New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ultralytics

by VectorSpaceLab in VectorSpaceLab/AREX-Skill

A skill your agent uses for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family…

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Ultralytics

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

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

GitHub CLI
$ gh skill install VectorSpaceLab/AREX-Skill ultralytics --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/ultralytics .claude/skills/ultralytics && rm -rf skills-src

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

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

Facts

Skill name
ultralytics
GitHub stars
330
Token cost
~1.2k tokens
SKILL.md length
502 words
Files
8 (incl. scripts, references)
Skills in repo
159
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family…

  • Ultralytics YOLO package workflows: CLI/Python model usage
  • SKILL.md covers Start Here, Route by User Goal, Common First Decisions and Safe Baseline, plus 1 more section
  • Runs Python scripts from its folder; calls pip and python
  • Data/config setup

What it does

Ultralytics is an agent skill from VectorSpaceLab/AREX-Skill. Use this skill for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family selection, and repo development.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/repo-provenance.md`, `references/repo-routing-metadata.json` and `references/routing-map.md`).

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

When your agent uses it

  • Ultralytics YOLO package workflows: CLI/Python model usage
  • Data/config setup
  • Prediction/results
  • Export/deployment

Example prompts

  • “/ultralytics”

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:

    • pip
    • python

    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

Ultralytics loads about 1.2k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 502 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

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). 502 words, ~1,228 tokens.

Download SKILL.mdSave it as .claude/skills/ultralytics/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
ultralytics
description
Use this skill for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family selection, and repo development.
disable-model-invocation
true
metadata.disco-role
operating
license
AGPL 3.0

Ultralytics Repo Skill

Use this skill when a user asks for help with Ultralytics YOLO workflows, the ultralytics Python package, or this repository's public APIs and maintainer tasks. Ultralytics covers detection, instance segmentation, semantic segmentation, classification, pose, oriented boxes, tracking, model export, deployment helpers, and analytics solutions.

Start Here

  • Read references/repo-provenance.md when deciding whether this skill matches the current checkout or needs refresh.
  • Read references/routing-map.md when a request spans more than one workflow or could route to multiple sub-skills.
  • Read references/version-and-capability-notes.md for version-sensitive items such as YOLO26, semantic segmentation, SAM3, downloads, optional extras, and backend requirements.
  • Read references/shared-cli-config-keys.md before validating yolo TASK MODE arg=value syntax or translating Python kwargs to CLI args.
  • Run scripts/check_ultralytics_env.py --json to inspect an active environment without downloads, training, export, or media processing.

Route by User Goal

  • Data and configuration: use sub-skills/data-and-configuration/SKILL.md for dataset YAMLs, label layout, config defaults, CLI/Python arg translation, converters, and safe command planning.
  • Training and validation: use sub-skills/training-and-validation/SKILL.md for model.train(), model.val(), model.tune(), yolo train, yolo val, resume, devices, metrics, and tuning.
  • Inference and results: use sub-skills/inference-and-results/SKILL.md for model.predict(), model(source), yolo predict, source types, streaming, batching, Results extraction, saving, and thread-safe inference.
  • Export and deployment: use sub-skills/export-and-deployment/SKILL.md for model.export(), yolo export, benchmark, ONNX/OpenVINO/TensorRT/CoreML/TFLite and deployment-format troubleshooting.
  • Tracking and solutions: use sub-skills/tracking-and-solutions/SKILL.md for model.track(), yolo track, tracker YAMLs, ReID/deep trackers, object counting, heatmaps, speed/queue/region workflows, Streamlit, and yolo solutions.
  • Model families and tasks: use sub-skills/model-families-and-tasks/SKILL.md for choosing YOLO, YOLOWorld, YOLOE, NAS, SAM, FastSAM, or RTDETR, and for mapping detect/segment/semantic/classify/pose/OBB tasks to outputs.
  • Repo development: use sub-skills/repo-development/SKILL.md for editing this repository, selecting focused tests, docs/style checks, optional extras, CI-like verification, and maintainer-safe native checks.
Show full SKILL.md (233 more words)Show less

Common First Decisions

  • CLI shape: Ultralytics uses yolo TASK MODE arg=value; avoid normal --flag value syntax for YOLO config arguments.
  • Downloads: names such as yolo26n.pt, sam3.pt, or coco8.yaml may download weights or datasets. Prefer explicit local paths for offline or deterministic work.
  • Task outputs: detection uses boxes, segmentation uses boxes and masks, semantic segmentation uses dense semantic_mask, classification uses probs, pose uses keypoints, and OBB uses rotated geometry.
  • Side effects: training, validation, prediction, export, tracking, and solutions can write runs, labels, media, or exports. Set project, name, exist_ok, save=False, or dry-run helper scripts when deterministic output matters.
  • Optional dependencies: install extras narrowly. Use export extras only for export workflows, solutions extras for analytics apps, logging extras for integrations, and dev extras for repository checks.
  • Hardware: GPU acceleration is optional for many inspections, but TensorRT, CUDA export, large training, and some ReID/deep trackers need compatible GPU packages and drivers.

Safe Baseline

bash
pip install ultralytics
python - <<'PY'
import ultralytics
print(ultralytics.__version__)
print("YOLO" in dir(ultralytics))
PY
yolo help

For local repository development, use editable install only in a disposable or project-specific environment and keep optional extras narrow. Do not install broad extras such as dev, export, solutions, or logging unless the selected workflow actually needs them.

Bundled Helpers

  • scripts/check_ultralytics_env.py: reports package versions, CLI availability, and optional backend modules in the active Python environment.
  • Sub-skill helpers are dry-run planners or inspectors. They do not train, infer, export, download weights, open media, or run native tests unless their help text explicitly says so.

© VectorSpaceLab, AGPL-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 7 other files (scripts, references) in skills/repositories/repo-skills/ultralytics of VectorSpaceLab/AREX-Skill.

  • SKILL.md
  • references/repo-provenance.md
  • references/repo-routing-metadata.json
  • references/routing-map.md
  • references/shared-cli-config-keys.md
  • references/version-and-capability-notes.md
  • scripts/check_ultralytics_env.py
  • sub-skills

Open the folder on GitHubat commit ac3fe1a

Compare with similar skills

Ultralytics 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.

Ultralytics compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ultralytics this skillVectorSpaceLab/AREX-Skill330—~1.2kAutomated safety check: PassAGPL-3.0
vLLM Model ServingOrchestra-Research/AI-Research-SKILLs13k5 repos~2.3kAutomated safety check: PassMIT
Python Environment Setup for SageMakerhuggingface/skills11k2 repos~1.7kAutomated safety check: PassApache-2.0
Hugging Face Vision Trainerhuggingface/skills11k1 repos~7.5kAutomated safety check: PassApache-2.0
Google Agents CLI Adk Codepifferologo/cloud-agents-cli1291 repos~768Automated safety check: PassApache-2.0
Generate Ors Envadithya-s-k/FineEnvs456—~2.3kAutomated safety check: NotesApache-2.0

Similar skills

  • vLLM Model Serving

    Orchestra-Research/AI-Research-SKILLs

    Deploys LLMs with vLLM for high-throughput serving, covering the OpenAI-compatible server, offline batch inference, monitoring and a Docker rollout.

    13k GitHub starsUsed in 5 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Python Environment Setup for SageMaker

    huggingface/skills

    Official

    Sets up an isolated Python environment with a supported interpreter and current boto3 before any SageMaker deployment, training or AWS automation code runs.

    11k GitHub starsUsed in 2 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Vision Trainer

    huggingface/skills

    Official

    Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.

    11k GitHub starsUsed in 1 repo~7.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Google Agents CLI Adk Code

    pifferologo/cloud-agents-cli

    This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…

    129 GitHub starsUsed in 1 repo~768 tokens
    AI & LLM EngineeringAuto-check passed

  • Generate Ors Env

    adithya-s-k/FineEnvs

    Builds an Open Reward Standard (ORS) variant of an RL environment using the official openreward Python package.

    456 GitHub stars~2.3k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes

  • Hugging Face Transformers Usage

    davila7/claude-code-templates

    Loads pre-trained Hugging Face Transformers models for text, vision and audio tasks, runs inference with pipelines and fine-tunes on custom datasets.

    32k GitHub starsUsed in 11 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

More from VectorSpaceLab/AREX-Skill

All 159 skills in this repo

  • Agent 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…

    330 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • 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…

    330 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • 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.

    330 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed

  • 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…

    330 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • 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.

    330 GitHub stars~500 tokensUpdated 1 mo ago
    Auto-check passed

  • Alphafold3

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.

    330 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Ultralytics

What does Ultralytics do?

A skill your agent uses for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family…. Ultralytics is an agent skill from VectorSpaceLab/AREX-Skill. Use this skill for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family selection, and repo development.

When should I use Ultralytics?

Ultralytics fits situations like: ultralytics YOLO package workflows: CLI/Python model usage; data/config setup; prediction/results; export/deployment.

How do I install Ultralytics in Claude Code?

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

How do I install Ultralytics in Codex?

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

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

What does Ultralytics need to run?

Going by SKILL.md and its folder, Ultralytics 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 Ultralytics 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 Ultralytics 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 Ultralytics use?

Ultralytics 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 Ultralytics use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 2.6k tokens, read only when the agent opens those files.

What are the alternatives to Ultralytics?

Skills that share tags, products or a category with Ultralytics: vLLM Model Serving (Orchestra-Research/AI-Research-SKILLs, 13k stars), Python Environment Setup for SageMaker (huggingface/skills, 11k stars), Hugging Face Vision Trainer (huggingface/skills, 11k stars) and Google Agents CLI Adk Code (pifferologo/cloud-agents-cli, 129 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ultralytics?

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.