Agent skill

Yolov5

by VectorSpaceLab in VectorSpaceLab/AREX-Skill

A skill your agent uses for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Yolov5

skills CLI

$ npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a claude-code

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

GitHub CLI

$ gh skill install VectorSpaceLab/AREX-Skill yolov5 --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/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/yolov5 .claude/skills/yolov5 && 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/

Paste into Claude Code

Install the "yolov5" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5 into .claude/skills/yolov5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yolov5", 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

$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5

Type 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.

skills CLI

$ npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install VectorSpaceLab/AREX-Skill yolov5 --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ 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/yolov5 .agents/skills/yolov5 && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "yolov5" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5 into .agents/skills/yolov5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yolov5", 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.

skills CLI

$ npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install VectorSpaceLab/AREX-Skill yolov5 --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ 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/yolov5 .cursor/skills/yolov5 && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "yolov5" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5 into .cursor/skills/yolov5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yolov5", 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

$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/yolov5

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install VectorSpaceLab/AREX-Skill yolov5 --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ 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/yolov5 .gemini/skills/yolov5 && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "yolov5" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5 into .gemini/skills/yolov5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yolov5", 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.

GitHub CLI

$ gh skill install VectorSpaceLab/AREX-Skill yolov5

Installs 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).

skills CLI

$ npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ 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/yolov5 .github/skills/yolov5 && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "yolov5" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5 into .github/skills/yolov5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yolov5", 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.

skills CLI

$ npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install VectorSpaceLab/AREX-Skill yolov5 --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ 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/yolov5 .opencode/skills/yolov5 && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "yolov5" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/yolov5 into .opencode/skills/yolov5/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yolov5", 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: yolov5
GitHub stars: 331
Token cost: ~1.6k tokens
SKILL.md length: 633 words
Files: 9 (incl. scripts, references)
Skills in repo: 157
Repo updated: Sep 3, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

A skill your agent uses for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.

Clone-run Ultralytics YOLOv5 workflows: detection
SKILL.md covers Start Here, Route by User Goal, Ordered Handoffs and Common First Decisions, plus 3 more sections
Runs Python scripts from its folder; calls python
Flask REST serving

What it does

Yolov5 is an agent skill from VectorSpaceLab/AREX-Skill. Use this skill for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `references/datasets-and-weights.md`, `references/environment.md` and `references/model-overview.md`).

It sits in AI & LLM Engineering, covering Computer vision. It works with Flask and PyTorch. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is AGPL-3.0.

When your agent uses it

Clone-run Ultralytics YOLOv5 workflows: detection
Flask REST serving

Example prompts

“/yolov5”

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:
- 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

Yolov5 loads about 1.6k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 633 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~42
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~6.9k

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 AGPL-3.0 licence (© VectorSpaceLab). 633 words, ~1,625 tokens.

Download SKILL.mdSave it as .claude/skills/yolov5/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.

name: yolov5
description: Use this skill for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.
disable-model-invocation: true
metadata.disco-role: operating
license: AGPL 3.0

YOLOv5 Repo Skill

Use this skill when a user asks about Ultralytics YOLOv5 repository workflows: object detection, instance segmentation, image classification, PyTorch Hub loading, dataset YAMLs, pretrained weights, model export, benchmarks, or the bundled Flask REST API example.

YOLOv5 is primarily a clone-run repository, not a normal import-first library. Public workflows use the repository's Python entrypoint names, shared models/ and utils/ modules, YAML configs, and checkpoint files. Prefer the bundled references and helper scripts here before reopening repository docs or examples.

Start Here

Read references/repo-provenance.md before deciding whether this skill matches a checkout or needs refresh.
Read references/environment.md for install, clone-run imports, Python/PyTorch requirements, CUDA, and optional extras.
Read references/datasets-and-weights.md before planning training, validation, downloads, named datasets, or checkpoint use.
Read references/model-overview.md when choosing between detection, segmentation, classification, P6, Hub, or exported runtime formats.
Read references/troubleshooting.md for install/import, optional dependency, data/config, download, device, output, export, and service failures.
Run scripts/check_yolov5_env.py --json for a safe active-environment inspection. It imports modules and checks optional dependencies without downloading models, training, exporting, opening media, or starting a server.

Route by User Goal

Object detection: use sub-skills/detection/SKILL.md for detect.py, train.py, val.py, PyTorch Hub loading, COCO-style datasets, bounding boxes, detection checkpoints, and detection-specific failures.
Instance segmentation: use sub-skills/segmentation/SKILL.md for segment/predict.py, segment/train.py, segment/val.py, *-seg.pt checkpoints, mask labels, mask output options, and segmentation validation.
Image classification: use sub-skills/classification/SKILL.md for classify/predict.py, classify/train.py, classify/val.py, YOLOv5-cls or torchvision classifier models, and ImageFolder/ImageNet-style datasets.
Export and benchmarks: use sub-skills/export/SKILL.md for export.py, benchmarks.py, TorchScript, ONNX, OpenVINO, TensorRT, CoreML, TensorFlow/TFLite/TF.js, Paddle, Edge TPU, dynamic shapes, half precision, and backend prerequisite checks.
Flask serving: use sub-skills/serving/SKILL.md for the YOLOv5 Flask REST API pattern, upload validation, API-key behavior, client requests, and safe smoke checks.

Ordered Handoffs

New custom detection project: references/datasets-and-weights.md → sub-skills/detection/ → sub-skills/export/ only after a checkpoint exists.
Segmentation project: references/datasets-and-weights.md → sub-skills/segmentation/ → sub-skills/export/ if deployment format conversion is needed.
Classification project: sub-skills/classification/ → references/datasets-and-weights.md for ImageFolder/named datasets → sub-skills/export/ for deployment formats.
REST API service: sub-skills/serving/ first; route to sub-skills/detection/ only for model behavior and to sub-skills/export/ only when the user wants non-PyTorch deployment artifacts.
Benchmark/export request without a trained checkpoint: first choose or train the task-specific model, then use sub-skills/export/.

Show full SKILL.md (280 more words)Show less

Common First Decisions

Repository position: most commands assume the user is acting in a YOLOv5 checkout or has otherwise made the repository modules importable.
Task family: detection uses boxes; segmentation uses boxes plus masks; classification uses class probabilities and ImageFolder-style labels.
Weights: names such as yolov5s.pt, yolov5s-seg.pt, or yolov5s-cls.pt may trigger downloads. Prefer explicit local paths for offline or deterministic work.
Datasets: training/validation commands depend on data YAMLs or ImageFolder directories. Validate dataset paths and class counts before launching expensive runs.
Side effects: prediction, training, validation, export, benchmarks, downloads, and servers can write output directories, fetch files, open streams, or run for a long time. Prefer planner/checker scripts before execution.
Optional dependencies: install export, logging, service, and accelerator packages narrowly for the selected workflow only.
Hardware: CPU is enough for parser/import checks and some tiny workflows, but CUDA is strongly preferred for real training; TensorRT and some half-precision paths require matching GPU/runtime support.

Safe Baseline

bash

python - <<'PY'
import torch
import models.common, models.yolo, utils.general
print('torch', torch.__version__)
print('cuda_available', torch.cuda.is_available())
print('yolov5 modules importable')
PY

If imports fail, read references/environment.md and references/troubleshooting.md before changing dependencies.

Bundled Helpers

scripts/check_yolov5_env.py: safe environment, import, backend, and optional-dependency checker.
sub-skills/detection/scripts/plan_detection_command.py: prints detection train/val/predict command previews with risk warnings.
sub-skills/segmentation/scripts/plan_segmentation_command.py: prints segmentation train/val/predict command previews with mask/data warnings.
sub-skills/classification/scripts/plan_classification_command.py: prints classification train/val/predict command previews with ImageFolder/model warnings.
sub-skills/export/scripts/check_export_prereqs.py: checks optional dependencies for export formats without exporting.
sub-skills/serving/scripts/rest_api_smoke.py: uses a Flask test client and dummy model to verify REST API request validation without downloading weights or starting a server.

Safety Policy

Do not run downloads, training, validation, prediction on streams, export conversion, benchmarks, notebooks, or long-lived servers until the task has explicit inputs, output locations, runtime budget, and backend expectations. Run original repo tests/examples only as verification after classifying them as safe for the current environment.

Files

SKILL.md and 8 other files (scripts, references) in skills/repositories/repo-skills/yolov5 of VectorSpaceLab/AREX-Skill.

SKILL.md
references/datasets-and-weights.md
references/environment.md
references/model-overview.md
references/repo-provenance.md
references/repo-routing-metadata.json
references/troubleshooting.md
scripts/check_yolov5_env.py
sub-skills

Open the folder on GitHubat commit ac3fe1a

Compare with similar skills

Yolov5 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.

Yolov5 compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Yolov5 this skillVectorSpaceLab/AREX-Skill	331	—	~1.6k	Automated safety check: Pass	AGPL-3.0	1 mo ago
Senior Computer Visiondavila7/claude-code-templates	33k	2 repos	~1.4k	Automated safety check: Pass	MIT	today
Computer Vision Pipelinecuriositech/some_claude_skills	244	—	~4k	Automated safety check: Pass	MIT	1 mo ago
Senior Computer Visionalirezarezvani/claude-skills	28k	1 repos	~3.2k	Automated safety check: Pass	MIT	1 mo ago
Tao Finetune ClipNVIDIA/skills	3.6k	—	~4k	Automated safety check: Notes	Apache-2.0	yesterday
Tao Finetune Huggingface ModelNVIDIA/skills	3.6k	—	~4.9k	Automated safety check: Notes	Apache-2.0	yesterday

Similar skills

Senior Computer Vision
davila7/claude-code-templates
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.
33k GitHub starsUsed in 2 repos~1.4k tokens
AI & LLM EngineeringAuto-check passed
Computer Vision Pipeline
curiositech/some_claude_skills
Build production computer vision pipelines for object detection, tracking, and video analysis.
244 GitHub stars~4k tokensUpdated 1 mo ago
AI & LLM EngineeringAuto-check passed
Senior Computer Vision
alirezarezvani/claude-skills
Computer vision engineering skill for object detection, image segmentation, and visual AI systems.
28k GitHub starsUsed in 1 repo~3.2k tokens
AI & LLM EngineeringAuto-check passed
Tao Finetune Clip
NVIDIA/skills
Official
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.
3.6k GitHub stars~4k tokensUpdated yesterday
AI & LLM EngineeringAuto-check: notes
Tao Finetune Huggingface Model
NVIDIA/skills
Official
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches.
3.6k GitHub stars~4.9k tokensUpdated yesterday
AI & LLM EngineeringAuto-check: notes
Tao Train Image Classification
NVIDIA/skills
Official
PyTorch-based TAO image classification. An agent skill from NVIDIA/skills.
3.6k GitHub stars~3.6k tokensUpdated yesterday
AI & LLM EngineeringAuto-check: notes

Questions about Yolov5

What does Yolov5 do?

A skill your agent uses for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving. Yolov5 is an agent skill from VectorSpaceLab/AREX-Skill. Use this skill for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.

When should I use Yolov5?

Yolov5 fits situations like: clone-run Ultralytics YOLOv5 workflows: detection; flask REST serving.

How do I install Yolov5 in Claude Code?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/yolov5 in VectorSpaceLab/AREX-Skill) into .claude/skills/yolov5 in your project. Claude Code loads it when a task matches its description.

How do I install Yolov5 in Codex?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill yolov5 -a codex`. Or copy the skill folder (skills/repositories/repo-skills/yolov5 in VectorSpaceLab/AREX-Skill) into .agents/skills/yolov5 in your project. Codex loads it when a task matches its description.

Can I use Yolov5 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 yolov5 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yolov5, .gemini/skills/yolov5, .github/skills/yolov5 and .opencode/skills/yolov5 in your project.

What does Yolov5 need to run?

Going by SKILL.md and its folder, Yolov5 needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Yolov5 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 Yolov5 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 Yolov5 use?

Yolov5 is published under the AGPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Yolov5 use?

About 1.6k tokens (SKILL.md is roughly 6.5k 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 5.3k tokens, read only when the agent opens those files.

What are the alternatives to Yolov5?

Skills that share tags, products or a category with Yolov5: Senior Computer Vision (davila7/claude-code-templates, 33k stars), Computer Vision Pipeline (curiositech/some_claude_skills, 244 stars), Senior Computer Vision (alirezarezvani/claude-skills, 28k stars) and Tao Finetune Clip (NVIDIA/skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yolov5?

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.

Install Yolov5

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

YOLOv5 Repo Skill

Start Here

Route by User Goal

Ordered Handoffs

Common First Decisions

Safe Baseline

Bundled Helpers

Safety Policy

Files

Compare with similar skills

Similar skills

More from VectorSpaceLab/AREX-Skill

Related

Questions about Yolov5