Yolodex

Q: Why use Yolodex on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/qtzx06/yolodex/tree/main/.agents/skills/yolodex. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Yolodex?

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 Yolodex?

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

Q: Is the Yolodex AI skill free?

It is published on GitHub by qtzx06. Check the repository for licensing terms. 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.

Community

qtzx06

yolodex

Train a custom YOLO object detection model from any YouTube gameplay video. Provide a video URL and target classes, and this skill handles the entire pipeline autonomously — frame extraction, AI-powered labeling, data augmentation, training, and evaluation with iterative improvement.

Overview

Publisher	qtzx06
Repository	`yolodex`
Skill name	`yolodex`
Stars	96
Forks	13
Bundled files	Instructions only
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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by qtzx06 on GitHub. Read the source before you install it.

Installation

Install the Yolodex 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/qtzx06/yolodex/tree/main/.agents/skills/yolodex
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.

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/qtzx06/yolodex.git /tmp/yolodex
mkdir -p .claude/skills
cp -r /tmp/yolodex/.agents/skills/yolodex .claude/skills/yolodex

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

Use it in TypingMind

Enable Yolodex 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 Yolodex 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 Yolodex 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.

Intake Flow

When the user wants to train a model, gather the following:

Video source (required): YouTube URL or local file path (e.g. /Users/me/Desktop/gameplay.mp4)
Project name (required): Short kebab-case name (e.g. "subway-surfers", "fortnite-clips"). Output goes to runs/<project>/
Target classes (required): What objects to detect (e.g. "players, weapons, vehicles")
Labeling mode (required): Ask the user which labeling method to use:
- CUA+SAM (recommended): OpenAI CUA clicks on objects, SAM segments precise boundaries. Best accuracy. Requires OPENAI_API_KEY.
- Gemini: Google Gemini native bounding box detection. Fast, good accuracy. Requires GEMINI_API_KEY.
- GPT: GPT vision model returns bounding boxes via structured output. Simple fallback. Requires OPENAI_API_KEY.
- Codex: Codex subagents use built-in image viewing and write YOLO labels directly. No API keys.
Target accuracy (optional, default 0.75): mAP@50 threshold
Parallel agents (optional, default 4): How many labeling subagents (GPT mode only)

After Gathering Config

Write the values to config.json:

python
import json
config = json.load(open("config.json"))
config["project"] = "subway-surfers"  # output goes to runs/subway-surfers/
config["video_url"] = "<user's url or local path>"
config["classes"] = ["player", "weapon", ...]
config["label_mode"] = "cua+sam"  # or "gemini" or "gpt" or "codex"
config["target_accuracy"] = 0.75
config["num_agents"] = 4
json.dump(config, open("config.json", "w"), indent=2)

Then execute the pipeline phases in order by following the iteration logic in AGENTS.md:
- uv run .agents/skills/collect/scripts/run.py
- Labeling (based on mode):
  - CUA+SAM: uv run .agents/skills/label/scripts/label_cua_sam.py
  - Gemini: uv run .agents/skills/label/scripts/label_gemini.py
  - GPT (parallel / call subagent): bash .agents/skills/label/scripts/dispatch.sh
  - Codex (parallel / no-key): bash .agents/skills/label/scripts/dispatch.sh
  - GPT (single): uv run .agents/skills/label/scripts/run.py
- uv run .agents/skills/augment/scripts/run.py
- uv run .agents/skills/train/scripts/run.py
- uv run .agents/skills/eval/scripts/run.py
Check runs/<project>/eval_results.json — if accuracy < target, re-label failures and retrain.

Autonomous Mode

For fully autonomous execution, run: bash yolodex.sh This is a Ralph-style loop that iterates until target accuracy is reached.

Prerequisites

OPENAI_API_KEY environment variable (for CUA+SAM and GPT modes)
GEMINI_API_KEY or GOOGLE_API_KEY (for Gemini mode)
No API key required when using label_mode=codex + dispatch.sh
yt-dlp and ffmpeg installed
uv for Python dependency management
codex CLI (optional, for parallel subagent dispatch)

Frequently asked questions

What does the Yolodex AI skill do?

Why use Yolodex on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/qtzx06/yolodex/tree/main/.agents/skills/yolodex. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Yolodex?

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 Yolodex?

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

Is the Yolodex AI skill free?

It is published on GitHub by qtzx06. Check the repository for licensing terms. 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

Audio Jingle

nexu-io

OrganizationPopular

Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or…

Proof Video

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

Facetime

Inspect FaceTime internal stages, place an approved call to a configured owner handle, and request hangup through facetime_call.

Camsnap

Capture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Intake Flow

After Gathering Config

Autonomous Mode

Prerequisites

Frequently asked questions

Related AI Skills

Set up your own AI workspace now