Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI agent developers, automation builders, AI-curious readers, and any developer wiring an AI coding agent to video understanding -- and who can pair oxbshw/watch-skill with Node 18+ + ffmpeg + yt-dlp + deno for the engine surface, uv (auto-installed) for the Python surface, an OpenAI API key for Whisper fallback transcription, and the `watch-skill setup --yes` auto-registration path for
Who should use it
Who should skip it
Consider oxbshw/watch-skill lower priority if you already have a working solution in this category.
About this signal
oxbshw/watch-skill is tracked by RepoRadar as a mcp server (13 tools) + cli + re in the MCP Video Watching Engine section. It was first seen on 2026-07-07 and last updated on 2026-07-07. The current verdict is 'try now' with a Silver tier and easy setup difficulty. oxbshw/watch-skill leads on workflow potential (9.4) and setup ease (8.8); its lowest signal is maturity (5.8), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned oxbshw/watch-skill a composite score of 7.9 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The 92* / 8-fork repo is at active maintenance but the auto-registration flow writes MCP config into every agent it finds (Claude Code / Claude Desktop / Cursor / Codex CLI / Windsurf / Gemini CLI) -- the installer backs up anything it touches; but the consumer SHOULD review the backup policy and decide which agents to register (use `--no` to opt out per-agent) before running on a multi-agent machine; the install is opt-in via `curl | sh` but the agent registration happens automatically after install -- the consumer SHOULD pin the version and review the auto-registration list; yt-dlp covers 1800+ sites including adult content platforms.