Skills for Real Engineers. Straight from my .agents directory.
color-correction
Agent skill fromartokun/comfyui-mcp
Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a contact sheet. Covers the "washed out" signature, why reference color-match (mkl/ColorMatch/ColorMatchAdobe) CAN'T add contrast a flat source lacks, the levels/contrast-stretch fix (core AdjustContrast / CurveEditor), the measure→fix→re-measure loop, the side-by-side sandbox pattern, and where to place the fix in a render graph (after decode, before save). Use when a render looks washed out / flat / dull / over-saturated / color-cast, or when deciding between a color-match and a contrast/levels fix.
How to install color-correction
npx skills add artokun/comfyui-mcp# or add only this skill to Claude Code: copy the folder
plugin/skills/color-correction/
# into
~/.claude/skills/color-correction/ (all projects)
.claude/skills/color-correction/ (one project)
1# Color Correction (measure, don't eyeball)23## The core principle45You cannot reliably judge color from a storyboard or contact sheet. "Is it washed6out?" flip-flops by eye, especially on AI-gen video. Make color measurable with the7`get_image (action:"analyze_color")` MCP tool, read the numbers like a colorist reads scopes, pick the8fix the data points to, then re-measure to confirm. The whole skill is this loop:910```11extract a frame ─► get_image (action:"analyze_color") ─► read black/white points + contrast + saturation12 ▲ │13 │ ▼14 re-measure ◄──── apply fix (levels / contrast / match) ◄── diagnose from the numbers15```1617> Origin: on a WAN-Animate render we argued for many turns over whether the clip was18> "washed out." The instant we measured it, the answer was unambiguous and the *correct*19> fix (a contrast stretch, not the color-match nodes we'd been adding) fell straight out.2021---2223## The `get_image (action:"analyze_color")` tool2425Read-only. Source = `asset_id`, a ComfyUI output ref (`filename`/`subfolder`/`type`), or26an image `path` (absolute, or under the output dir). It returns per-image stats, heuristic27flags, a one-line verdict, and optionally an overlaid R/G/B/luma histogram PNG.2829```30get_image({ action: "analyze_color", filename: "render_00007_.png" }) # absolute numbers31…
Excerpt shown under the repository's MIT license.
More skills in comfyui-mcp
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
