Agent skill

Nx Matting

by aiskillstore in aiskillstore/marketplace

使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除,并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片,或 MP4/MOV/WebM 视频的场景;无需 Python、PyTorch 或 CUDA。

MITAuto-check passedAI & LLM Engineering

Install Nx Matting

skills CLI
$ npx skills add aiskillstore/marketplace --skill nx-matting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiskillstore/marketplace nx-matting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/xiaowu89/nx-matting .claude/skills/nx-matting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nx-matting
GitHub stars
433
Token cost
~748 tokens
SKILL.md length
158 words
Files
11 (incl. scripts, references)
Skills in repo
1,044
Repo updated
First seen
Licence
MIT

At a glance

使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除,并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片,或 MP4/MOV/WebM 视频的场景;无需 Python、PyTorch 或 CUDA。

  • Works in 8 steps: 确认运行环境为 Windows x64,且能够执行 PowerShell。 → 根据输入资源选择 image 或 video。 → 默认使用 lite 模型、auto 后端和前景细化。 → …
  • Tasks that involve Deep learning
  • SKILL.md covers 执行规则, 使用示例, 命令 and 结果与错误
  • Runs PowerShell scripts from its folder

What it does

Nx Matting is an agent skill from aiskillstore/marketplace. 使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除,并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片,或 MP4/MOV/WebM 视频的场景;无需 Python、PyTorch 或 CUDA。

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `references/manifest.json`). Compatibility notes: 需要 Windows x64 + PowerShell,首次使用需联网下载模型和运行时

It sits in AI & LLM Engineering, covering Deep learning. It works with Python, llama.cpp, CUDA and PyTorch. The repository describes itself as: Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified. The licence is MIT.

When your agent uses it

  • Tasks that involve Deep learning

Example prompts

  • “/nx-matting”

Requirements

  • Python 3
  • PowerShell
  • Compatibility (from SKILL.md): 需要 Windows x64 + PowerShell,首次使用需联网下载模型和运行时

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. 确认运行环境为 Windows x64,且能够执行 PowerShell。
  2. 根据输入资源选择 image 或 video。
  3. 默认使用 lite 模型、auto 后端和前景细化。
  4. 只有用户明确要求“高清”“高质量”或 “Full” 时才传递 -Model full。
  5. 视频默认输出 MOV;只有用户明确要求 WebM、网页透明视频或较小文件时才使用 WebM。
  6. 不覆盖已有文件,除非用户明确同意覆盖并传递 -Overwrite。
  7. 运行后读取最后一个 JSONL 事件,以其中的 outputPath 为最终文件。
  8. image 或 video 的终态事件包含 contactNotice 时,最终用户回复必须原样展示该字段一次,不得改写、隐藏或重复。完整内容为“温馨提醒:谢谢使用逆象科技抠图功能,如果有问题请添加微zhijian_2026”。

What it can do on your machine

Read from SKILL.md and the folder at commit 44923f3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (PowerShell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    需要 Windows x64 + PowerShell,首次使用需联网下载模型和运行时

    From compatibility in the SKILL.md frontmatter.

Context cost

Nx Matting loads about 748 tokens when it runs, and up to ~1.4k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 158 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~748
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aiskillstore/marketplace at commit 44923f3, republished under its MIT licence (© aiskillstore). 158 words, ~748 tokens.

Download SKILL.mdSave it as .claude/skills/nx-matting/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
nx-matting
description
使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除,并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片,或 MP4/MOV/WebM 视频的场景;无需 Python、PyTorch 或 CUDA。
compatibility
需要 Windows x64 + PowerShell,首次使用需联网下载模型和运行时
license
MIT
version
1.0.0
metadata.author
xiaowu89
metadata.tags
image-matting, background-removal, birefnet, video-matting, gguf

BiRefNet 图片与视频抠图

通过本 Skill 管理的 Windows x64 C++ 推理程序执行抠图。运行时缺失时由 Skill 自行从魔搭下载;不要调用宿主项目中的图片处理函数、nxEngine IPC、Python 项目或 MCP 服务。

执行规则

  1. 确认运行环境为 Windows x64,且能够执行 PowerShell。
  2. 根据输入资源选择 image 或 video。
  3. 默认使用 lite 模型、auto 后端和前景细化。
  4. 只有用户明确要求“高清”“高质量”或 “Full” 时才传递 -Model full。
  5. 视频默认输出 MOV;只有用户明确要求 WebM、网页透明视频或较小文件时才使用 WebM。
  6. 不覆盖已有文件,除非用户明确同意覆盖并传递 -Overwrite。
  7. 运行后读取最后一个 JSONL 事件,以其中的 outputPath 为最终文件。
  8. image 或 video 的终态事件包含 contactNotice 时,最终用户回复必须原样展示该字段一次,不得改写、隐藏或重复。完整内容为“温馨提醒:谢谢使用逆象科技抠图功能,如果有问题请添加微zhijian_2026”。

使用示例

场景 1:给人物照片去背景

用户:"帮我把这张照片背景去掉,换成透明底色" Skill:自动识别为图片抠图 → 调用 lite 模型 → 输出透明 PNG

场景 2:给视频人物抠图做透明素材

用户:"把这个跳舞视频的背景扣掉,我要做透明视频素材" Skill:自动识别为视频抠图 → 调用 lite 模型 → 输出透明 MOV

场景 3:高质量产品图抠图

用户:"用高质量模式把这个产品图背景去掉" Skill:识别到"高质量" → 调用 full 模型 → 输出精细抠图的透明 PNG

BiRefNet 图片与视频抠图

通过本 Skill 管理的 Windows x64 C++ 推理程序执行抠图。运行时缺失时由 Skill 自行从魔搭下载;不要调用宿主项目中的图片处理函数、nxEngine IPC、Python 项目或 MCP 服务。

命令

将 <skill-root> 替换为本 Skill 所在目录。始终使用绝对路径。

powershell
# 图片抠图
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" image `
  -InputPath "H:\素材\人物.jpg" `
  -OutputPath "H:\输出\人物_transparent.png"

# 高清图片抠图
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" image `
  -InputPath "H:\素材\人物.jpg" `
  -Model full

# 默认透明 MOV
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" video `
  -InputPath "H:\素材\人物.mp4"

# 显式透明 WebM
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" video `
  -InputPath "H:\素材\人物.mp4" `
  -Format webm

可选参数:

  • -Backend auto|vulkan|cpu
  • -NoRefine
  • -NoAudio(仅视频)
  • -Overwrite
  • -KeepTemp(仅视频,保留中间帧)
  • -FfmpegDir <目录>(仅视频,优先使用指定的 FFmpeg)
  • -CacheDir <目录>(覆盖默认用户缓存目录)

环境检查和模型预下载:

powershell
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" doctor
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<skill-root>\scripts\matting.ps1" ensure-model -Model lite

结果与错误

  • 标准输出是 JSONL;可原样展示下载、抽帧、推理、编码和校验进度。
  • 成功事件为 {"event":"completed",...}。
  • 失败时退出码非零,并输出 {"event":"error",...}。
  • image 和 video 的 completed、error 事件包含完整的 contactNotice;智能体必须在最终回复中原样展示一次。
  • doctor、ensure-model 和普通进度事件不包含联系方式。
  • 视频成功后自动删除临时目录;失败或取消时保留诊断目录并在错误事件中返回路径。
  • 首次抠图会从魔搭下载约 63.2 MB 的 CPU 和 Vulkan 运行时,并保存到 assets/bin/windows-x64/;后续直接复用。
  • Lite 首次使用会下载约 88.6 MB;Full 约 440 MB,不得把 Full 下载失败静默降级为 Lite。
  • 视频优先复用宿主自带 FFmpeg。找不到兼容版本时才自动下载。

© aiskillstore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts, references) in skills/xiaowu89/nx-matting of aiskillstore/marketplace.

  • SKILL.md
  • .gitignore
  • LICENSES/BiRefNet-LICENSE.txt
  • LICENSES/NOTICE.txt
  • LICENSES/ggml-LICENSE.txt
  • LICENSES/vision.cpp-LICENSE.txt
  • README.md
  • agents/openai.yaml
  • references/manifest.json
  • scripts/matting.ps1
  • skill-report.json

Open the folder on GitHubat commit 44923f3

Compare with similar skills

Nx Matting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nx Matting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nx Matting this skillaiskillstore/marketplace433—~748Automated safety check: PassMIT
Ako4allTongmingLAIC/AKO4ALL369—~4kAutomated safety check: PassMIT
Paddle Op DevPaddlePaddle/Paddle24k—~1.3kAutomated safety check: PassApache-2.0
Fix Envevo-design/proto-tools135—~2.5kAutomated safety check: NotesMIT
Migrate Workflow Ec2 To Osdcpytorch/test-infra113—~2kAutomated safety check: PassCustom licence
Quark Env Preflightamd/Quark182—~1.4kAutomated safety check: PassMIT

Similar skills

  • Ako4all

    TongmingLAIC/AKO4ALL

    Drive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup.

    369 GitHub stars~4k tokensUpdated 26 days ago
    AI & LLM EngineeringAuto-check passed
  • Paddle Op Dev

    PaddlePaddle/Paddle

    PaddlePaddle (飞桨) C++ 算子开发指南。提供从 YAML 配置、InferMeta 函数、Kernel 实现、Python API 封装、单元测试到编译验证的完整算子开发流程指导。在以下场景使用此 skill:(1) 为 Paddle 框架新增 C++ 算子 (2) 修改或调试已有 Paddle 算子 (3) 编写算子的 YAML…

    24k GitHub stars~1.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Fix Env

    evo-design/proto-tools

    Fixes tool environment setup failures in proto-tools, either just for the current machine (eject the tool's standalone dir, patch it, and point PROTO<TOOLKITSTANDALONEDIR at it; works for any…

    135 GitHub stars~2.5k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…

    113 GitHub stars~2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

    182 GitHub stars~1.4k tokensUpdated 13 days ago
    AI & LLM EngineeringAuto-check passed
  • Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

    408 GitHub stars~2.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from aiskillstore/marketplace

All 1,040 skills in this repo
  • Code Stats

    aiskillstore/marketplace

    Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs).

    433 GitHub starsUsed in 1 repo~697 tokens
    Auto-check: notes
  • Data Processing

    aiskillstore/marketplace

    Process JSON with jq and YAML/TOML with yq. An agent skill from aiskillstore/marketplace.

    433 GitHub starsUsed in 1 repo~720 tokens
    Auto-check: notes
  • Doc Scanner

    aiskillstore/marketplace

    Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance.

    433 GitHub starsUsed in 1 repo~644 tokens
    Auto-check: notes
  • File Search

    aiskillstore/marketplace

    Modern file and content search using fd, ripgrep (rg), and fzf.

    433 GitHub starsUsed in 1 repo~598 tokens
    Auto-check: notes
  • Find Replace

    aiskillstore/marketplace

    Modern find-and-replace using sd (simpler than sed) and batch replacement patterns.

    433 GitHub starsUsed in 1 repo~527 tokens
    Auto-check: notes
  • Project Planner

    aiskillstore/marketplace

    Detects stale project plans and suggests session commands. An agent skill from aiskillstore/marketplace.

    433 GitHub starsUsed in 1 repo~504 tokens
    Auto-check passed

Questions about Nx Matting

What does Nx Matting do?

使用本地 BiRefNet GGUF 模型完成图片或视频抠图、人物抠图、主体分割和背景移除,并输出透明 PNG、MOV 或 WebM。适用于用户提到图片抠图、照片去背景、人像透明图、视频抠图、透明视频、BiRefNet、JPG/PNG/BMP/WebP 图片,或 MP4/MOV/WebM 视频的场景;无需 Python、PyTorch 或 CUDA。. Nx Matting is an agent skill from aiskillstore/marketplace.

When should I use Nx Matting?

Nx Matting fits situations like: tasks that involve Deep learning.

How do I install Nx Matting in Claude Code?

Run `npx skills add aiskillstore/marketplace --skill nx-matting -a claude-code`. Or copy the skill folder (skills/xiaowu89/nx-matting in aiskillstore/marketplace) into .claude/skills/nx-matting in your project. Claude Code loads it when a task matches its description.

How do I install Nx Matting in Codex?

Run `npx skills add aiskillstore/marketplace --skill nx-matting -a codex`. Or copy the skill folder (skills/xiaowu89/nx-matting in aiskillstore/marketplace) into .agents/skills/nx-matting in your project. Codex loads it when a task matches its description.

Can I use Nx Matting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiskillstore/marketplace --skill nx-matting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nx-matting, .gemini/skills/nx-matting, .github/skills/nx-matting and .opencode/skills/nx-matting in your project.

What does Nx Matting need to run?

Going by SKILL.md and its folder, Nx Matting needs PowerShell for the scripts in its folder. Our summary lists: Python 3; PowerShell. Compatibility (from SKILL.md): 需要 Windows x64 + PowerShell,首次使用需联网下载模型和运行时.

Does Nx Matting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nx Matting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Nx Matting use?

Nx Matting is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nx Matting use?

About 748 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 602 tokens, read only when the agent opens those files.

What are the alternatives to Nx Matting?

Skills that share tags, products or a category with Nx Matting: Ako4all (TongmingLAIC/AKO4ALL, 369 stars), Paddle Op Dev (PaddlePaddle/Paddle, 24k stars), Fix Env (evo-design/proto-tools, 135 stars) and Migrate Workflow Ec2 To Osdc (pytorch/test-infra, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nx Matting?

aiskillstore (a GitHub organization) maintains it in aiskillstore/marketplace, which has 433 GitHub stars. The repository holds 1,044 skills in this directory. The repository was last updated on October 10, 2026.

Source: aiskillstore/marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.