Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add calesthio/generative-media-skills --skill lighting-directiongit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/calesthio/generative-media-skills/lighting-direction)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/lighting-direction"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/lighting-direction/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/lighting-direction"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/lighting-direction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.05183 |
| Opus 5 | $0.00046 | $0.02592 |
| Sonnet 5 | $0.00018 | $0.01037 |
| Haiku 4.5 | $0.00009 | $0.00518 |
Grade A, and why
lighting-direction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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. Translate the guidance into the syntax of the chosen image, video, avatar, or composition tool after reading that tool's own instructions.
Evidence labels
Use these labels in plans, prompts, and reviews when claims matter:
- Documented fact: supported by a cited lighting, cinematography, color, accessibility, or manufacturer source.
- Empirical observation: based on direct inspection of generated outputs or references in the current project.
- Production heuristic: a repeatable craft rule that often works but should be tested against the brief and model behavior.
Do not present a heuristic as a universal law. ARRI's lighting handbook explicitly frames hard-versus-soft choices as judgment calls rather than right/wrong rules, while documenting that physical source size and diffusion strongly affect shadow softness.
First decision: what should the light do?
Before writing a prompt, answer five questions:
- Narrative motivation: What real or implied source explains the light: window, sun, skylight, street sign, laptop, vanity mirror, car headlights, softbox, studio cyc, product light tent, neon practical?
- Emotional contrast: Should shadows feel open, friendly, premium, clinical, suspenseful, nocturnal, nostalgic, harsh, sweaty, or sculptural?
- Subject hierarchy: What must be brightest, sharpest, or separated from the background? What can fall into shadow?
- Surface behavior: Are the important surfaces skin, hair, glass, chrome, matte packaging, fabric, liquid, screen UI, jewelry, food, or architecture?
- Continuity requirement: Is this a one-off still, a multi-shot scene, a talking avatar, or a product/ad sequence that must preserve the same lighting geometry?
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 352 lines · 92 tokens per session scan A 22730df9e87e
lighting-direction is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 5,183 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…