> ## Documentation Index
> Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# Agent Skill α

> Install the TabPFN-Rel skill so Claude Code or Codex can set up and run relational predictions on your data

The `relational-prediction` skill guides a coding agent from raw tables and a plain-language question to a scored [TabPFN-Rel](/capabilities/relational) task. It works in Claude Code and Codex, and installs as a plugin from the [TabPFN-Rel repository](https://github.com/PriorLabs/tabpfn-rel).

With the skill, the agent:

1. Profiles every table and column, and identifies keys, time columns and columns that leak the future.
2. Proposes the data preparation and waits for your approval.
3. Writes the database YAML file and a rerunnable `prepare.py`.
4. Proposes two or three prediction tasks and lets you choose.
5. Writes the task YAML file and checks the label counts and class balance per split.
6. Compares TabPFN-Rel with constant and LightGBM baselines on held-out data.

The agent asks you before it changes data or picks the task.

## Install

**Claude Code**

In a Claude Code session, run:

```
/plugin marketplace add PriorLabs/tabpfn-rel
/plugin install tabpfn-rel@prior-labs
```

Start a new session. The skill is listed as `tabpfn-rel:relational-prediction`.

**Codex**

In a terminal, run:

```bash theme={null}
codex plugin marketplace add PriorLabs/tabpfn-rel
codex plugin add tabpfn-rel@prior-labs
```

Start a new session. The skill is listed as `tabpfn-rel:relational-prediction`.

The skill runs in your Python environment, which needs Python 3.11 or 3.12. On first use, the agent installs `tabpfn-rel[api]` and the [RelArena](https://github.com/PriorLabs/relarena) baselines there. For hosted inference, set `TABPFN_TOKEN` or run `tabpfn_client.init()` once; get a token at [platform.priorlabs.ai](https://platform.priorlabs.ai). Hosted fits consume API quota.

## Use

Open the agent in a directory with your tables (CSV or Parquet) and ask a question about them, for example:

> Which of these sellers will receive no orders in the next 30 days?

The agent writes its files to `data/<name>/` unless you choose another directory:

```
data/<name>/
  raw/            downloaded files, never edited
  prepare.py      raw -> tables/
  tables/         the prepared tables
  database.yaml   schema: keys, time columns, kept columns
  <task>.yaml     label SQL, prediction window, split timestamps
```

To try the skill on a public dataset, point the agent at the Olist database from the [TabPFN-Rel cookbook](/cookbook/relational_predictions_tabpfn_rel).

> [!TIP]
>
> Review the preparation the agent proposes. TabPFN-Rel assumes static rows: every value in a row was written at the row's timestamp and not changed afterwards. Drop any column that violates this, such as an order status or delivery date filled in after the order was placed.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.