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 PicsArt/gen-ai-skills --skill video-prompt-engineergit clone --depth 1 https://github.com/PicsArt/gen-ai-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/picsart/gen-ai-skills/video-prompt-engineer)<a href="https://agentmods.dev/skills/picsart/gen-ai-skills/video-prompt-engineer"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/video-prompt-engineer/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/picsart/gen-ai-skills/video-prompt-engineer"><img src="https://agentmods.dev/badge/skills/picsart/gen-ai-skills/video-prompt-engineer.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 | $0.00015 | $0.04876 |
| Opus 5 | $0.00008 | $0.02438 |
| Sonnet 5 | $0.00003 | $0.00975 |
| Haiku 4.5 | $0.00002 | $0.00488 |
Grade A, and why
video-prompt-engineer 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Prompt Engineer
You turn a rough video idea, or a prompt that is not working, into a prompt that names every decision a generator would otherwise make at random. Your output is always a prompt. You do not generate video, you do not call a CLI, and you do not describe what you would write: you hand back the finished text, ready to paste.
When to Use
Use when the user wants to write, improve, rescue or review a prompt for AI video generation, or when they report a defect in a video they already generated, or when they want a clip to match an existing style guide. Covers commercial work, live action and animation.
- Prompt work: "improve this video prompt", "optimize my prompt", "write a prompt for a video of X", "make this prompt better", "video prompt for Sora / Veo / Seedance / Kling / Runway", "add camera direction to this", "turn this idea into a video prompt", "review my prompt", "match this style guide", "same look as the last clip", "use my style guide for this".
- Commercial and marketing: "animate this product shot", "make a product video", "product video ad", "swap the clothing on this model", "change the model", "show this on a different skin tone", "apparel video", "jewellery video", "rotate the car", "showroom turntable", "make this into a Reel", "video ad for Instagram or TikTok".
- Craft: "cinematic shot", "film look", "how do I light this", "make it look like a movie", "cartoon animation prompt", "animate on twos", "cel shaded animation", "my character keeps changing between shots".
- Defect reports, because almost every one of them is a missing clause: "there is an extra hand", "extra limbs", "too many fingers", "the hands look melted", "the face is distorted", "there is an artifact in the generated video", "there are glitches", "the subject warps", "it morphs halfway through", "the character changes appearance", "there are objects that were not in my prompt", "there are people I did not describe", "something appeared in the background", "there is text on the video", "there is a watermark I did not ask for", "why does my video look wrong", "my generated video is drifting", "nothing happens in the clip", "it looks like a slideshow", "the shots do not match each other", "the ending is abrupt".
What ships with it
12 files 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.
- references/animation.md 6.2 KB
- references/audio.md 1.0 KB
- references/camera.md 3.7 KB
- references/cinematography.md 6.5 KB
- references/commerce.md 11 KB
- references/examples.md 2.2 KB
- references/exclusions.md 2.2 KB
- references/light-and-colour.md 1.7 KB
- references/motion-and-pacing.md 3.0 KB
- references/structure.md 1.4 KB
- references/style-and-medium.md 1.4 KB
- references/timing-and-format.md 1.0 KB
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 · 385 lines · 15 tokens per session scan A f8e12bbcba35
video-prompt-engineer is a skill published in the GitHub repository PicsArt/gen-ai-skills (4 stars, last pushed 15d ago), licensed MIT. It adds 15 tokens to every session and 4,876 once invoked, about $0.0001 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
prompt-craft
Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
prompt-engineer
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other…
prompt-decompiler
This skill should be used when the user says "decompile this prompt", "reverse engineer this prompt", "analyze this prompt", "break down this prompt", "what does this prompt do", "adapt this prompt for", "simplify this prompt", "split this prompt", "migrate this prompt", "why does this prompt work", "explain this…
prompt-factory
World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory…
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
prompt-analyzer
Analyze prompts for constraint complexity, audit failure risks, and generate optimized rewrites for Claude and GPT. Based on "How LLMs Follow Instructions" (Rocchetti & Ferrara, 2026) constraint taxonomy research. Use when reviewing prompt files, optimizing prompt bases, or auditing instruction quality. Trigger…