autogluon-preset-strategy

autogluon-preset-strategy is a skill for Claude Code, Codex from topprismdata/cultivating-ml-agent. It costs 180 tokens per session (2,212 once invoked), scanned A, original, MIT.

A guide for choosing AutoGluon presets for tabular machine-learning data, meaning data arranged in rows and columns. It weighs dataset size, available graphics hardware, evaluation metric, training time, and prediction quality.

In plain words
What is it for?
Use it when selecting an AutoGluon starting preset, deciding whether to upgrade training quality, or configuring classification predictions and probability calibration.
Why use it?
It prevents spending hours on a preset that is too slow or too weak for the dataset and hardware. It also avoids using a single default choice when the task has different accuracy or probability-scoring needs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when selecting an AutoGluon starting preset, deciding whether to upgrade training quality, or configuring classification predictions and probability calibration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add topprismdata/cultivating-ml-agent --skill autogluon-preset-strategy
Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for autogluon-preset-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy/github.svg)](https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy)
Your own site
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for autogluon-preset-strategy

Your own site · 80×15
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/autogluon-preset-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,212 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00180 $0.02212
Opus 5 $0.00090 $0.01106
Sonnet 5 $0.00036 $0.00442
Haiku 4.5 $0.00018 $0.00221

Measured 11d ago against content hash ed2a84f07a36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

autogluon-preset-strategy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/examples/autogluon-preset-strategy/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoGluon Preset Strategy

Problem

autogluon-first says "use best_quality preset always". But:

  • best_quality takes 1-4 hours — wasted if you only need a quick baseline
  • medium_quality is the default but doesn't enable bagging/stacking → no OOF predictions
  • The choice between presets has a 5x time × accuracy tradeoff that the existing skill doesn't quantify

Decision Tree

N = training rows
N < 10K   → presets='best_quality' (single GBDT plateau is real concern)
N 10K-100K → presets='good_quality' first (10-30 min), upgrade to high if time allows
N > 100K  → presets='good_quality' is enough (data variance dominates model choice)

GPU available? 
  No → presets='high_quality' max (TabPFNv2 needs GPU)
  Yes → consider 'extreme_quality' (uses TabPFNv2, TabICL, Mitra)

Metric?
  balanced_accuracy / F1 → add calibrate_decision_threshold=True
  accuracy → default ('auto')
  log_loss → use predict_proba, no calibration

Preset Reference (from AG 1.4.0 docstring)

Preset Train Time OOF Available? Models When
medium_quality (default) ~5min ❌ No (auto_stack=False) 3 NEVER for serious use
good_quality 10-30min ✅ Yes 12 Default starting point
high_quality 30-60min ✅ Yes 14 When good isn't enough
best_quality 1-4h ✅ Yes ~100 Kaggle competition
extreme_quality 2-8h ✅ Yes 22+TabFM GPU only, 30K rows ideal

Why medium_quality has no OOF: AG's predict_oof() requires bag mode (auto_stack=False means no bag). The "val score" reported is in-sample on the holdout — not real OOF. Don't trust it.

Empirical Validation (s6e7, N=690K, 3-class)

Preset Time Models Best Val OOF OOF/Val gap
medium_quality 182s 3 0.8825 N/A N/A
good_quality 376s 12 0.8730 0.8730 0
high_quality 947s 14 0.8739 0.8739 0

Read the full file on GitHub · 192 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 192 lines · 180 tokens per session scan A ed2a84f07a36

Subscribe to this mod's changes

autogluon-preset-strategy is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 14d ago), licensed MIT. It adds 180 tokens to every session and 2,212 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

huggingface-hub

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

braxtonROSE4/zorro-agent · 43 tokens

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

davila7/claude-code-templates · 33 tokens

datachain-knowledge

Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…

datachain-ai/datachain · 104 tokens

prompt-scanner

A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.

alibaba/anolisa · 103 tokens

install-openviking-memory

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…

volcengine/OpenViking · 191 tokens