tabpfn SKILL.md skillA

tabpfn from magnus919/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add magnus919/agent-skills/tabpfn@git:20261013.11dbfbf

Pins git:20261013.11dbfbf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
magnus919/agent-skills
Path
tabpfn/SKILL.md
Versions recorded
1
Latest version
git:20261013.11dbfbf, committed Oct 13, 2026
Size
6,066 bytes
Repository stars
166
License
MIT

Operate and evaluate TabPFN for local tabular classification, regression and dataset-specific fine-tuning: checkpoint selection, weight licensing, environment setup, training-context leakage, calibration, resource budgeting and reproducible inference artifacts. Use for TabPFN package or checkpoint workflows. Do not use for generic model selection, operating TabICL, or language-model fine-tuning; use ml-engineering, the selected tool, or unsloth respectively.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# TabPFN

Deliver a pinned, task-evaluated TabPFN workflow rather than treating a sklearn-like
API as proof of compatibility, permission or predictive quality. TabPFN learns a
synthetic-data prior during pretraining and conditions on a labeled training table
at inference. Its ordinary `fit` is not necessarily dataset-specific gradient
training; explicit fine-tuning is a distinct operation.

## When not to use

- For choosing among trees, TabPFN, TabICL, sequence models and LLMs, load
  [ml-engineering](../ml-engineering/SKILL.md).
- For statistical design/calibration, use [data-scientist](../data-scientist/SKILL.md).
- For language-model SFT/LoRA/RL, use [unsloth](../unsloth/SKILL.md).
- TabICL has different models/APIs and terms. This skill does not operate it.

## First decision and authority

Identify classification versus regression, local package versus hosted client,
checkpoint generation, data schema and permission, commercial/production scope,
selected accelerator and run destination. Do not silently choose the latest
checkpoint: code and weight terms differ by release. A download may involve
license acceptance and authentication; task authorization does not authorize
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add magnus919/agent-skills/tabpfn@sha256:9def61ce79732fc6

The line at the top of this page pins the label git:20261013.11dbfbf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_aobtksgkczyxrfk6.svg)](https://markdownregistry.com/a/art_aobtksgkczyxrfk6)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 13, 2026.

versioncommittedcommitsizeaudit
git:20261013.11dbfbf latest2026-10-13 11dbfbf 6,066 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6066 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

magnus919/agent-skills · 166 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_aobtksgkczyxrfk6
GET https://markdownregistry.com/api/v1/resolve?ref=magnus919/agent-skills/tabpfn
GET https://markdownregistry.com/api/v1/blob/9def61ce79732fc6f5641fae2ffa658c4a79d15c41bbfb69c9b341b51f5cbbbc

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from magnus919/agent-skills

AGENTS.md AGENTS.md file
magnus919/agent-skills · AGENTS.md
git:20261010.bfe1eb1 · audit A · 166 stars
actuarial-risk-modeling SKILL.md skill
magnus919/agent-skills · actuarial-risk-modeling/SKILL.md · Use when analyzing, selecting, validating, or communicating models for insurance, actuarial, financial-risk, or other…
git:20260823.077c5d0 · audit A · 166 stars
adr-authoring SKILL.md skill
magnus919/agent-skills · adr-authoring/SKILL.md · Write, review, and maintain architecture decision records with clear context, alternatives, consequences, confirmation…
git:20260906.d8f3554 · audit A · 166 stars
agent-council SKILL.md skill
magnus919/agent-skills · agent-council/SKILL.md · Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware…
git:20260823.6efee5c · audit A · 166 stars
agent-evals-and-observability SKILL.md skill
magnus919/agent-skills · agent-evals-and-observability/SKILL.md · Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when…
git:20261103.c336267 · audit A · 166 stars
AGENTS.md@agent-production-operations AGENTS.md file
magnus919/agent-skills · agent-production-operations/AGENTS.md
git:20260814.c0c7690 · audit A · 166 stars
agent-production-operations SKILL.md skill
magnus919/agent-skills · agent-production-operations/SKILL.md · Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning…
git:20261103.c336267 · audit A · 166 stars
agent-skills SKILL.md skill
magnus919/agent-skills · agent-skills/SKILL.md · Use this skill when creating, reviewing, or editing Agent Skills-format skills, or when implementing skill discovery…
git:20261102.915225c · audit B · 166 stars
ai-governance SKILL.md skill
magnus919/agent-skills · ai-governance/SKILL.md · Design and operate AI governance: principles, decision rights, risk tiers, lifecycle gates, fairness, transparency…
git:20261101.83d2784 · audit A · 166 stars
ai-operating-economics SKILL.md skill
magnus919/agent-skills · ai-operating-economics/SKILL.md · Use when deciding whether an AI-enabled workflow should be adopted, scaled, constrained, redesigned, or retired, and…
git:20260821.1291f95 · audit A · 166 stars
amazon-memo SKILL.md skill
magnus919/agent-skills · amazon-memo/SKILL.md · Create, adapt, or revise Amazon-style narrative decision memos, six-pagers, PR/FAQs, and short decision briefs…
git:20261019.89945ee · audit A · 166 stars
analog-occultism SKILL.md skill
magnus919/agent-skills · analog-occultism/SKILL.md · Use this skill to create subject-neutral images and videos in an analog occultism / industrial CRT noir aesthetic…
git:20260905.3d54d7b · audit A · 166 stars

Every file in magnus919/agent-skills

Browse by kind, by grade A, or by owner.