Adelai Det

Q: Why use Adelai Det on TypingMind?

Because you install it once and use it with any model. Adelai Det 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.

Q: How do I install Adelai Det in TypingMind?

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

Q: Which AI models can use Adelai Det?

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.

Q: How many AI models can I use with Adelai Det?

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

Q: Is the Adelai Det 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.

Q: 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.

Q: 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.

Organization

VectorSpaceLab

adelai-det

Routes AdelaiDet users through legacy-compatible setup, model config selection, training/evaluation, demos, text spotting, dataset preparation, and export/conversion workflows.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`adelai-det`
Stars	341
Forks	26
Bundled files	29
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.
29 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 Adelai Det 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/adelai-det
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/adelai-det

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/adelai-det .claude/skills/adelai-det

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

Use it in TypingMind

Enable Adelai Det 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 Adelai Det 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 Adelai Det 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.

AdelaiDet

AdelaiDet is an AIM/Adelaide Detectron2-based research platform for instance-level recognition: object detection, instance segmentation, text spotting, keypoint detection, and related deployment utilities. Use this repo skill when a task names AdelaiDet, adet, FCOS, BlendMask, CondInst, BoxInst, SOLOv2, BAText/ABCNet, MEInst, FCPose, DenseCL, or asks how to train, evaluate, demo, prepare data, or export models for this repository.

Start here

Read references/repo-provenance.md before refreshing the skill or checking whether the source snapshot matches a task.
Read references/compatibility.md before installing or building AdelaiDet. This repo is legacy Detectron2 code and needs a version-compatible PyTorch/CUDA stack.
Read references/model-overview.md to choose a config family and understand which workflow owns it.
Read references/api-reference.md for the verified import surface, config keys, registries, custom ops, and public CLIs.
Read references/troubleshooting.md when install, import, CUDA extension, CLI, dataset, checkpoint, or export errors appear.

Install and smoke-check

The verified runtime stack is CUDA-capable and legacy-compatible:

Python 3.9
PyTorch 1.10.x with CUDA 11.3
TorchVision 0.11.x
Detectron2 0.6 built for the same PyTorch/CUDA pair
AdelaiDet installed editable from a matching source checkout
Pillow <10, rapidfuzz <3, NumPy 1.23.x, and OpenCV headless 4.8.x

Do not start with a modern PyTorch 2.x stack for unmodified AdelaiDet CUDA extensions: the source includes legacy THC headers in ml_nms.cu that are absent from PyTorch 2.x.

After installation, run the skill-owned smoke check:

bash
python scripts/check_install.py --cuda-ops

Run without --cuda-ops only when you intentionally need a CPU/import-only diagnosis.

Route map

`setup-build`

Use this route for environment creation, Detectron2/PyTorch/CUDA versioning, editable builds, compiled adet._C checks, custom op smoke tests, and install failure diagnosis.

Read:

sub-skills/setup-build/SKILL.md
sub-skills/setup-build/references/setup-build.md
sub-skills/setup-build/references/runtime-checks.md

`train-eval`

Use this route for Detectron2-style AdelaiDet training, evaluation, config overrides, model-family selection for training, checkpoints, distributed launches, and output directory expectations.

Read:

sub-skills/train-eval/SKILL.md
sub-skills/train-eval/references/train-eval-workflows.md
sub-skills/train-eval/references/config-selection.md

`demo-visualize`

Use this route for image/video/webcam demos, VisualizationDemo, confidence thresholds, text/non-text visualizations, and dataset visualization.

Read:

sub-skills/demo-visualize/SKILL.md
sub-skills/demo-visualize/references/demo-workflows.md
sub-skills/demo-visualize/references/visualization.md

`text-spotting`

Use this route for ABCNet/BAText, BezierAlign, text datasets, custom dictionaries, lexicons, text evaluation, and OCR-specific pitfalls.

Read:

sub-skills/text-spotting/SKILL.md
sub-skills/text-spotting/references/text-workflows.md
sub-skills/text-spotting/references/text-data-and-eval.md

`data-prep`

Use this route for COCO/PIC/LVIS/text dataset layouts, semantic mask generation, dataset registration, mapper expectations, MEInst mask encoding, and data validation.

Read:

sub-skills/data-prep/SKILL.md
sub-skills/data-prep/references/dataset-preparation.md
sub-skills/data-prep/references/data-formats.md

`export-convert`

Use this route for checkpoint key conversion, optimizer stripping, FCOS/BlendMask weight migration, ONNX export, and optional Caffe/NCNN/TensorRT deployment caveats.

Read:

sub-skills/export-convert/SKILL.md
sub-skills/export-convert/references/export-and-checkpoints.md
sub-skills/export-convert/references/onnx-export.md

Skill-owned scripts

scripts/check_install.py — verify import, Detectron2 registries, config keys, and optionally CUDA custom ops.
Sub-skill scripts wrap or adapt the repository workflows with preflight validation. When a script asks for --repo-root, pass a source checkout matching the provenance baseline or a refreshed AdelaiDet checkout.

Operating cautions

Full training, evaluation, demos with real images, and ONNX runtime validation need external datasets, model weights, and sometimes extra runtimes. Use help/dry-run checks first.
ONNX/Caffe/NCNN/TensorRT shell pipelines from the source repository are reference-only here because they assume external workspaces and large artifacts.
Keep installation/build issues routed to setup-build; do not debug model configs until scripts/check_install.py --cuda-ops passes for CUDA workflows.

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 Adelai Det AI skill do?

Routes AdelaiDet users through legacy-compatible setup, model config selection, training/evaluation, demos, text spotting, dataset preparation, and export/conversion workflows.

Why use Adelai Det on TypingMind?

Because you install it once and use it with any model. Adelai Det 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 Adelai Det in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/adelai-det. 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 Adelai Det?

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 Adelai Det?

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

Is the Adelai Det 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

AdelaiDet

Start here

Install and smoke-check

Route map

setup-build

train-eval

demo-visualize

text-spotting

data-prep

export-convert

Skill-owned scripts

Operating cautions

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

`setup-build`

`train-eval`

`demo-visualize`

`text-spotting`

`data-prep`

`export-convert`