NeMo Anonymizer skill

---
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
name: anonymizer
description: Use when the user wants to anonymize a text dataset, redact PII, de-identify free-text data, or rewrite text to remove sensitive or inferable identifying information. Produces a runnable Python script that calls the NeMo Anonymizer pipeline (detection → replace or rewrite).
license: Apache-2.0
metadata:
  author: Aaron Gonzales <aagonzales@nvidia.com>
---

# Before You Start

Do not explore the workspace first. The workflow's data-inspection step shows you what you need.

# Goal

Anonymize a text dataset using NeMo Anonymizer in the way the user describes:

$ARGUMENTS

The output is a single runnable Python script that builds an `AnonymizerConfig`, previews results on a few rows, inspects failures and quality metrics, optionally scores output with LLM-as-judge evaluation (Replace and Rewrite modes), and (on user approval) runs the full pipeline. The script is the durable artifact — the user keeps it for re-runs, version control, and production.

# Workflow

Read `references/interactive.md` and follow it. Anonymization is high-stakes,
so there is no autopilot mode. Even when the user says "you decide" or "be
opinionated", ask the minimum questions needed to choose `risk_tolerance` and
phrase `privacy_goal`. The user must make those choices based on their
regulatory and business context.

# Rules

- **Always preview before running the full pipeline.** Preview is cheap; a full run can be expensive and slow.
- **If `result.failed_records` is non-empty after preview, fix that *before* tweaking strategy.** Dropped rows are a model/provider/infra problem (rate limits, auth, etc.), not a config problem. Strategy knobs won't help. See `docs/troubleshooting.md` "Did the run actually complete cleanly?" or the [published troubleshooting guide](https://nvidia-nemo.github.io/Anonymizer/dev/troubleshooting/).
- **Ask the user which mode.** Briefly describe both: Replace detects entities and replaces each in place (faster, cheaper, keeps shape); Rewrite transforms the full text to also remove inferable identifiers (more expensive, may restructure). Use the data shape as a hint — free-text with implicit identifiers (clinical notes, biographies, depositions) leans Rewrite; structured records / log lines lean Replace — but the user picks.
- **For cross-record consistency** (same value → same replacement everywhere), use `Hash`, not `Substitute`. `Substitute` is consistent within a row only.
- **In Replace mode, default to `Substitute`** if the user hasn't specified a strategy. It's the most general-purpose choice and matches the bulk of production usage.
- **`Annotate` is for inspection, not production.** Its output keeps the original entity text and is not privacy-safe. Use it during iteration to confirm detection is working, then switch.
- **Evaluation is opt-in and runs as a separate step** (Replace and Rewrite modes). After `preview()` / `run()`, call `anonymizer.evaluate(result)` to score the output with LLM-as-judge. **Entity coverage always runs** in both modes — it reports detection recall over the judge's unique candidate values (`entity_coverage` + `missed_entities`). On top of that: Replace `Substitute` adds three quality judges (type fidelity, relational consistency, attribute fidelity); Rewrite adds the holistic privacy/quality/style judge. Detection validity is **opt-in** via `EvaluateConfig(compute_detection_validity=True)` (off by default). Evaluation is diagnostic — it scores quality, it does not change the anonymized output.
- **Always set `data_summary` on the input**, even briefly. It is the single cheapest quality lever and it improves both detection and rewrite.