Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/remove-bgWrote 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/zju-real/easel/remove-bg)<a href="https://agentmods.dev/skills/zju-real/easel/remove-bg"><img src="https://agentmods.dev/badge/skills/zju-real/easel/remove-bg.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00168 | $0.01004 |
| Opus 5 | $0.00084 | $0.00502 |
| Sonnet 5 | $0.00034 | $0.00201 |
| Haiku 4.5 | $0.00017 | $0.00100 |
Grade A, and why
remove-bg 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.
What it actually says
图片去背景 / 抠图换背景
用 rembg（AI 语义分割）把主体抠出，输出透明 PNG 或换新背景。无需绿幕。全部走
skills/shared/scripts/remove_bg.py。
绿幕视频抠像见 green-screen；电商视觉方案见 ecom-details-image； 常规缩放/裁切/水印见 image-editing。
前置
首次运行自动下载模型（~4-170MB，视模型而定），需外网代理（脚本读 EASEL_PROXY/http(s)_proxy，未设则直连）。先自检：
python skills/shared/scripts/remove_bg.py check
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 图片 | 是 | 要抠图的图片（没给就问） |
| 输出背景 | 否 | 透明（默认）/ 纯色 / 换图片背景 |
| 模型 | 否 | 通用 / 人像 / 精细，见下表 |
输出（outputs/主题名/）
- 抠好的图片（透明用
.png） - 报告：所用模型、背景形态
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/remove_bg.py（remove -h 看参数）。
# 透明背景（务必输出 .png）
python skills/shared/scripts/remove_bg.py remove -i product.jpg \
-o outputs/主题名/cutout.png
# 电商白底主图
python skills/shared/scripts/remove_bg.py remove -i product.jpg \
-o outputs/主题名/white.jpg --bg-color white
# 换新场景背景
python skills/shared/scripts/remove_bg.py remove -i person.jpg \
-o outputs/主题名/scene.png --bg-image scene.jpg
# 人像 + 毛发边缘细腻
python skills/shared/scripts/remove_bg.py remove -i portrait.jpg \
-o outputs/主题名/cut.png --model u2net_human_seg --alpha-matting
模型选择
| 模型 | 适用 |
|---|---|
u2net（默认） |
通用主体 |
u2netp |
轻量快速（质量略低） |
u2net_human_seg |
人像专用 |
isnet-general-use |
更精细的通用分割 |
silueta |
体积小的通用模型 |
抠不干净/边缘毛糙时：换更精细的模型，或加 --alpha-matting（慢但边缘更好，适合头发/毛绒）。
规则
- 要透明背景必须输出 .png（jpg 不支持透明，脚本会自动改白底并提示）。
- 电商主图用
--bg-color white；换场景用--bg-image（自动等比覆盖裁切）。 - 人像优先
u2net_human_seg，商品/通用用u2net。 - 抠图质量取决于主体与背景对比度；复杂/低对比图无法保证完美。
- 产物统一进
outputs/主题名/。
参考来源
去背景用 rembg（u2net 系列显著性目标检测/分割模型）+ onnxruntime CPU 推理，是无 GPU 抠图的 主流方案。换背景合成用 Pillow alpha_composite。把模型加载、代理注入、背景合成封装成确定性脚本。
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 · 81 lines · 168 tokens per session scan A 6a5d23ee1f2c
remove-bg is a skill published in the GitHub repository ZJU-REAL/Easel (411 stars, last pushed yesterday), licensed Apache-2.0. It adds 168 tokens to every session and 1,004 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chart-visualization
Generate charts: select type, extract data, render image.
ppt-generation
Generate PPTX presentations from slide plan + content.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…