

Use resolve_export_frame to export the current frame to a temporary file:

• Path: /tmp/resolve_color_assist_frame.png

3. Convert to sRGB

Run ffmpeg via Bash to convert the exported frame to sRGB:

ffmpeg -y -i /tmp/resolve_color_assist_frame.png \
  -vf "colorspace=all=bt709:iall=bt2020:fast=1" \
  -color_primaries bt709 -color_trc iec61966-2-1 -colorspace bt709 \
  /tmp/resolve_color_assist_srgb.png 2>/dev/null

If that fails (project might already be in Rec.709/sRGB), fall back:

ffmpeg -y -i /tmp/resolve_color_assist_frame.png \
  -pix_fmt rgb24 \
  /tmp/resolve_color_assist_srgb.png 2>/dev/null

If ffmpeg is not available, use the exported frame as-is and note the limitation.

4. Read the sRGB frame

Use the Read tool on /tmp/resolve_color_assist_srgb.png — Claude is multimodal and can see images directly. This is the key step: YOU are looking at the actual frame from the timeline.

5. Get current grade state