Add claude-video-plus to Agent Skills#503
Open
abe238 wants to merge 1 commit into
Open
Conversation
Adds an entry for the claude-video-plus skill (/watch) in the Agent Skills section, linking to github.com/abe238/claude-video-plus. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CwpMQWJ9SvysUvCvQFPk4R
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds claude-video-plus to the 🧠 Agent Skills section.
What it does: A Claude Code skill (
/watch) that answers a question about a video by retrieving only the chapters, numeric facts, and on-screen moments that actually answer it, instead of sampling the whole timeline.Install:
npx skills add abe238/claude-video-plus -g/plugin marketplace add abe238/claude-video-plusthen/plugin install watch@claude-video-plusWhy it fits the list's bar: A sealed, receipt-gated benchmark matched the original pipeline's blind-judged answer quality (8.83 vs 8.80) at ~56% fewer tokens. It ships 338 deterministic tests and fails open, reverting to the original pipeline on no captions, a local file, a short video, or any error.
Attribution: An attributed MIT fork of bradautomates/claude-video, with upstream authorship preserved.
Single-line addition to the Agent Skills list; no existing entries were reformatted.