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 jeremylongworth-source/AgentSkills --skill ai-video-prompt-packgit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/ai-video-prompt-pack)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/ai-video-prompt-pack"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/ai-video-prompt-pack/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/jeremylongworth-source/agentskills/ai-video-prompt-pack"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/ai-video-prompt-pack.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 | $0.00083 | $0.00754 |
| Opus 5.5 | $0.00033 | $0.00302 |
| Sonnet 5.5 | $0.00017 | $0.00151 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
ai-video-prompt-pack 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Video Prompt Pack
Core Workflow
- Identify platform or model, output length, aspect ratio, audience, campaign goal, source assets, distribution channel, and review owner.
- Verify current official constraints when the platform matters: duration, aspect ratio, audio support, reference images, watermarking, upload limits, rights rules, and safety policies.
- Reduce the idea to one clear visual job per generated clip. For short clips, prefer one transformation, one setting, one camera move, and one CTA moment.
- Write the prompt with concrete subject, action, scene, style, camera, motion, pacing, lighting, audio, and final-frame instructions.
- Add negative prompts or avoidance notes for known failure modes: unreadable text, fake logos, distorted interfaces, generic stock visuals, shaky camera, over-busy scenes, and off-brand visual cliches.
- Provide timing maps, overlay copy, voiceover, post-production notes, and a regeneration prompt when the first output misses the mark.
- Include a post-generation review checklist before publish.
Short-Form Timing Pattern
For 8-second clips, use a simple timing map:
- 0-2 seconds: hook or problem state
- 2-5 seconds: transformation, reveal, or product action
- 5-7 seconds: outcome or proof state
- 7-8 seconds: final hold for CTA or brand mark
For 9:16 vertical videos, keep important details in the middle third and avoid placing essential text near the top or bottom safe areas.
Freshness Rule
AI video tools change quickly. Before giving tool-specific claims about Gemini, Veo, Sora, Runway, Pika, Luma, YouTube Shorts, TikTok, Instagram Reels, or other platforms, verify current official docs when practical.
Read references/ai-video-prompt-checklist.md when the user needs a complete
prompt pack, a platform-specific prompt, or post-generation review criteria.
Safety Rules
- Do not claim generated video is licensable, platform-compliant, or safe for commercial use without human and rights review.
- Do not prompt for private likenesses, living-artist style mimicry, protected characters, copyrighted logos, or voice cloning unless rights are explicit.
- Do not rely on generated in-video text for exact brand copy or URLs; recommend adding critical text in editing unless the tool is known to handle it reliably.
- Require review before publishing regulated, political, medical, financial, legal, employment, crisis, or reputation-sensitive content.
What ships with it
2 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.
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.
- 1mo ago First seen · 79 lines · 83 tokens per session scan A 373f0d94a4bd
ai-video-prompt-pack is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 17d ago), licensed MIT. It adds 83 tokens to every session and 754 once invoked, about $0.0003 per session on Opus 5.5. 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
kermt-pretrain-scratch
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrainddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model…
cdf-auto-labeling
Use when a user needs to get started with CDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, configure a stage, or pull the prebuilt stage containers from NGC (nvcr.io). Confirm critical inputs (data path, output path, endpoints) and ask when any are…
prompt-analysis
Analyze AI prompting patterns and acceptance rates.
prompt-lab
LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.
better-prompt
A prompt editor that turns rough instructions for AI systems into clearer, more complete prompts. It follows published OpenAI and Anthropic guidance.
promptfoo-evals
Design and run promptfoo evaluations for LLM behavior regressions or comparisons across prompts, agent rules, and models. Use for repeatable behavioral cases with explicit assertions, not ordinary unit tests or static configuration checks.