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 kevinnft/ai-agent-skills --skill social-media-slideshow-videogit clone --depth 1 https://github.com/kevinnft/ai-agent-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/kevinnft/ai-agent-skills/social-media-slideshow-video)<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/social-media-slideshow-video"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/social-media-slideshow-video/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/kevinnft/ai-agent-skills/social-media-slideshow-video"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/social-media-slideshow-video.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 | $0.00027 | $0.01877 |
| Opus 5 | $0.00014 | $0.00938 |
| Sonnet 5 | $0.00005 | $0.00375 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
social-media-slideshow-video scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(cmd, capture_output=True, text=True, timeout=300) How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media Slideshow Video Generator
When to use
Use when users request: product review videos, promotional slideshow videos, TikTok/Reels/Shorts content from static images, photo-based video with text overlays, hijab/fashion/beauty review videos, unboxing recap videos, or any image-to-video social media content with designed slides.
Stack
| Layer | Tool | Purpose |
|---|---|---|
| Imaging | Pillow (PIL) | Slide design, text rendering, image manipulation |
| Encoding | ffmpeg (CLI) | Frame sequence → MP4 encoding |
| Core | Python 3 | Orchestration |
No GPU, no moviepy, no heavy dependencies needed.
Architecture: File-Based Frame Pipeline
Critical: Do NOT store all frames as numpy arrays in memory. A 15-second 1080×1920 video at 24fps = 360 frames × ~6MB each = 2.1GB RAM → OOM kill.
Correct approach:
1. Render each SLIDE as a static PIL Image (5-10 slides in memory is fine)
2. For each slide, generate per-frame variations (fade, zoom) and SAVE AS PNG to tmpdir
3. Feed the PNG sequence to ffmpeg via -i pattern
4. Clean up temp files
Why not pipe to ffmpeg stdin?
Piping raw RGB frames to ffmpeg stdin causes deadlocks and broken pipe errors in many environments. The file-based approach is robust and debuggable.
Resolution Presets
| Platform | Resolution | Aspect | FPS |
|---|---|---|---|
| TikTok / Reels / Shorts | 1080×1920 | 9:16 | 24 |
| YouTube landscape | 1920×1080 | 16:9 | 24-30 |
| Instagram square | 1080×1080 | 1:1 | 24 |
| Story/Status | 1080×1920 | 9:16 | 24 |
Slide Types & Design Patterns
1. Title Slide
- Gradient background (soft, matching product color)
- Hero photo in rounded-rect or circular frame with colored border
- Product name + subtitle text centered below
- Tag/category text above photo
2. Detail/Review Slide
- Blurred photo as background (
GaussianBlur(radius=20)+ dark blend at 0.55) - Photo at top with gradient fade mask at bottom edge
- Semi-transparent card overlay (
RGBAwith alpha ~220) with rounded corners - Bullet points + rating text
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 · 196 lines · 27 tokens per session scan A d7b60414b941
social-media-slideshow-video is a skill published in the GitHub repository kevinnft/ai-agent-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,877 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
extract-design
Extract a complete design system — colors, typography, spacing, components, shadows, and W3C design tokens — from any live website using Dembrandt. Runs a headless browser against the URL and returns real computed values from the DOM. Use when you need a site's actual design tokens, want to reverse-engineer a visual…
elevation-and-depth
Elevation — subtle shadows and layering — communicates visual hierarchy by lifting elements above the surface. Combined with border-radius, it creates the tactile quality of cards, modals, and interactive surfaces. Use when designing cards, dropdowns, modals, tooltips, or any floating UI element.
loading-states-and-perceived-performance
Manage user expectations during wait times with appropriate loading states — from simple spinners to complex skeleton screens and staggered animations. Perceived performance is often more important than actual load time. Use when designing data-heavy components, handling API calls, building hero sections, or improving…
tab-navigation
Tabs organise related content under a shared context — switching tabs swaps the view without leaving the page. Use when a screen has multiple distinct content areas that share a common header or action set, and when the user needs to switch between them frequently. Use when designing tabbed layouts, content panels…
status-colors-and-errors
Keep status and error colours minimal and consistent — too many semantic colours confuse users. Each colour must mean exactly one thing. Errors should be recoverable, large failures must be prevented, and the UI should always give the user a path forward. Use when designing status indicators, error states, form…