Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HK-hub/AgentSkills --skill bangumi-framesgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hk-hub/agentskills/bangumi-frames)<a href="https://agentmods.dev/skills/hk-hub/agentskills/bangumi-frames"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/bangumi-frames.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.01909 |
| Opus 5 | $0.00055 | $0.00955 |
| Sonnet 5 | $0.00022 | $0.00382 |
| Haiku 4.5 | $0.00011 | $0.00191 |
Grade A, and why
bangumi-frames scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to bangumi-frames — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 intocharacters/char_NN/. - with
--ref DIR(one-vs-rest mode) — given ONE character's reference folder, pull every crop in the video that matches it intomatched/, 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.
Bundled resources
| Resource | Read it when |
|---|---|
references/pipeline.md |
Tuning a stage — download (--height/--prefer), extract (--scene/--interval/--dedup/--skip), --clean (OCR+LaMa subtitle/watermark removal), classify (--conf/--min-area); feature caching; the CPU/CoreML rule; --redo |
references/modes.md |
Choosing/tuning the two modes — mode 1 cluster (--eps/--min-samples) vs mode 2 one-vs-rest (--ref-eps, the distance-band histogram, the compressed-embedding threshold lore); full output layout |
scripts/bangumi_frames.py |
The entry point (all stages + both modes) |
scripts/remove_overlay.py |
Standalone subtitle/watermark removal on a frame dir or single image |
Prerequisites
ffmpegon PATH;yt-dlpon PATH for downloads (a local-file input skips download).- Python 3.9+,
pip install dghs-imgutils(first run pulls ~300 MB of models from HuggingFace, then cached locally). - A Bilibili cookie (Netscape
cookies.txt). Resolution order:--cookies>$BILIBILI_COOKIES>~/bb_up/bb_cookies/www.bilibili.com_cookies.txt. 1080p+ / premium episodes need a cookie with membership; a preview-only download means the cookie lacks access to that episode. Local-file input needs no cookie. - Run the CCIP step on CPU — do not set
ONNX_MODE=CoreML(CCIP crashes; the script pops it before clustering/matching). Person detection is fine on CoreML. - (Only for
--clean)pip install rapidocr-onnxruntime simple-lama-inpainting. - (Only for
--engine pyscenedetect)pip install scenedetect.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 111 lines · 110 tokens per session scan A 00b7df529a73
bangumi-frames is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 20d ago), licensed MIT. It adds 110 tokens to every session and 1,909 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bangumi-frames, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
minimax-h3-keyframe-video-prompt
Narrow downstream MiniMax H3 specialist for pure I2VA, FL2VA, and L2VA boundary-frame prompts. Use only after minimax-h3-creative-director verifies that the user explicitly declared the images as literal first/last frames and that they have no character, identity, person, object, costume, scene, style, voice, action…
minimax-h3-reference-video-prompt
Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role. Use the official six-section full-reference format for character/person/object consistency, scene/style/action/camera/storyboard/voice/audio…
minimax-h3-multishot-planner
Non-skippable planning-only MiniMax H3 subskill used by minimax-h3-creative-director before final prompt formatting. Invoke when the user explicitly requests multiple shots, scenes, cuts, montage, or shot-by-shot design, or when a video of at least 10 seconds has no declared single-shot/multishot preference and the…
minimax-h3-text-video-prompt
Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format. Use after minimax-h3-creative-director routes a request with no image, video, or audio reference asset, or when this skill is explicitly invoked for a text-only idea, script, or storyboard requiring an…
minimax-h3-creative-director
Primary mandatory entrypoint for every MiniMax H3 video-generation request. Use before any other H3 skill for creation, animation, extension, editing, restyling, reference, or prompt review. It reads the official h3-prompt-writing specification, defaults image-based work to full-reference consistency, permits pure…
minimax-h3-prompt-reviewer
Downstream MiniMax H3 specialist that audits, repairs, and rewrites T2VA, I2VA, FL2VA, L2VA, and full-reference prompts into an official structured format. Use after minimax-h3-creative-director routes an existing prompt for diagnosis or repair, or when explicitly invoked for formatting, timeline, camera, dialogue…