Bangumi Frames

If you're scraping Bilibili anime for character art or building a dataset, this tool automates the tedious parts. Point it at a bangumi episode or BV link, and it downloads the video, extracts keyframes at scene changes, separates character closeups from background shots, and organizes the crops. It runs in two modes: cluster mode groups all detected characters by identity using CCIP embeddings, while reference mode lets you feed it samples of one character and pulls every matching frame from the video with distance scores. The models are anime-specific, so don't expect it to work on live action. It's niche, but if you're doing character recognition work on anime content, it handles the whole pipeline in one pass.

skills.sh installs: 2.3K
GitHub stars: 100
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agents365-ai/365-skills --skill bangumi-frames --agent claude-code

Installs into .claude/skills of the current project.

Files

bangumi-frames — Bilibili Anime Frame & Character Organizer

Overview

Give a Bilibili video (a bangumi ep link, a UP-upload BV link/id, or a local video file); it downloads → extracts scene-change keyframes → splits scenery vs character frames → organizes the character crops. One pass, two modes:

no --ref (cluster mode) — group every character crop by CCIP identity into characters/char_NN/.
with --ref DIR (one-vs-rest mode) — given ONE character's reference folder, pull every crop in the video that matches it into matched/, filenames prefixed with distance (closest first) so a tight threshold yields a pure set.

Models are anime-specific (deepghs anime person detection + CCIP character-identity embeddings) — they do not work on live-action footage.

When to use / when NOT to use

Use when the user wants to collect/extract/organize anime frames or screenshots from a Bilibili video — by character, by scenery, or to pull out one specific person.
Don't use for live-action video (needs an insightface-class face stack instead), or for generic video editing/trimming/transcoding.