soul0710

Cinematic — AI skill for Claude Code

AI community

AI video prompt cheat sheet & Claude Skill: cinematic camera angles, camera movement, lighting, composition, color grading for Veo 3, Kling, Sora, Runway, Midjourney.

How to install Cinematic

This entry records only its repository, not the path inside it, so there is no exact command to give. Open soul0710/cinematic and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Cinematic does

AI video prompt cheat sheet & Claude Skill: cinematic camera angles, camera movement, lighting, composition, color grading for Veo 3, Kling, Sora, Runway, Midjourney. 700+ terms with Vietnamese explanations.

Alternatives in AI

Open AI Design Agent — Open-source AI design agent — alternative to Lovart AI, Runway Agent, Luma Labs Agent, Krea Agent, Pika Agent 356 ★
Visual Skills — AI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for 212 ★
AI Pair Collaboration — Coordinate heterogeneous AI teams: one creates, two review from different angles 190 ★

README

🎬 Cinematic Video Prompt Skill

**AI video prompt cheat sheet & Claude Skill for Veo 3, Google Flow, Kling, Sora, Runway, Hailuo, Luma, Midjourney** — camera angles, camera movement, cinematic lighting, composition, color grading, mood, and a ready-to-use prompt formula.

**Bộ từ điển prompt điện ảnh cho AI tạo video/ảnh** — 700+ thuật ngữ về góc máy, chuyển động camera, ánh sáng, bố cục, màu sắc, cảm xúc, có giải thích tiếng Việt và công thức ghép prompt dùng được ngay.

[English](#english) · [Tiếng Việt](#tiếng-việt)

English

What is this?

A **Claude Skill** (works with Claude Code, Claude Cowork and Claude.ai) that teaches the AI professional cinematography vocabulary so your text-to-video and text-to-image prompts stop being vague ("a nice cinematic scene") and start being precise ("medium close-up, low angle, slow dolly in, rim lighting, teal and orange grading").

It is model-agnostic: the vocabulary works for **Veo 3 / Google Flow, Kling, Sora, Runway Gen-4, Hailuo, Luma Dream Machine, Pika, Midjourney, Stable Diffusion, Flux, Nano Banana**, and any future model that reads English prompts.

What's inside

File	Content
`SKILL.md`	The skill itself: workflow, prompt formula, condensed keyword tables, ready-made combos by video type, mood → combo lookup, pre-flight checklist
`references/01-camera-angles-and-movement.md`	70+ camera angles & shot sizes, 60+ camera movements (dolly, arc, crane, FPV drone, dolly zoom, bullet time…) with "when to use"
`references/02-lighting.md`	80+ lighting terms (golden hour, rim light, Rembrandt, chiaroscuro, volumetric, practical, neon…)
`references/03-composition.md`	80+ composition rules (rule of thirds, leading lines, S-curve, negative space, repoussoir…)
`references/04-lens-technical-film.md`	Lenses, aperture, shutter, bokeh, flare, filters, film stocks, aspect ratios, color grading tech
`references/05-style-color-mood.md`	100+ art styles, 80+ color