Ito Inference
affaan-m/ECC
Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest.
A skill your agent uses for RobustVideoMatting human video matting workflows: MattingNetwork APIs, inference conversion, training data setup, and RVM evaluation metrics.
GPL-3.0Auto-check passed
Install Robust Video Matting
$ npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill robust-video-matting --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/robust-video-matting .claude/skills/robust-video-matting && rm -rf skills-srcUse ~/.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/
Install the "robust-video-matting" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-matting into .claude/skills/robust-video-matting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "robust-video-matting", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-mattingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill robust-video-matting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/robust-video-matting .agents/skills/robust-video-matting && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "robust-video-matting" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-matting into .agents/skills/robust-video-matting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "robust-video-matting", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill robust-video-matting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/robust-video-matting .cursor/skills/robust-video-matting && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "robust-video-matting" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-matting into .cursor/skills/robust-video-matting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "robust-video-matting", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/robust-video-matting--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill robust-video-matting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/robust-video-matting .gemini/skills/robust-video-matting && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "robust-video-matting" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-matting into .gemini/skills/robust-video-matting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "robust-video-matting", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill robust-video-mattingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/robust-video-matting .github/skills/robust-video-matting && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "robust-video-matting" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-matting into .github/skills/robust-video-matting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "robust-video-matting", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill robust-video-matting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/robust-video-matting .opencode/skills/robust-video-matting && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "robust-video-matting" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/robust-video-matting into .opencode/skills/robust-video-matting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "robust-video-matting", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
robust-video-matting- GitHub stars
- 331
- Token cost
- ~1.3k tokens
- SKILL.md length
- 480 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
A skill your agent uses for RobustVideoMatting human video matting workflows: MattingNetwork APIs, inference conversion, training data setup, and RVM evaluation metrics.
- RobustVideoMatting human video matting workflows: MattingNetwork APIs
- SKILL.md covers First route the task, Install and import orientation, Shared references and helpers and Key operating constraints, plus 1 more section
- Runs Python scripts from its folder; calls pip and python
- Inference conversion
What it does
Robust Video Matting is an agent skill from VectorSpaceLab/AREX-Skill. Use for RobustVideoMatting human video matting workflows: MattingNetwork APIs, inference conversion, training data setup, and RVM evaluation metrics.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/model-catalog.md`, `references/repo-provenance.md` and `references/repo-routing-metadata.json`).
The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is GPL-3.0.
When your agent uses it
- RobustVideoMatting human video matting workflows: MattingNetwork APIs
- Inference conversion
- Training data setup
- RVM evaluation metrics
Example prompts
- “/robust-video-matting”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. 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/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pippython
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
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.
Context cost
Robust Video Matting loads about 1.3k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 480 words of instructions outside code blocks.
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 VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its GPL-3.0 licence (© VectorSpaceLab). 480 words, ~1,309 tokens.
Download SKILL.mdSave it as
.claude/skills/robust-video-matting/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- robust-video-matting
- description
- Use for RobustVideoMatting human video matting workflows: MattingNetwork APIs, inference conversion, training data setup, and RVM evaluation metrics.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- GPL 3.0
RobustVideoMatting Repo Skill
Use this skill when a task involves Robust Video Matting (RVM), the repository for robust human video matting with temporal guidance. RVM predicts foreground RGB and alpha mattes from ordinary human videos, recycles recurrent states over time, and provides source-checkout/TorchHub workflows for PyTorch inference, training, and evaluation.
First route the task
- Use sub-skills/model-api for
MattingNetwork,mobilenetv3vsresnet50, refiners, tensor shapes, recurrent states,segmentation_pass, or safe synthetic forward checks. - Use sub-skills/inference-workflows
for loading checkpoints or TorchHub models, calling
convert_video, running image/video conversion, choosing output alpha/foreground/composition, or using TorchScript, ONNX, TensorFlow, TensorFlow.js, and CoreML artifacts. - Use sub-skills/training-data for
VideoMatte240K, ImageMatte, background, COCO, SPD, or YouTubeVIS layouts;
DATA_PATHS; augmentations/losses; and the official four-stage training commands. - Use sub-skills/evaluation-tools for LR/HR matting metrics, prediction/ground-truth directory structures, synthetic evaluation composite scripts, and speed benchmark caveats.
Install and import orientation
This repository snapshot is not a normal pip-installable distribution. It has
no setup.py or pyproject.toml; local source workflows import modules such as
model, inference, dataset, and evaluation from a checkout root. TorchHub
is also supported for model and converter loading when network/cache behavior is
acceptable.
For source-checkout workflows, make the checkout importable and install the needed dependencies for the chosen route:
# Historical repo requirement files exist for inference and training, but may
# need Python/PyTorch-version adjustment on modern systems.
pip install torch torchvision tqdm pillow
pip install av pims # video file IO / converter video workflows
pip install opencv-python-headless xlsxwriter kornia # evaluation workflows
pip install easing_functions tensorboard # training workflowsMinimal source import and model smoke check:
python scripts/check_rvm_environment.py --repo-root /path/to/RobustVideoMatting --device cpuThe helper validates imports, signatures, and a tiny synthetic forward pass. It is not a quality test, paper reproduction, GPU speed benchmark, or full training check.
Shared references and helpers
- Read references/model-catalog.md for model variants, artifact families, backend support, and speed caveats shared across workflows.
- Read references/troubleshooting.md for source-layout, dependency, network, CUDA, and media IO failures before diving into a sub-skill-specific troubleshooting page.
- Read references/repo-provenance.md before deciding whether this skill is current for a checkout or whether it needs a refresh.
references/repo-routing-metadata.jsoncontains structured router metadata for managed repo-skill import.- Run scripts/check_rvm_environment.py to check importability and a tiny model forward from arbitrary working directories.
Show full SKILL.md (171 more words)Show less
Key operating constraints
- Do not hide network downloads. TorchHub default pretrained models,
pretrained_backbone=True, official weights, and datasets may download external artifacts. - Do not use CPU smoke checks as evidence for CUDA speed, HR evaluation, or full training. CUDA is required for those claims.
- Do not run full training as a quick validation.
train.pyuses GPU count, multiprocessing, NCCL, DDP, SyncBatchNorm, AMP, and large datasets. - Prefer PNG sequence conversion while debugging media/model behavior; video conversion adds PyAV/PIMS/codec issues.
- Preserve recurrent states for video matting. Independent per-frame calls are valid for image-like tests but discard RVM's temporal memory.
Quick task patterns
- "Convert my frames to alpha PNGs": route to
inference-workflows and use its
bundled
rvm_convert_image_sequence.pywrapper with a local checkpoint. - "Why does my tensor call fail?": route to
model-api, verify
[B,3,H,W]or[B,T,3,H,W], and runrvm_model_smoke.py. - "Prepare custom data for training": route to
training-data, validate
fgr/phaand background roots, then adapt the stage commands. - "Evaluate predicted alpha against ground truth": route to evaluation-tools, check exact dataset/clip/frame matching, then choose LR/tiny or HR/CUDA metrics.
© VectorSpaceLab, GPL-3.0. 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 6 other files (scripts, references) in skills/repositories/repo-skills/robust-video-matting of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/model-catalog.md
- references/repo-provenance.md
- references/repo-routing-metadata.json
- references/troubleshooting.md
- scripts/check_rvm_environment.py
- sub-skills
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Robust Video 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Robust Video Matting this skillVectorSpaceLab/AREX-Skill | 331 | — | ~1.3k | Automated safety check: Pass | GPL-3.0 | |
| Ito Inferenceaffaan-m/ECC | 276k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Gke Inferencegoogle/skills | 21k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| LLM Inference Scalingsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Debug InferenceNVIDIA/OpenShell | 16k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Robustnessbrycewang-stanford/Auto-Empirical-Research-Skills | 4.6k | — | ~1.4k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Gke Inference
google/skills
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers.
LLM Inference Scaling
sickn33/agentic-awesome-skills
Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling.
- Official
Debug Inference
NVIDIA/OpenShell
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM.
Robustness
brycewang-stanford/Auto-Empirical-Research-Skills
Checklist of empirical robustness tests for finance/economics papers
- Official
Type Inference
biomejs/biome
A skill your agent uses when working on Biome's Salsa-backed JavaScript and TypeScript inference, including type-aware lint rules, raw collection or inferred representations, analyzer requests…
More from VectorSpaceLab/AREX-Skill
All 157 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Questions about Robust Video Matting
What does Robust Video Matting do?
A skill your agent uses for RobustVideoMatting human video matting workflows: MattingNetwork APIs, inference conversion, training data setup, and RVM evaluation metrics. Robust Video Matting is an agent skill from VectorSpaceLab/AREX-Skill. Use for RobustVideoMatting human video matting workflows: MattingNetwork APIs, inference conversion, training data setup, and RVM evaluation metrics.
When should I use Robust Video Matting?
Robust Video Matting fits situations like: robustVideoMatting human video matting workflows: MattingNetwork APIs; inference conversion; training data setup; RVM evaluation metrics.
How do I install Robust Video Matting in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/robust-video-matting in VectorSpaceLab/AREX-Skill) into .claude/skills/robust-video-matting in your project. Claude Code loads it when a task matches its description.
How do I install Robust Video Matting in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill robust-video-matting -a codex`. Or copy the skill folder (skills/repositories/repo-skills/robust-video-matting in VectorSpaceLab/AREX-Skill) into .agents/skills/robust-video-matting in your project. Codex loads it when a task matches its description.
Can I use Robust Video 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 VectorSpaceLab/AREX-Skill --skill robust-video-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/robust-video-matting, .gemini/skills/robust-video-matting, .github/skills/robust-video-matting and .opencode/skills/robust-video-matting in your project.
What does Robust Video Matting need to run?
Going by SKILL.md and its folder, Robust Video Matting needs Python for the scripts in its folder and the command-line tools its instructions call (pip and python). Our summary lists: Python 3.
Does Robust Video Matting access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Robust Video 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 Robust Video Matting use?
Robust Video Matting is published under the GPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Robust Video Matting use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 2.2k tokens, read only when the agent opens those files.
What are the alternatives to Robust Video Matting?
Skills that share tags, products or a category with Robust Video Matting: Ito Inference (affaan-m/ECC, 276k stars), Gke Inference (google/skills, 21k stars), LLM Inference Scaling (sickn33/agentic-awesome-skills, 47k stars) and Debug Inference (NVIDIA/OpenShell, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Robust Video Matting?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 331 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.