Ab3dmot

Organization

VectorSpaceLab

ab3dmot

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`ab3dmot`
Stars	341
Forks	26
Bundled files	22
License	NOASSERTION
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
22 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by VectorSpaceLab on GitHub. Read the source before you install it.

Installation

Install the Ab3dmot AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ab3dmot
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ab3dmot

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git /tmp/AREX-Skill
mkdir -p .claude/skills
cp -r /tmp/AREX-Skill/skills/repositories/repo-skills/ab3dmot .claude/skills/ab3dmot

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ab3dmot in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ab3dmot on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ab3dmot is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AB3DMOT repo skill

Use this skill when a task involves AB3DMOT, 3D multi-object tracking, KITTI/nuScenes tracking inputs, the AB3DMOT tracker API, AB3DMOT result evaluation, confidence thresholding, or qualitative visualization.

AB3DMOT is a CPU-oriented Python baseline that combines 3D object detections, a 3D Kalman filter, ego-motion compensation, and Hungarian/greedy data association. It is organized as a repository script workflow rather than an installed console-entry-point package.

Start here

If the task is about installation, imports, dependencies, or runtime smoke checks, read references/install-and-dependencies.md and run scripts/ab3dmot_environment_check.py.
If the task is about repository layout, public source areas, configs, result roots, or which bundled sub-skill owns a file family, read references/repository-map.md.
If the task fails before you know the owning workflow, read references/troubleshooting.md.
For provenance and staleness checks, read references/repo-provenance.md.

Route by workflow

Use sub-skills/data-conversion/SKILL.md for KITTI/nuScenes data placement, detector-result conversion, AB3DMOT detection row validation, category-specific detection folders, and nuScenes-to-KITTI intermediate layouts.
Use sub-skills/tracking-pipeline/SKILL.md for main.py tracking commands, config defaults, output naming, direct AB3DMOT.track API use, Box3D/matching/Kalman behavior, and one-frame smoke checks.
Use sub-skills/evaluation-visualization/SKILL.md for KITTI 2D/3D MOT metrics, nuScenes official/quick evaluation, confidence thresholding, result export/submission packaging, and image/video visualization.

Common task routing

User asks for	Read
“Validate this AB3DMOT detection file”	`data-conversion` validator and data formats
“Convert nuScenes detections for AB3DMOT”	`data-conversion` nuScenes conversion reference
“Run KITTI PointRCNN tracking”	`tracking-pipeline` tracking workflow
“Use AB3DMOT.track directly”	`tracking-pipeline` API reference and synthetic smoke script
“Why did `main.py` use nuScenes defaults?”	`tracking-pipeline` configuration/troubleshooting
“Evaluate KITTI validation with 0.25/0.5/0.7 3D IoU”	`evaluation-visualization` KITTI evaluation
“Make KITTI 2D MOT submission files”	`evaluation-visualization` KITTI threshold/submission guidance
“Convert AB3DMOT nuScenes results to JSON and evaluate”	`evaluation-visualization` nuScenes evaluation
“Render track videos”	`evaluation-visualization` visualization troubleshooting

Minimal runtime expectations

AB3DMOT command workflows assume a working AB3DMOT checkout or equivalent project tree with:

Python runtime compatible with the repository and dependencies.
NumPy and SciPy in addition to FilterPy, Numba, Matplotlib, Pillow, OpenCV, PyYAML, EasyDict, and the other requirements.txt entries.
The external Xinshuo Python toolbox (Xinshuo_PyToolbox) importable via --toolbox-root or PYTHONPATH; it is not bundled or reliably pin-able as a PyPI dependency.
Full external KITTI or nuScenes tracking data when running dataset-level tracking or metrics; detection text files alone are not sufficient for main.py.
Optional nuScenes dependencies when running nuScenes conversion or official evaluation.

Safe first check from this generated skill directory, pointing it at an AB3DMOT checkout:

bash
python scripts/ab3dmot_environment_check.py --repo-root /path/to/AB3DMOT --smoke-track

If the Xinshuo toolbox is not already importable, also pass --toolbox-root <path-to-Xinshuo_PyToolbox>.

Important constraints

AB3DMOT is not a detector; it consumes already-generated 3D detections.
The README quick KITTI demo command is explicit, but main.py parser defaults point at nuScenes. Always pass --dataset, --split, and --det_name deliberately.
KITTI val maps to the external KITTI training tree and a validation sequence list. KITTI test maps to the external testing tree.
nuScenes tracking uses the repo's KITTI-like data/nuScenes/nuKITTI/ intermediate tree.
Local test-set labels are unavailable for KITTI and nuScenes; official test metrics require external benchmark servers.

Verification status for this generated skill

This skill's lightweight repair checks cover Python syntax and CLI help only; the synthetic tracker smoke remains dependent on an external AB3DMOT checkout, NumPy/SciPy and the Xinshuo toolbox. Full benchmark-scale tracking/evaluation requires external datasets and is intentionally not run here.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ab3dmot AI skill do?

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

Why use Ab3dmot on TypingMind?

Because you install it once and use it with any model. Ab3dmot is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ab3dmot in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ab3dmot. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ab3dmot?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ab3dmot?

As many as you like. As long as a model supports skills, you can use Ab3dmot with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ab3dmot AI skill free?

Yes. It is published on GitHub by VectorSpaceLab under the NOASSERTION license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Weights And Biases

NousResearch

OrganizationPopular

W&B: log ML experiments, sweeps, model registry, dashboards.

Faiss

Fast vector similarity search at billion scale.

Serving Llms Vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Huggingface Hub

HuggingFace hf CLI: search/download/upload models, datasets.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

AB3DMOT repo skill

Start here

Route by workflow

Common task routing

Minimal runtime expectations

Important constraints

Verification status for this generated skill

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now