Text Spotting

Q: Why use Text Spotting on TypingMind?

Because you install it once and use it with any model. Text Spotting 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 Text Spotting 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/text-spotting. 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 Text Spotting?

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 Text Spotting?

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

Q: Is the Text Spotting 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

text-spotting

Guides AdelaiDet BAText/ABCNet text spotting, BezierAlign, text datasets, dictionaries, lexicons, and TextEvaluator workflows.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`text-spotting`
Stars	341
Forks	26
Bundled files	2
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.
2 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 Text Spotting 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/text-spotting
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/text-spotting

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/text-spotting .claude/skills/text-spotting

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

Use it in TypingMind

Enable Text Spotting 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 Text Spotting 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 Text Spotting 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.

text-spotting

Use this sub-skill when a task names BAText, ABCNet, BezierAlign, scene text, text spotting, OCR recognition, lexicons, dictionaries, text evaluation, or Bezier control-point annotations in AdelaiDet.

Use this route for

Choosing and editing BAText/ABCNet configs.
Preparing text datasets and Bezier/control-point annotations.
Understanding BezierAlign, TextEvaluator, custom dictionaries, and lexicons.
Running text-model demos after setup succeeds.
Debugging missing recognized strings, evaluator failures, rapidfuzz issues, or text visualization problems.

Do not use this route for

General installation and CUDA extension failures. Use ../setup-build/SKILL.md.
Non-text FCOS/BlendMask/CondInst training. Use ../train-eval/SKILL.md.
General COCO/PIC/LVIS conversion unrelated to text. Use ../data-prep/SKILL.md.
Checkpoint/ONNX conversion. Use ../export-convert/SKILL.md.

Read first

references/text-workflows.md for BAText/ABCNet config, training, demo, and evaluation flow.
references/text-data-and-eval.md for annotation fields, dictionaries, lexicons, and evaluator caveats.
../../references/api-reference.md for verified BezierAlign/TextEvaluator surfaces.

Typical workflow

Confirm setup with CUDA ops:

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

Choose a configs/BAText/ YAML and inspect MODEL.BATEXT keys.
Validate text dataset annotations through data-prep if files are custom.
For training/eval, use train-eval launch wrappers and add text-specific overrides.
For visualization, use demo-visualize wrappers with the text config/weights.
Interpret recognition/evaluation results here, not in generic detection routes.

Decision points

rapidfuzz.string_metric error: pin rapidfuzz<3 in setup.
BezierAlign op failure: return to setup-build; text pooling depends on adet._C.
Boxes draw but text is blank/wrong: check dictionary/lexicon config and annotation transcription fields.
Dataset lacks Bezier points: route to data-prep; box-only COCO annotations are insufficient for text recognition.
Evaluation protocol disagreement: identify the target benchmark lexicon/protocol before comparing numbers.

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 Text Spotting AI skill do?

Guides AdelaiDet BAText/ABCNet text spotting, BezierAlign, text datasets, dictionaries, lexicons, and TextEvaluator workflows.

Why use Text Spotting on TypingMind?

Because you install it once and use it with any model. Text Spotting 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 Text Spotting 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/text-spotting. 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 Text Spotting?

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 Text Spotting?

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

Is the Text Spotting 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

Release Openclaw Ci

openclaw

OrganizationPopular

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Release Openclaw Mac

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

Release Openclaw Maintainer

openclaw

OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

Release Openclaw Plugin Testing

openclaw

OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

text-spotting

Use this route for

Do not use this route for

Read first

Typical workflow

Decision points

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now