Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting.
Install Ops And Detection
$ npx skills add VectorSpaceLab/AREX-Skill --skill ops-and-detection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill ops-and-detection --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/torchvision/sub-skills/ops-and-detection .claude/skills/ops-and-detection && 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 "ops-and-detection" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection into .claude/skills/ops-and-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-and-detection", 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/torchvision/sub-skills/ops-and-detectionType 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 ops-and-detection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill ops-and-detection --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/torchvision/sub-skills/ops-and-detection .agents/skills/ops-and-detection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ops-and-detection" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection into .agents/skills/ops-and-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-and-detection", 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 ops-and-detection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill ops-and-detection --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/torchvision/sub-skills/ops-and-detection .cursor/skills/ops-and-detection && 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 "ops-and-detection" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection into .cursor/skills/ops-and-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-and-detection", 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/torchvision/sub-skills/ops-and-detection--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 ops-and-detection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill ops-and-detection --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/torchvision/sub-skills/ops-and-detection .gemini/skills/ops-and-detection && 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 "ops-and-detection" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection into .gemini/skills/ops-and-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-and-detection", 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 ops-and-detectionInstalls 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 ops-and-detection -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/torchvision/sub-skills/ops-and-detection .github/skills/ops-and-detection && 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 "ops-and-detection" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection into .github/skills/ops-and-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-and-detection", 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 ops-and-detection -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 ops-and-detection --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/torchvision/sub-skills/ops-and-detection .opencode/skills/ops-and-detection && 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 "ops-and-detection" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection into .opencode/skills/ops-and-detection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-and-detection", 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
ops-and-detection- GitHub stars
- 330
- Token cost
- ~698 tokens
- SKILL.md length
- 299 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- BSD-3-Clause
At a glance
Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting.
- Works in 6 steps: Confirm coordinate convention and tensor… → Normalize formats explicitly with… → Keep boxes, scores, labels, feature… → …
- AI & LLM Engineering work in your project
- SKILL.md covers Route first, Fast workflow, References and Bundled check
- Runs Python scripts from its folder; calls python
What it does
Ops And Detection is an agent skill from VectorSpaceLab/AREX-Skill. Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting.
Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/box-and-roi-ops.md`, `references/detection-helpers.md` and `references/troubleshooting.md`).
It sits in AI & LLM Engineering. It works with PyTorch. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is BSD-3-Clause.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/ops-and-detection”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Confirm coordinate convention and tensor shapes before calling ops. Most detection model internals use xyxy boxes with shape [N, 4] and…
- Normalize formats explicitly with torchvision.ops.box_convert before IoU/NMS; do not mix xyxy, xywh, and center formats in the same tensor.
- Keep boxes, scores, labels, feature maps, and ROI tensors on compatible devices and dtypes; device mismatches are common when CUDA tensors…
- Treat NMS output order as score-sorted indices, but avoid relying on deterministic tie-breaking when multiple boxes have identical scores…
- For ROI ops, validate feature map rank [N, C, H, W], box format, batch indices, output_size, spatial_scale, and featmap_names before…
- If an op raises operator torchvision::nms does not exist or a custom-ops loading error, diagnose install/build compatibility before…
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:
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
Ops And Detection loads about 698 tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 299 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 BSD-3-Clause licence (© VectorSpaceLab). 299 words, ~698 tokens.
Download SKILL.mdSave it as
.claude/skills/ops-and-detection/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- ops-and-detection
- description
- Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- BSD 3-Clause
TorchVision Ops And Detection
Use this sub-skill when the task needs low-level torchvision.ops APIs, detection box utilities, ROI/NMS behavior, detection postprocessing concepts, or diagnosis of missing custom C++ operators.
Route first
- Use this skill for
torchvision.ops.nms,batched_nms, box IoU/conversion/clipping/filtering,masks_to_boxes,roi_align,roi_pool,MultiScaleRoIAlign, FPN helpers, losses, and operator availability errors. - Use
../models-and-weights/for choosing or constructing high-level detection models and pretrained weights. - Use
../training-references/for official detection training/evaluation command patterns. - Use
../transforms-and-tv-tensors/for annotation-aware transform pipelines, TVTensor metadata, and bounding-box transform migration.
Fast workflow
- Confirm coordinate convention and tensor shapes before calling ops. Most detection model internals use
xyxyboxes with shape[N, 4]and coordinates orderedx1 <= x2,y1 <= y2. - Normalize formats explicitly with
torchvision.ops.box_convertbefore IoU/NMS; do not mixxyxy,xywh, and center formats in the same tensor. - Keep
boxes,scores,labels, feature maps, and ROI tensors on compatible devices and dtypes; device mismatches are common when CUDA tensors meet CPU boxes. - Treat NMS output order as score-sorted indices, but avoid relying on deterministic tie-breaking when multiple boxes have identical scores and IoUs.
- For ROI ops, validate feature map rank
[N, C, H, W], box format, batch indices,output_size,spatial_scale, andfeatmap_namesbefore debugging model heads. - If an op raises
operator torchvision::nms does not existor a custom-ops loading error, diagnose install/build compatibility before rewriting model code.
References
references/box-and-roi-ops.md: box formats, IoU variants, NMS, masks, ROI Align/Pool, FPN, and layers/losses.references/detection-helpers.md: detection model helper concepts, postprocessing knobs, output structures, and boundaries.references/troubleshooting.md: extension, version, device, coordinate, nondeterminism, and ROI-shape failures.
Bundled check
Run the tiny CPU smoke script to verify that import, boxes, IoU, NMS, and ROI Align work without downloads or large tensors:
python sub-skills/ops-and-detection/scripts/smoke_ops.pyIf the script reports missing compiled ops, follow references/troubleshooting.md rather than treating it as a model-definition issue.
© VectorSpaceLab, BSD-3-Clause. 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 4 other files (scripts, references) in skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/box-and-roi-ops.md
- references/detection-helpers.md
- references/troubleshooting.md
- scripts/smoke_ops.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Ops And Detection 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 |
|---|---|---|---|---|---|---|
| Ops And Detection this skillVectorSpaceLab/AREX-Skill | 330 | — | ~698 | Automated safety check: Pass | BSD-3-Clause | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Add Torch Shapes Examplefacebook/pyrefly | 7.1k | — | ~1.3k | Automated safety check: Pass | MIT | |
| MUSA GPU Training Optimizeropen-infra-skills/infra-skills | 141 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Ghstack CIpytorch/pytorch | 104k | — | ~1.4k | Automated safety check: Pass | Custom licence |
Similar skills
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.
- Official
Add Torch Shapes Example
facebook/pyrefly
A skill your agent uses when adding a new PyTorch model to Pyrefly's shape-tracking example corpus under tensor-shapes/pyrefly-torch-stubs/examples — i.e.
MUSA GPU Training Optimizer
open-infra-skills/infra-skills
Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.
Ghstack CI
pytorch/pytorch
Manage CI for PyTorch ghstack stacks by running CI where its results are useful now and deferring other PRs with [no-ci].
Depth Estimation
SharpAI/DeepCamera
Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)
More from VectorSpaceLab/AREX-Skill
All 159 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 Ops And Detection
What does Ops And Detection do?
Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting. Ops And Detection is an agent skill from VectorSpaceLab/AREX-Skill.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting.
When should I use Ops And Detection?
Ops And Detection fits situations like: AI & LLM Engineering work in your project.
How do I install Ops And Detection in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill ops-and-detection -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection in VectorSpaceLab/AREX-Skill) into .claude/skills/ops-and-detection in your project. Claude Code loads it when a task matches its description.
How do I install Ops And Detection in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill ops-and-detection -a codex`. Or copy the skill folder (skills/repositories/repo-skills/torchvision/sub-skills/ops-and-detection in VectorSpaceLab/AREX-Skill) into .agents/skills/ops-and-detection in your project. Codex loads it when a task matches its description.
Can I use Ops And Detection 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 ops-and-detection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ops-and-detection, .gemini/skills/ops-and-detection, .github/skills/ops-and-detection and .opencode/skills/ops-and-detection in your project.
What does Ops And Detection need to run?
Going by SKILL.md and its folder, Ops And Detection needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Ops And Detection 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 Ops And Detection 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 Ops And Detection use?
Ops And Detection is published under the BSD-3-Clause licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ops And Detection use?
About 698 tokens (SKILL.md is roughly 2.8k 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 4k tokens, read only when the agent opens those files.
What are the alternatives to Ops And Detection?
Skills that share tags, products or a category with Ops And Detection: Add Uint Support (pytorch/pytorch, 104k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Torch Shapes Example (facebook/pyrefly, 7.1k stars) and MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ops And Detection?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 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.