jevbooks

← All projects

youtube-sponsor-skip

AnatoliyLikarchuk/youtube-sponsor-skip

Chrome/Safari extension that auto-skips Russian YouTube sponsor segments via Jev.

Other0.27Runner-up: Agent DecisionsFail open, fail closed
Automated README summary

Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Chrome and Safari (macOS) extension that finds sponsor integrations read aloud in Russian-language YouTube videos and automatically skips them, using subtitles rather than manual SponsorBlock markup, so it also works on small channels.

How it uses Jev

Russian subtitles (manual or auto) are split into 20-second chunks; Jev answers "ad" or "content" per chunk. Adjacent ad chunks are merged, boundaries refined in a second ~5-second pass, and the player skips the segment with a "Return" hint. Results are cached.

Primitives:choice

Technique worth stealing

Chunk subtitles into fixed windows, classify each with a typed choice, then merge and refine boundaries in a second pass.

Try it

Load the unpacked extension in chrome://extensions, paste an OpenRouter sk-or- key in options, open a Russian YouTube video.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.92
  • Shows a System One patternnot found in the excerpt0.14
  • Describes handling uncertaintynot found in the excerpt0.04
  • Reports measured numbersnot found in the excerpt0.03
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalnot found in the excerpt0.14
  • Is a replica of the modelnot found in the excerpt0.02
  • Solves a common problem (0–2)score on a 0–2 scale0.95 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.92Shows a System One pattern0.14Describes handling uncertainty0.04Reports measured numbers0.03Is a runnable tool0.98Top-10 learning shortlist signal0.14Is a replica of the model0.0200.51Solves a common problem (0–2)0.95 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.73Check-up0.68Viewfinder0.59Funnel0.47Inspection0.28Scorecard0.21Flight recorder0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 24 Oct 2026.