tabpfn-classify

tabpfn-classify is a skill for Claude Code from dianaprior/kaggle-competition-agent-skill. It costs 51 tokens per session (3,180 once invoked), scanned A, original, no licence file.

A machine-learning workflow for creating a TabPFN classification baseline and an initial competition submission. Classification means assigning data to categories; the workflow also tests features and improves the model using other tree-based models, decision thresholds, and probability adjustment.

In plain words
What is it for?
Use it to create a first classification submission, test input features, combine models, choose decision thresholds, and calibrate predicted probabilities.
Why use it?
It provides a structured starting point for classification work after the data and cross-validation folds have been prepared.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to create a first classification submission, test input features, combine models, choose decision thresholds, and calibrate predicted probabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify
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 dianaprior/kaggle-competition-agent-skill --skill tabpfn-classify
Clone the repo
git clone --depth 1 https://github.com/dianaprior/kaggle-competition-agent-skill

Made for: Claude Code.

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 tabpfn-classify

README.md
[![agentmods](https://agentmods.dev/badge/skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify/github.svg)](https://agentmods.dev/skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify)
Your own site
<a href="https://agentmods.dev/skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify"><img src="https://agentmods.dev/badge/skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify/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 tabpfn-classify

Your own site · 80×15
<a href="https://agentmods.dev/skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify"><img src="https://agentmods.dev/badge/skills/dianaprior/kaggle-competition-agent-skill/tabpfn-classify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,180 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 unknown 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 $0.00051 $0.03180
Opus 5 $0.00026 $0.01590
Sonnet 5 $0.00010 $0.00636
Haiku 4.5 $0.00005 $0.00318

Measured 9d ago against content hash 0a9773032cdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tabpfn-classify 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 9d 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.

.claude/skills/tabpfn-classify/SKILL.md · 340 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 9d ago First seen · 340 lines · 51 tokens per session scan A 0a9773032cdd

Subscribe to this mod's changes

tabpfn-classify is a skill published in the GitHub repository dianaprior/kaggle-competition-agent-skill (5 stars, last pushed 6mo ago), with no licence file. It adds 51 tokens to every session and 3,180 once invoked, about $0.0003 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

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates · 32 tokens

liter-llm

Universal LLM API client for 165 providers with native bindings for 14 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C, when running the OpenAI-compatible proxy, or when calling LLMs through the MCP server. Covers chat…

xberg-io/liter-llm · 117 tokens

calling-llms

Use when sending chat completions through liter-llm and routing to a specific provider via the provider/model prefix. Covers the chat call shape, provider routing, modelhint, message roles, and error categories.

xberg-io/liter-llm · 49 tokens

embeddings-and-search

Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.

xberg-io/liter-llm · 48 tokens

running-the-proxy

Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.

xberg-io/liter-llm · 50 tokens

streaming-responses

Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chatstream, delta handling, and null-content chunks.

xberg-io/liter-llm · 39 tokens