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 jnichor/creador_videos_ai --skill creador_videos_aigit clone --depth 1 https://github.com/jnichor/creador_videos_aiWrote 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/jnichor/creador_videos_ai/creador_videos_ai)<a href="https://agentmods.dev/skills/jnichor/creador_videos_ai/creador_videos_ai"><img src="https://agentmods.dev/badge/skills/jnichor/creador_videos_ai/creador_videos_ai/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/jnichor/creador_videos_ai/creador_videos_ai"><img src="https://agentmods.dev/badge/skills/jnichor/creador_videos_ai/creador_videos_ai.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 | $0.00160 | $0.09734 |
| Opus 5 | $0.00080 | $0.04867 |
| Sonnet 5 | $0.00032 | $0.01947 |
| Haiku 4.5 | $0.00016 | $0.00973 |
Grade A, and why
creador_videos_ai 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
14. **Verify each subpage iframe-embeds before adding to the tour.** Check `X-Frame-Options` and `Content-Security-Policy: frame-ancestors` with `curl -I <url>`. If a page is blocked, FALL BACK to a static full-page scre How it starts
The opening of the file, as written. The whole thing — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
creador_videos_ai — Marketing Video Pipeline
Turns any public website URL into a polished marketing MP4 by combining a self-playing HTML cinematic tour (live <iframe> scrolled by CSS keyframes) with whisper.cpp-derived burned-in subtitles, then renders to multiple social-media formats.
Source of truth: the project's PIPELINE.md has the full workflow with diagrams, FFmpeg flag rationale, voice presets per language, and troubleshooting. Read it before authoring a new template if the user is starting from scratch. This skill is the trigger + the rules; the doc has the long-form detail.
When to invoke
Trigger this skill when the user asks for any of:
- "Make a marketing/promo video for this site/URL"
- A cinematic scrolling tour of a webpage with voice off
- Burned-in subtitles synced to a voice over
- Multi-format social media video (square / vertical / horizontal) from a website
- "Vídeo para Reels/TikTok/LinkedIn" tied to a website URL
Do NOT invoke for:
- Animated infographics, kinetic typography, data-driven bar charts (different stack — HyperFrames or Remotion)
- Podcast / audio editing
- Videos longer than 60 seconds (out of scope — the pipeline is tuned for 25–35 s)
- Pure motion graphics with no real-website footage
Inputs to gather BEFORE starting
Confirm with the user; do NOT invent these. Six are REQUIRED — do NOT proceed without all of them. Claude cannot generate voice off or music itself; the user must produce these and place the files where Claude can read them.
Required (6) — block until provided
- Live website URL — must be public, no login walls, no localhost, no
X-Frame-Options: DENY - Brand logo PNG with transparent background — ~1500×500 or square. File path required (e.g.
videos/<client>-logo.png) - Contact info for the CTA — phone, WhatsApp, or email
- Voice script — text in any language, 45–55 words for ~25 s voice off. Used both to write the captions and as reference for the user's TTS generation
- Voice off MP3 —
videos/voiceover.mp3already generated. Claude does NOT have ElevenLabs credentials and cannot generate this. If the user doesn't have it, walk them through the ElevenLabs steps (Voice presets table in section 9.1) and STOP — wait for them to download the MP3 and confirm before continuing - Background music MP3 —
videos/music.mp3already downloaded. Royalty-free source (YouTube Audio Library, Pixabay, Mixkit). If the user doesn't have one, give them search filters (Cinematic / Corporate / Inspirational, 1+ min) and STOP — wait for the file before continuing
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 · 577 lines · 160 tokens per session scan A 08dba561df59
creador_videos_ai is a skill published in the GitHub repository jnichor/creador_videos_ai (3 stars, last pushed 4mo ago), licensed MIT. It adds 160 tokens to every session and 9,734 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
demo-video
Produce a polished, ScreenStudio-style 60fps product demo video of a web app with a tiny, dependency-light pipeline — Playwright frame capture + a multiprocess Pillow compositor streaming into ffmpeg (no Node/Remotion). Drives the app one step per frame so playback is true 60fps regardless of capture speed, then…
acestep
AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem…
ffmpeg
Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.
moviepy
Python video composition with moviepy 2.x — overlaying deterministic text on AI-generated video (LTX-2, SadTalker), compositing clips, single-file build.py video projects. Use when adding labels/captions/lower-thirds to LTX-2 or SadTalker outputs, building short ad-style spots in pure Python without Remotion, or doing…
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
elevenlabs
Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.