moonvalley-marey
Produce video with Moonvalley's Marey model family (Marey Realism v1.5) — a filmmaker-oriented, 1080p/24fps generative video model marketed as trained exclusively on licensed data. Use this skill when a task asks for Marey or Moonvalley specifically, when a brief demands brand-safe / legally reviewed AI video for commercial or studio work, or when the request needs Marey's director-style controls (camera trajectory, motion transfer, pose transfer, keyframing, reference conditioning). It covers what "commercially safe" really means versus the actual terms of service, access routes (Moonvalle
npx skills add calesthio/generative-media-skills --skill moonvalley-marey --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
This skill helps an agent produce video using Moonvalley Marey Realism v1.5, a professional, licensed-data video model with director-style controls. It instructs when to choose Marey (brand-safe, legally reviewed needs, or when motion/pose transfer and camera trajectory are required) and outlines its output constraints (1080p 24fps, no audio, short clip lengths) and governance around training provenance and indemnity. It covers how Marey fits production compared to other models and provides a workflow for iteration, reference-driven control, and post-processing.
How it works
The skill outlines to use Marey through multiple access routes (Moonvalley web app/Voyager, fal API, ComfyUI) and to employ Marey’s controls: Camera Control, Motion Transfer, Pose Control/Transfer, Trajectory Control, Keyframing, Reference, Shot Extension, and Multi-layer Spatial Composition. It emphasizes constructing long, cinematographer-style prompts (minimum ~50 words) following a formula: [Camera movement] + [Scale / perspective] + [Core visual] + [Environmental details] + [Lighting / technical specs]. It prescribes aligning prompt strategy with a shot list of 5–10s clips, using motion/pose transfer with references when possible, and preferring i2v workflows to anchor composition. It also advises thorough quality checks for temporal consistency, hand/gesture accuracy, camera flicker, skin quality, and prompt adherence, and recommends post-processing steps (upscale, color, add audio off-platform).
When to use it
Use Marey when the client requires brand/studio-grade compliance with training-data provenance, the shot is single-subject or controlled, and there is a reference to drive motion or pose (or a previz need). Use it for projects needing director-style control through Marey’s ecosystem (Voyager, keyframing, shot extension) rather than for audio generation or multi-character, high-midelity talking-head work. If the brief needs native audio or complex multi-character choreography, other models may be preferred.
What it can touch
The skill lists the available tools and endpoints: Moonvalley web app / Voyager, fal API endpoints (t2v, i2v, motion-transfer, pose-transfer), and ComfyUI. Access parameters for fal API include prompt, image_url, negative_prompt, seed, dimensions, duration. Pricing details for per-generation and credits are provided for planning budgets.
Caveats
Key cautions include: Marey outputs silent video with no native audio; 1080p is the ceiling (no native 4K), and short 5s or 10s clips require assembly in an NLE. The training-data provenance is a first-party claim, not an independently audited guarantee, and user indemnification is required by Moonvalley ToS with liability capped at the greater of $500 or amounts paid. Enterprise terms may offer more robust indemnity, but any output indemnity would be contractually defined. The model can exhibit temporal instability, hand/gesture fidelity issues, and motion/artifact risks, particularly under motion-heavy prompts; iteration cost is non-trivial (roughly 3–8 attempts per keeper shot).
# Moonvalley Marey Marey is Moonvalley's generative video model, aimed at professional filmmakers, studios, and brand teams that need AI video they can put through legal review. Its differentiator is not raw fidelity — it is **provenance**: Moonvalley markets Marey as trained exclusively on owned or licensed footage, and pairs it with a set of director-style controls. This skill helps an agent dec
What does the moonvalley-marey skill do?
Produce video with Moonvalley's Marey model family (Marey Realism v1.5) — a filmmaker-oriented, 1080p/24fps generative video model marketed as trained exclusively on licensed data. Use this skill when a task asks for Marey or Moonvalley specifically, when a brief demands brand-safe / legally reviewed AI video for commercial or studio work, or when the request needs Marey's director-style controls (camera trajectory, motion transfer, pose transfer, keyframing, reference conditioning). It covers what "commercially safe" really means versus the actual terms of service, access routes (Moonvalle
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill moonvalley-marey --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.