TAO Image Embeddings
NVIDIA/skills
Turns a parquet of image file paths into a parquet of embeddings with CLIP, SigLIP or a TAO checkpoint, using the TAO Data Services container, ahead of neighbor mining.
Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows.
Install Swin Transformer
$ npx skills add VectorSpaceLab/AREX-Skill --skill swin-transformer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill swin-transformer --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/swin-transformer .claude/skills/swin-transformer && 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 "swin-transformer" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/swin-transformer into .claude/skills/swin-transformer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "swin-transformer", 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/swin-transformerType 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 swin-transformer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill swin-transformer --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/swin-transformer .agents/skills/swin-transformer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "swin-transformer" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/swin-transformer into .agents/skills/swin-transformer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "swin-transformer", 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 swin-transformer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill swin-transformer --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/swin-transformer .cursor/skills/swin-transformer && 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 "swin-transformer" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/swin-transformer into .cursor/skills/swin-transformer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "swin-transformer", 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/swin-transformer--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 swin-transformer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill swin-transformer --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/swin-transformer .gemini/skills/swin-transformer && 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 "swin-transformer" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/swin-transformer into .gemini/skills/swin-transformer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "swin-transformer", 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 swin-transformerInstalls 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 swin-transformer -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/swin-transformer .github/skills/swin-transformer && 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 "swin-transformer" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/swin-transformer into .github/skills/swin-transformer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "swin-transformer", 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 swin-transformer -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 swin-transformer --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/swin-transformer .opencode/skills/swin-transformer && 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 "swin-transformer" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/swin-transformer into .opencode/skills/swin-transformer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "swin-transformer", 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
swin-transformer- GitHub stars
- 331
- Token cost
- ~1.2k tokens
- SKILL.md length
- 492 words
- Files
- 10 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows.
- Tasks that involve Computer vision
- SKILL.md covers Quick routing, Baseline prerequisites, Safe helper scripts and Important boundaries, plus 1 more section
- Runs Python scripts from its folder; calls python
What it does
Swin Transformer is an agent skill from VectorSpaceLab/AREX-Skill. Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `references/configuration.md`, `references/model-zoo-and-configs.md` and `references/repo-provenance.md`).
It sits in AI & LLM Engineering, covering Computer vision. It works with CUDA. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- Tasks that involve Computer vision
Example prompts
- “/swin-transformer”
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 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
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.
Context cost
Swin Transformer loads about 1.2k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 492 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 MIT licence (© VectorSpaceLab). 492 words, ~1,183 tokens.
Download SKILL.mdSave it as
.claude/skills/swin-transformer/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- swin-transformer
- description
- Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
Swin-Transformer Repo Skill
Use this skill when a task involves the official Microsoft Swin-Transformer image-classification codebase: Swin V1/V2, Swin-MLP, SimMIM masked image modeling, ImageNet data layouts, pretrained checkpoint handling, supervised training/evaluation commands, Swin-MoE, or the optional fused CUDA window-process extension.
This is a self-contained operating guide. It does not require the original source checkout used during skill creation. When a workflow needs code execution, use the user's current checkout or installed copy of Swin-Transformer and the bundled helper scripts in this skill.
Quick routing
| User intent | Read next |
|---|---|
Build or inspect SwinTransformer, SwinTransformerV2, SwinMLP, build_model, tensor shapes, FLOPs, or CPU smoke models | sub-skills/core-models/SKILL.md |
Validate ImageNet folder/zip/22K layouts, understand --zip, map files, SimMIM data, checkpoint resume/pretrained behavior, or 22K-to-1K head remapping | sub-skills/data-and-checkpoints/SKILL.md |
Construct or debug supervised main.py commands for training, fine-tuning, evaluation, throughput, AMP, DDP launch, or --opts overrides | sub-skills/training-eval-cli/SKILL.md |
| Run or adapt SimMIM pretraining/fine-tuning/evaluation workflows and mask/loss checks | sub-skills/simmim-workflows/SKILL.md |
| Work with Swin-MoE, Tutel, Apex fused optimizers/layernorm, or the fused CUDA window-process extension | sub-skills/moe-and-acceleration/SKILL.md |
| Need a config/model family map before choosing a route | references/model-zoo-and-configs.md |
| Need shared YACS config and flag behavior | references/configuration.md |
| Need cross-cutting troubleshooting | references/troubleshooting.md |
| Need to verify that a checkout/environment is usable | scripts/check_env.py |
Baseline prerequisites
Swin-Transformer is a research-code checkout rather than an ordinary packaged distribution. For code execution, future agents should work against a current checkout or source tree on PYTHONPATH and install the runtime dependencies relevant to the selected workflow:
- Required for baseline inspection and CPU smoke checks: Python, PyTorch, torchvision,
timm==0.4.12,yacs,PyYAML,numpy,scipy, andtermcolor. - Required for full supervised or SimMIM training/evaluation: CUDA-capable PyTorch, GPUs, ImageNet-style data, checkpoints when evaluating/fine-tuning, and distributed launcher environment.
- Optional: Apex for fused layernorm/fused optimizers, Tutel for Swin-MoE, and a compiled
swin_window_processCUDA extension for--fused_window_process.
Minimal import smoke for a checkout:
python - <<'PY'
from config import get_config
from models import build_model
from data import build_loader
print('Swin-Transformer modules import')
PYIf that fails, read references/troubleshooting.md before running full training.
Show full SKILL.md (190 more words)Show less
Safe helper scripts
- Run
scripts/check_env.py --repo-root <checkout>to check required imports and optional CUDA/Tutel/Apex/fused-extension availability without training or downloading. - Run
scripts/inspect_swin_config.py --repo-root <checkout> --cfg <config.yaml>to summarize a YAML config and flag risky settings. - Run
scripts/swin_cli_command_builder.py --helpto assemble copyable command templates for supervised, SimMIM, and MoE workflows.
These helpers are safe by default: they do not download models or data, do not run distributed training, and do not build CUDA extensions.
Important boundaries
- This skill covers image classification and the code in this repository. Object detection, semantic segmentation, video action recognition, feature distillation, and other downstream projects linked by the public README are separate repositories and are not covered here.
- Full accuracy reproduction and throughput benchmarking are intentionally not used as skill-verification gates because they require large datasets, checkpoints, GPUs, and long distributed runs.
- CPU smoke checks validate config/model/data plumbing only. They are not evidence that CUDA training, Swin-MoE, Apex, or the fused window kernel works.
Provenance and staleness
Read references/repo-provenance.md before deciding whether this skill matches a particular checkout. If source APIs, config layout, CLI flags, or dependency behavior differ, refresh this repo skill before relying on it.
© VectorSpaceLab, 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 9 other files (scripts, references) in skills/repositories/repo-skills/swin-transformer of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/configuration.md
- references/model-zoo-and-configs.md
- references/repo-provenance.md
- references/repo-routing-metadata.json
- references/troubleshooting.md
- scripts/check_env.py
- scripts/inspect_swin_config.py
- scripts/swin_cli_command_builder.py
- sub-skills
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Swin Transformer 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 |
|---|---|---|---|---|---|---|
| Swin Transformer this skillVectorSpaceLab/AREX-Skill | 331 | — | ~1.2k | Automated safety check: Pass | MIT | |
| TAO Image EmbeddingsNVIDIA/skills | 3.6k | — | ~2k | Automated safety check: Notes | Apache-2.0 | |
| Teach A ModelAseiel/VideoHighlighter | 166 | — | ~839 | Automated safety check: Pass | AGPL-3.0 | |
| Deepstream DevNVIDIA/skills | 3.6k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
- Official
Teach A Model
Aseiel/VideoHighlighter
Train a custom VideoHighlighter action or object model from a few videos the user provides — cut into samples, sort with CLIP, review contact sheets, build, train, install only if better.
- Official
Deepstream Dev
NVIDIA/skills
NVIDIA DeepStream SDK development with Python pyservicemaker API.
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
CLIP Image-Text Matching
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
Yolo Master Agent
Tencent/YOLO-Master
A skill your agent uses when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.
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.
Related
Works with
Categories
Questions about Swin Transformer
What does Swin Transformer do?
Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows. Swin Transformer is an agent skill from VectorSpaceLab/AREX-Skill. Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows.
When should I use Swin Transformer?
Swin Transformer fits situations like: tasks that involve Computer vision.
How do I install Swin Transformer in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill swin-transformer -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/swin-transformer in VectorSpaceLab/AREX-Skill) into .claude/skills/swin-transformer in your project. Claude Code loads it when a task matches its description.
How do I install Swin Transformer in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill swin-transformer -a codex`. Or copy the skill folder (skills/repositories/repo-skills/swin-transformer in VectorSpaceLab/AREX-Skill) into .agents/skills/swin-transformer in your project. Codex loads it when a task matches its description.
Can I use Swin Transformer 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 swin-transformer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/swin-transformer, .gemini/skills/swin-transformer, .github/skills/swin-transformer and .opencode/skills/swin-transformer in your project.
What does Swin Transformer need to run?
Going by SKILL.md and its folder, Swin Transformer needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Swin Transformer 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 Swin Transformer 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 Swin Transformer use?
Swin Transformer 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 Swin Transformer use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 2.5k tokens, read only when the agent opens those files.
What are the alternatives to Swin Transformer?
Skills that share tags, products or a category with Swin Transformer: TAO Image Embeddings (NVIDIA/skills, 3.6k stars), Teach A Model (Aseiel/VideoHighlighter, 166 stars), Deepstream Dev (NVIDIA/skills, 3.6k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Swin Transformer?
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.