Train Eval

Organization

VectorSpaceLab

train-eval

Routes AdelaiDet config selection, training, evaluation, Detectron2 launch flags, checkpoints, and model-family run workflows.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`train-eval`
Stars	341
Forks	26
Bundled files	3
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.
3 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 Train Eval 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/sub-skills/train-eval
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/sub-skills/train-eval

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/sub-skills/train-eval .claude/skills/train-eval

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

Use it in TypingMind

Enable Train Eval 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 Train Eval 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 Train Eval 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.

train-eval

Use this sub-skill when a task asks how to train, evaluate, resume, benchmark, debug a config, or launch an AdelaiDet model family through the repository's Detectron2-style training workflow.

Use this route for

Selecting a config family for FCOS, BlendMask, CondInst, BoxInst, SOLOv2, MEInst, FCPose, DenseCL, or non-text detection/segmentation tasks.
Building safe AdelaiDet training/evaluation commands with config overrides.
Running --eval-only, --resume, distributed launch flags, or checkpoint-backed evaluation.
Understanding output directories, dataset names, solver/batch overrides, and MODEL.WEIGHTS behavior.
Diagnosing model registry/config errors after installation is already healthy.

Do not use this route for

Install/build/import failures. Use ../setup-build/SKILL.md first.
Text spotting lexicons/dictionaries/evaluation. Use ../text-spotting/SKILL.md.
Dataset conversion or semantic mask generation. Use ../data-prep/SKILL.md.
Demo visualization only. Use ../demo-visualize/SKILL.md.
Checkpoint key conversion or ONNX export. Use ../export-convert/SKILL.md.

Read first

references/config-selection.md to choose a model/config family.
references/train-eval-workflows.md for launch patterns, flags, and outputs.
../../references/model-overview.md for package-wide model routing.
../../references/api-reference.md for verified config and registry surfaces.

Skill-owned scripts

scripts/run_train_eval.py — validates common paths and builds/runs an AdelaiDet training or evaluation command. Use --dry-run before expensive jobs.

Typical workflow

Confirm setup:

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

Choose the config family and config YAML.
Confirm datasets are registered and available; switch to data-prep if not.

Dry-run the launch:

bash
python scripts/run_train_eval.py --repo-root /path/to/AdelaiDet \
  --config configs/FCOS-Detection/R_50_1x.yaml --num-gpus 1 --dry-run

Add --eval-only --model-weights /path/to/model.pth for evaluation-only runs, or --resume for continuation.
Inspect OUTPUT_DIR, logs, metrics, checkpoints, and evaluator output.

Decision points

If the task names BAText/ABCNet or text recognition, load text-spotting before finalizing training flags.
If the config references generated semantic masks, PIC/LVIS/COCO conversions, or MEInst components, load data-prep before launch.
If checkpoint keys mismatch, switch to export-convert for conversion utilities.
If No object named ... in registry appears, verify setup/import first, then check config family/key spelling.

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 Train Eval AI skill do?

Routes AdelaiDet config selection, training, evaluation, Detectron2 launch flags, checkpoints, and model-family run workflows.

Why use Train Eval on TypingMind?

Because you install it once and use it with any model. Train Eval 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 Train Eval 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/sub-skills/train-eval. 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 Train Eval?

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 Train Eval?

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

Is the Train Eval 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

Gstack Openclaw Ceo Review

garrytan

CommunityPopular

Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.

Caveman Stats

Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

Ci Metrics

Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics. Use when users ask about CI duration, job failures, queue times, workflow trends, runner health, dashboard data, or PyTorch…

Notcrawl

Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

train-eval

Use this route for

Do not use this route for

Read first

Skill-owned scripts

Typical workflow

Decision points

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now