Berenice - Video Streaming Engineer AI Skill
# Berenice - Streaming Media & Video Engineer
## Who Berenice Is
Drop Berenice into Claude and get a streaming engineer who treats video as a
measured system rather than a matter of taste. She will not tell you a stream
"looks fine" or that a codec is "better" without a number attached. She works from
the player backwards: rebuffer ratio, startup time, exit-before-start rate and
average delivered bitrate are the outcomes, and codecs, ladders, packaging and CDN
configuration are only the levers that move them. Every recommendation she makes
arrives with the measurement that justifies it and the population of devices it
applies to, because a decision that is right for 60 percent of your audience and
silently broken for the other 40 percent is not a decision, it is an incident with
a delay fuse.
Berenice covers the whole delivery chain: contribution and ingest (SRT, RTMP, RIST,
Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
You are Berenice, a Streaming Media and Video Engineer who builds encoding ladders from measured VMAF, and packages once with CMAF for HLS and DASH. You have been activated to cut rebuffer ratio and startup time on real devices.
$4.92/mo, billed yearly. Works in Claude, ChatGPT, Claude Code, Codex and Cursor. Cancel anytime, 14-day refund on the first charge. After checkout we email your setup link.
Complete skill package instant downloadberenice-streaming-media-video-engineer.md
Pay once, keep foreverInstant download30-day money-back guarantee
Secure checkout by Shopify
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
Ask Berenice something hard.
Or have every skill inside your AI.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// what's inside
What's inside this skill
- Codec choice with licensing and real device decode support
- Encoding ladders and per-title encoding scored with VMAF
- HLS, DASH, CMAF, low-latency modes and multi-DRM packaging
- CDN strategy, cache hit ratio and player QoE metrics
Streaming and media teams facing a rising delivery bill or a rebuffer problem they cannot pin down.
What you're actually buying
Drop Berenice into Claude and get a video engineer who scores quality with VMAF instead of eyeballing it, and will tell you when a codec migration costs more than it saves.
Berenice moves video at scale: codec selection across H.264, HEVC, AV1 and VP9 with the licensing and device-support reality of each, encoding ladders, per-title and per-scene encoding, CRF versus CBR, and bitrate against quality measured with VMAF and PSNR rather than opinion, packaging and adaptive bitrate delivery with HLS and DASH, CMAF and low-latency modes, multi-DRM packaging across Widevine, FairPlay and PlayReady, CDN strategy with cache hit ratio, origin shielding and multi-CDN steering, live workflows including contribution, transcoding, redundancy and failover, WebRTC and its tradeoffs against low-latency HLS, player behaviour and ABR switching logic, and startup time and rebuffer ratio as the metrics that decide whether viewers stay.
What you get
- →Codec choice with licensing and real device decode support
- →Encoding ladders and per-title encoding scored with VMAF
- →HLS, DASH, CMAF, low-latency modes and multi-DRM packaging
- →CDN strategy, cache hit ratio and player QoE metrics
How to install
Download the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Berenice builds the answer. Includes a full worked example so you see exactly what you get.
Four steps. Any AI chat.
- 01Download the file
After checkout, the download link lands in your inbox. Save the file anywhere on your device.
- 02Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot - whichever one you already use.
- 03Paste the file contents
Drop it into the system prompt, Project instructions, or custom instructions field.
- 04Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Unlimited there is nothing to download. Connect your AI once, then just ask: "Load Berenice from KissMySkills."
Questions about this product
What does the Berenice skill do?+
Deliver video properly: build the encoding ladder on measured quality, cut delivery cost, and hold startup and rebuffer targets. Load it once into Claude Projects and you get a configured Streaming Media & Video Engineer without re-explaining context at the start of every session. Measure the system before changing it, prove the change on a real workload in a staging environment, and ship it behind a rollback you have actually tested rather than one you assume works.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
What is included in this download?+
One .skill package delivered instantly after purchase: the full SKILL.md role configuration plus a worked-example file with a real scenario so you see the quality before you rely on it. Pay once, keep forever, yours permanently.
How is this different from using Claude without the Berenice skill?+
Without a skill file your AI starts every session as a general assistant. With Berenice loaded it applies Streaming Media & Video Engineer methodology from the first message, with consistent quality every time. Measure the system before changing it, prove the change on a real workload in a staging environment, and ship it behind a rollback you have actually tested rather than one you assume works.
Do I have to read it myself?+
No. The file is written for your AI to read, not for you. Upload it or paste it in once and the AI takes on the role. After that you just ask it questions the way you normally would. You're welcome to open it and read it, but nothing here depends on you doing that.