Yolo Training

What it does

When your agent uses it

• Asks to improve my mAP
• Why is my model overfitting
• My training is diverging
• Read my results.csv

Example prompts

• “improve my mAP”
• “why is my model overfitting”
• “my training is diverging”
• “/yolo-training”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Epochs and schedule. Undertrained looks like every other problem, and it costs nothing
2. 2Augmentation. The knob for the generalization gap, at no extra compute per epoch.
3. 3Loss weights and LR. Cheap, and the curves usually say which one is wrong.
4. 4Model size. Scale up when train loss is still falling at the end of the schedule and the
5. 5Resolution. Compute scales with the square of imgsz, so 640 to 1280 is roughly 4x the
6. 6Data, label quality and class balance. The highest ceiling and the slowest to move. The

What it can do on your machine

Read from SKILL.md and the folder at commit 7a519d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python and bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Yolo Training loads about 1.4k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 669 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~121

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from fcakyon/claude-codex-settings at commit 7a519d8, republished under its Apache-2.0 licence (© fcakyon). 669 words, ~1,390 tokens.

name

yolo-training

description

This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but AP50-95 is bad", "my recall is low", "how do I pick learning rate", "which augmentations should I use", "should I use a bigger model", "tune hyperparameters", or asks how to train YOLO26 for detection, instance or semantic segmentation, pose, OBB, classification, or depth.

import pandas as pd

df = pd.read_csv("runs/detect/train/results.csv")
df.columns = df.columns.str.strip()
print(df.tail(10)[["epoch", "train/box_loss", "val/box_loss", "metrics/mAP50(B)", "metrics/mAP50-95(B)"]])
print("best epoch:", df["metrics/mAP50-95(B)"].idxmax(), "of", len(df))

yolo train model=yolo26s.pt data=my-data.yaml epochs=200 imgsz=640 batch=16 \
  optimizer=AdamW lr0=0.001 lrf=0.01 cos_lr=True warmup_epochs=3 \
  patience=50 close_mosaic=20

© fcakyon, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in plugins/ultralytics-dev/skills/yolo-training of fcakyon/claude-codex-settings.

• SKILL.md
• references/diagnostics.md
• references/task-notes.md

Open the folder on GitHubat commit 7a519d8

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in fcakyon/claude-codex-settings, which our catalogue first saw on October 7, 2026.

• majiayu000/claude-skill-registryskills/ai-ml/yolo-training