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 u2n4/gemini-media-mcp --skill veo-promptinggit clone --depth 1 https://github.com/u2n4/gemini-media-mcpWrote 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/u2n4/gemini-media-mcp/veo-prompting)<a href="https://agentmods.dev/skills/u2n4/gemini-media-mcp/veo-prompting"><img src="https://agentmods.dev/badge/skills/u2n4/gemini-media-mcp/veo-prompting/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/u2n4/gemini-media-mcp/veo-prompting"><img src="https://agentmods.dev/badge/skills/u2n4/gemini-media-mcp/veo-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00108 | $0.04336 |
| Opus 5 | $0.00054 | $0.02168 |
| Sonnet 5 | $0.00022 | $0.00867 |
| Haiku 4.5 | $0.00011 | $0.00434 |
Grade A, and why
veo-prompting 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 11d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VEO 3.1 Professional Prompting Mastery
When to Use This Skill
Activate this skill EVERY TIME before calling any VEO tool:
veo:veo_generate_video— Text-to-Videoveo:veo_image_to_video— Image-to-Videoveo:veo_interpolate_video— First/Last Frame transitionsveo:veo_extend_video— Extend existing clips
Read and apply these techniques to transform any video request into a cinematic-grade prompt.
Model Capabilities & Constraints
| Parameter | Options |
|---|---|
| Resolution | 720p, 1080p (1080p requires 8s duration) |
| Duration | 4, 6, or 8 seconds per clip |
| Aspect Ratio | 16:9 (landscape), 9:16 (portrait) |
| Audio | Native synchronized audio (dialogue, SFX, ambient, music) |
| Reference Images | Up to 3 images for character/style consistency |
| Frame Control | First frame, last frame, or both for transitions |
| Extension | ~7s per extension, max 148s total (720p only) |
Key Behaviors
- VEO interprets prompts like a film crew — precise direction yields precise results
- Front-loaded shot type ensures framing priority
- Without explicit camera direction, defaults to static/subtle handheld
- Audio is generated WITH video — not layered on top
- Same prompt + different seed = very similar output (unlike image models)
- 100-180 words is the sweet spot for text-to-video prompts
- 50-100 words for image-to-video prompts
THE MASTER FORMULA (7 Layers)
[1. CINEMATOGRAPHY] + [2. SUBJECT] + [3. ACTION] + [4. ENVIRONMENT] + [5. LIGHTING & MOOD] + [6. AUDIO DESIGN] + [7. TECHNICAL CONTROLS]
Layer 1: CINEMATOGRAPHY (Camera — Always First!)
Shot Types: Extreme Wide (EWS) → Wide (WS) → Medium (MS) → Medium Close-Up (MCU) → Close-Up (CU) → Extreme Close-Up (ECU) → Over-the-Shoulder (OTS) → Two-Shot
Camera Movements: Static/Tripod | Slow Pan | Dolly In/Out | Tracking | Crane | Aerial/Drone | Handheld | Whip Pan | POV | Orbit/Arc
Lens & Focus: 16mm wide-angle | 24mm establishing | 35mm natural | 50mm balanced | 85mm portrait | Macro detail | Shallow DOF f/1.4-2.8 | Deep Focus | Soft Focus
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.
- 11d ago First seen · 335 lines · 108 tokens per session scan A b21b6b25805e
veo-prompting is a skill published in the GitHub repository u2n4/gemini-media-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 4,336 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.