Menu
Use when invoking training, evaluation, and dataset preparation via CLI. Provides all standard commands for this project.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | cli-usage |
| description | Use when invoking training, evaluation, and dataset preparation via CLI. Provides all standard commands for this project. |
| triggers | ["train model","run training","evaluate","download dataset","cli commands","modal"] |
This skill covers all CLI commands for operating the tiny-cats-model project.
# Install dependencies
pip install -r requirements.txt
# Download and prepare dataset
bash data/download.sh
# Dataset will be at: data/cats/cat/ and data/cats/other/
# Basic training (10 epochs, resnet18)
python src/train.py data/cats
# Custom training
python src/train.py data/cats \
--epochs 20 \
--batch-size 64 \
--lr 0.0001 \
--backbone resnet34 \
--output my_model.pt
# Training without pretrained weights
python src/train.py data/cats --no-pretrained
# Evaluate with default settings
python src/eval.py
# Evaluate with custom checkpoint
python src/eval.py \
--data-dir data/cats \
--checkpoint cats_model.pt \
--backbone resnet18
# Run all unit tests
pytest tests/ -v
# Run with coverage
pytest tests/ -v --cov=src --cov-report=term-missing
# Lint
ruff check .
flake8 . --max-line-length=88
# Auto-fix lint issues
ruff check . --fix
# Format code
black .
# Check formatting without modifying
black --check .
# Set credentials globally (Modal 1.0+ uses 'token new')
modal token new
# Run training on GPU
modal run src/train.py
# Run with custom options
modal run src/train.py --epochs 20 --batch-size 64
--detach.volume.commit() after writing a checkpoint volume. We do this in both
train.py and train_dit.py.modal token new is the canonical auth command. The old modal token set (Modal
0.x) no longer works.Speed: 2.2 steps/s printed by the trainer reflects GPU
forward+backward only — wall-clock between step reports includes container cold-start,
image pull, dataset download, and per-iteration volume/ONNX overhead. See
plans/ADR-057-modal-cli-verification-and-best-practices-2026.md for the full breakdown.# Run complete CI check suite
bash .agents/skills/testing-workflow/verify.sh
# Or use the quality gate
bash .agents/skills/git-workflow/quality-gate.sh
# Or use the new scripts
bash scripts/quality-gate.sh
| Task | Command |
|---|---|
| Install | pip install -r requirements.txt |
| Dataset | bash data/download.sh |
| Train | python src/train.py data/cats |
| Evaluate | python src/eval.py |
| Tests | pytest tests/ -v |
| Lint | ruff check . && flake8 . |
| Format | black . |
| CI verify | bash .agents/skills/testing-workflow/verify.sh |
Enhance session checkpoints with git context and diff summaries. Use after completing significant work to enrich checkpoint.md files with repository state, recent commits, and code change summaries. Triggers include "enhance checkpoint", "update checkpoint with git", "add git context to checkpoint", or when finishing a multi-file change session.
Use for model training, hyperparameter tuning, and Modal GPU training.
Multi-perspective code analysis using three AI personas (RYAN, FLASH, SOCRATES) for comprehensive decision-making. Use when complex code decisions need analysis from multiple viewpoints, or when avoiding single-perspective blind spots is critical.
Use for authentication management, token validation, and credential troubleshooting.
Use for secrets management, credentials handling, and security best practices.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.