TypingMindTypingMindThe best frontend for AI
Evaluation Visualization logo

Evaluation Visualization

Organization
VectorSpaceLab
evaluation-visualization

Evaluate, threshold, combine, and visualize AB3DMOT KITTI and nuScenes tracking results.

Overview

PublisherVectorSpaceLab
RepositoryAREX-Skill
Skill nameevaluation-visualization
Stars
341
Forks
26
Bundled files
5
LicenseNOASSERTION
Links
Skill sourceRepository
  • 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.

  • 5 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 Evaluation Visualization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ab3dmot/sub-skills/evaluation-visualization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/sub-skills/evaluation-visualization .claude/skills/evaluation-visualization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Evaluation Visualization 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 Evaluation Visualization 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 Evaluation Visualization 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 evaluation and visualization router

Use this sub-skill when a future agent already has AB3DMOT tracking outputs and needs to evaluate, threshold, package, combine, inspect, or visualize them. It covers completed KITTI and nuScenes result folders only.

Do not use this sub-skill to prepare raw datasets, convert detections into tracker inputs, or run the tracker. Route those tasks to the data-conversion or tracking-pipeline sub-skills.

Route by task

  • KITTI local validation metrics, 3D/2D IoU choices, and KITTI test-server submission packaging: read references/kitti-evaluation.md.
  • nuScenes result export, official local evaluation, quick validation evaluation, optional dependencies, and test-server packaging: read references/nuscenes-evaluation.md.
  • Interpreting results/<dataset>/<result_sha>/, combined/category folders, hypothesis folders, thresholded folders, affinity output, and visualization folders: read references/result-layout.md.
  • Failures involving result SHA names, missing data_0/trk_withid_0, threshold selection, missing nuScenes JSON, or visualization image/calibration roots: read references/troubleshooting.md.
  • To generate safe shell command sequences without importing AB3DMOT or touching data, run scripts/build_postprocess_commands.py.

Use this route for

  • Building KITTI validation metric commands for 3D IoU thresholds such as 0.25, 0.5, and strict Car-only 0.7.
  • Building KITTI 2D MOT commands at 0.5 IoU and preparing thresholded test-submission folders.
  • Applying AB3DMOT's detector/category confidence thresholds before 2D MOT submission or qualitative visualization.
  • Converting AB3DMOT nuScenes tracking output to results_<split>.json before official nuScenes tracking evaluation.
  • Choosing between official nuScenes evaluation and the quicker KITTI-style validation diagnostic.
  • Rendering image/video visualizations from trk_withid_<hypothesis>/ result folders.

Do not use this route for

  • Creating raw KITTI or nuScenes data trees; use data-conversion first.
  • Running main.py; use tracking-pipeline first.
  • Claiming official test-set metrics without an external benchmark-server result.
  • Debugging detector-row schemas before tracking; use the data-conversion validator.

Operating assumptions

  • Evaluation/visualization commands run from the root of an AB3DMOT checkout with its runtime dependencies available; the generated skill directory only provides routing and command-building helpers.
  • result_sha is the folder basename under results/KITTI/ or results/nuScenes/, for example pointrcnn_val_H1, pointrcnn_test_H1, or megvii_val_H1.
  • Evaluation and visualization are downstream of tracking; if the expected result folder is absent, first produce the tracking results rather than changing these commands.
  • Local validation metrics require local validation labels or converted nuScenes metadata. Test-set metrics require external benchmark servers because test labels are not shipped to users.

Fast preflight

  1. Confirm results/<dataset>/<result_sha>/data_0 exists before metrics.
  2. Confirm results/<dataset>/<result_sha>/trk_withid_0 exists before visualization or confidence-threshold output checks.
  3. For nuScenes official evaluation, confirm results/<split>.json exists or run the result-export command first.
  4. Use the bundled command builder to print commands before running scripts that mutate result folders.

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 Evaluation Visualization AI skill do?

Evaluate, threshold, combine, and visualize AB3DMOT KITTI and nuScenes tracking results.

Why use Evaluation Visualization on TypingMind?

Because you install it once and use it with any model. Evaluation Visualization 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 Evaluation Visualization 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/sub-skills/evaluation-visualization. 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 Evaluation Visualization?

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 Evaluation Visualization?

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

Is the Evaluation Visualization 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.

Related AI Skills

View all
affaan-m logo

X Api

affaan-m
CommunityPopular

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants…

40.4K
270.2K
1 files
View
affaan-m logo

Postgres Patterns

affaan-m
CommunityPopular

Patrones de base de datos PostgreSQL para optimización de consultas, diseño de esquemas, indexación y seguridad. Basado en las buenas prácticas de Supabase.

39.1K
261.1K
Instructions
View
affaan-m logo

Android Clean Architecture

affaan-m
CommunityPopular

Android と Kotlin Multiplatform プロジェクトのクリーンアーキテクチャパターン — モジュール構造、依存関係ルール、UseCase、Repository、データ層パターン。

39.1K
261.1K
Instructions
View
NousResearch logo

Blackbox

NousResearch
OrganizationPopular

Delegate coding tasks to the Blackbox AI multi-model CLI.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇