lighting-direction
Provider-independent lighting direction for AI-generated images, video clips, ads, film scenes, avatars, product shots, interviews, beauty work, and social content. Use when an agent must specify, translate, maintain, troubleshoot, or QA motivated lighting, key/fill/back/rim/practical lights, hard or soft light, color temperature, exposure, contrast, time-of-day, continuity, reference strategy, or safety/accessibility risks in generated media.
Profile →npx skills add calesthio/generative-media-skills --skill lighting-direction --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
States lighting as a structured prompt: specify audience-understanding motivation from light, then concrete visible lighting behavior (source motivation, direction, quality, color, contrast, exposure, falloff, catchlights, separation, practicals, continuity).
How it works
Guides the model to identify and name visible or implied light sources (e.g., late afternoon window camera-left, warm bedside lamp), then describes lighting roles (Key, Fill, Back/rim, Background, Catchlight) with explicit properties like side, height, softness, and color. Distinguishes hard vs soft light by source size and diffusion, and uses exposure ratios and falloff rules to craft prompts (e.g., 1:1 to 2:1, dramatic low key, silhouette). Provides color temperature guidance (e.g., 3000-3200K warm tungsten, 5000-5600K neutral daylight). Includes a translated prompt structure for prompts to models, with sections: Intent, Motivation, Lighting geometry, Contrast/exposure, Color, Surface/camera cues, Continuity constraints, Negative constraints. Includes example fragment:
Lighting direction: motivated late-afternoon window light from camera-left, large soft source with gentle wrap, key side at normal exposure, fill side about two stops darker with negative fill, warm practical lamp visible in the background but not clipping, subtle cool rim from the window edge, background one stop under, natural skin texture, single clean catchlight, no flat front flash, no random colored light.
When to use it
Use when an agent must specify or maintain motivated lighting, or ensure continuity across shots and scenes, including time-of-day and exposure relationships. It also provides a reference strategy and negative constraints to avoid common lighting issues (e.g., flat frontal flash, blown highlights, inconsistent light direction).
What it can touch
Declares tools: claude-code, codex, copilot, cursor. It translates the lighting plan into the syntax of the chosen tool after reading that tool's instructions.
Caveats
License: MIT. Declared evidence labels and production heuristics emphasize documented facts, empirical observations, and production heuristics; avoids universal rules, and prescribes testing against briefs and model behavior.
# Lighting direction for generated media Use lighting as story structure, not decoration. State what the audience should understand from the light, then specify the visible lighting behavior that an image or video model can render: source motivation, direction, quality, color, contrast, exposure, falloff, catchlights, separation, practicals, and continuity. This skill is provider-independent. Tran
What does the lighting-direction skill do?
Provider-independent lighting direction for AI-generated images, video clips, ads, film scenes, avatars, product shots, interviews, beauty work, and social content. Use when an agent must specify, translate, maintain, troubleshoot, or QA motivated lighting, key/fill/back/rim/practical lights, hard or soft light, color temperature, exposure, contrast, time-of-day, continuity, reference strategy, or safety/accessibility risks in generated media.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill lighting-direction --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.