Updated 6mo ago
by qtzx06
yolodex
agent skills for autonomous data labeling, winner at openai codex hackathon 2026
96 GitHub stars (96)
Steady at 96 stars — no new stars in the 16 days since Sep 30.
- 6 skills (6 skills found in its SKILL.md files)
- 13 forks (13 forks)
- 6mo ago last update (Last updated 6mo ago)
Install
Skills CLI
npx skills add qtzx06/yolodex
Asks which skills and agents to install. Just one: npx skills add qtzx06/yolodex --skill augment — add -g for every project.
Claude Code
git clone https://github.com/qtzx06/yolodexcp -r "yolodex/.agents/skills/augment" ~/.claude/skills/
Copies the augment skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add qtzx06/yolodex
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
augment
Generate synthetic training data variations using image transforms. Increases dataset diversity with flips, brightness jitter, and noise. Use after labeling.
.agents/skills/augment/SKILL.md on GitHub (opens in a new tab) -
collect
Download YouTube videos and extract frames using yt-dlp and ffmpeg for YOLO training data. Use when you need to gather frames from a video URL.
.agents/skills/collect/SKILL.md on GitHub (opens in a new tab) -
eval
Evaluate trained YOLO model accuracy with mAP metrics and per-class error analysis. Identifies failure cases for targeted improvement. Use after training.
.agents/skills/eval/SKILL.md on GitHub (opens in a new tab) -
label
Auto-label frames with bounding boxes. Supports four modes — CUA+SAM (best accuracy, OpenAI CUA clicks + SAM segmentation), Gemini (native bbox detection), GPT vision (API fallback), or Codex vision subagents (no API keys). Parallel dispatch via git worktrees. Use after collecting frames.
.agents/skills/label/SKILL.md on GitHub (opens in a new tab) -
train
Train a YOLO model on labeled dataset using ultralytics. Splits data into train/val, generates dataset.yaml, and produces trained weights. Use after labeling and augmenting.
.agents/skills/train/SKILL.md on GitHub (opens in a new tab) -
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.
.agents/skills/yolodex/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
-
graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs…
-
agent-skillsby addyosmani Production-grade engineering skills for AI coding agents.
-
paperclipby paperclipai The open-source app everyone uses to manage agents at work