How do I install the REPLACE-WITH-SKILL-NAME skill?

Run npx skillmds@latest add nvidia-tao/replace-with-skill-name in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is REPLACE-WITH-SKILL-NAME safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with REPLACE-WITH-SKILL-NAME?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is REPLACE-WITH-SKILL-NAME free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Apache-2.

Who published REPLACE-WITH-SKILL-NAME?

NVIDIA-TAO (@nvidia-tao) published this skill. Their other Agent Skills are listed on their SkillMD profile.

REPLACE-WITH-SKILL-NAME by nvidia-tao

Name: REPLACE-WITH-SKILL-NAME
Rating: 4.2 (5 reviews)
Author: NVIDIA-TAO

REPLACE-WITH-SKILL-NAME

One-to-three-sentence description of what this data transformation does. Use when the user asks to "REPLACE-WITH-INTENT", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases the user is likely to say.

NVIDIA-TAO 3e3d3a9 3 files · 4.2 KB Updated Sep 10, 2026

File contents

Skill Name

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Two-line summary of the transformation. Inputs → outputs.

External dependencies

Dependency	Purpose	Install
docker	Run the container	https://docs.docker.com/engine/install/

(or for local scripts)

Dependency	Purpose	Install
Python 3.8+	Runtime	System / conda
Pillow	Image I/O	`pip install pillow`

Quick start

Containerized

docker run --gpus all --rm \
  -v /path/to/input:/input \
  -v /path/to/output:/output \
  nvcr.io/nvidian/iva/<image>:<tag> \
  <command> --input /input --output /output

Local Python script

python scripts/<script>.py --input-dir <path> --output <path>

Multi-defect / multi-source loop (advanced)

for label in bridge tombstone shift; do
  python scripts/<script>.py --input-dir data/${label}/ --output ${label}.csv --label ${label}
done

See tao-skill-bank:tao-run-on-docker for docker conventions (when containerized).

Inputs

Field	Type	Description
`<input-dir>`	folder	What's in it, expected format
`<input-parquet>`	file	Schema, columns

Outputs

Field	Type	Description
`<output-csv>`	file	Schema produced

CLI Reference

Argument	Required	Default	Description
`--input-dir`	Yes	—	Input directory
`--output`	No	`output.csv`	Output path
`--label`	No	auto-detect	Force single label for all rows

How it works

Step-by-step description of the transformation:

Step 1
Step 2

Optional pipeline diagram:

Input A ─┐
Input B ─┼─→ [processing] ─→ Output
Input C ─┘

Caveats

Document non-obvious behaviors, edge cases, permission quirks.

Known pitfalls

Symptom	Cause	Fix
`KeyError: ...`	Wrong column name in input parquet	Use `--column-name` to override

---name: replace-with-skill-namedescription: One-to-three-sentence description of what this data transformation does. Use when the user asks to "REPLACE-WITH-INTENT", or mentions REPLACE-WITH-DOMAIN-TERMS. Include literal trigger phrases the user is likely to say.license: Apache-2.0---# Skill Name> **Standalone install?** If this session was not initialized by the TAO skill bank plugin, run the `tao-setup` skill first (host preflight, credentials, cross-skill discovery).Two-line summary of the transformation. Inputs → outputs.## External dependencies| Dependency | Purpose | Install ||---|---|---|| docker | Run the container | https://docs.docker.com/engine/install/ |(or for local scripts)| Dependency | Purpose | Install ||---|---|---|| Python 3.8+ | Runtime | System / conda || Pillow | Image I/O | `pip install pillow` |## Quick start### Containerized```bashdocker run --gpus all --rm \ -v /path/to/input:/input \ -v /path/to/output:/output \ nvcr.io/nvidian/iva/<image>:<tag> \ <command> --input /input --output /output```### Local Python script```bashpython scripts/<script>.py --input-dir <path> --output <path>```### Multi-defect / multi-source loop (advanced)```bashfor label in bridge tombstone shift; do python scripts/<script>.py --input-dir data/${label}/ --output ${label}.csv --label ${label}done```See `tao-skill-bank:tao-run-on-docker` for docker conventions (when containerized).## Inputs| Field | Type | Description ||---|---|---|| `<input-dir>` | folder | What's in it, expected format || `<input-parquet>` | file | Schema, columns |## Outputs| Field | Type | Description ||---|---|---|| `<output-csv>` | file | Schema produced |## CLI Reference| Argument | Required | Default | Description ||---|---|---|---|| `--input-dir` | Yes | — | Input directory || `--output` | No | `output.csv` | Output path || `--label` | No | auto-detect | Force single label for all rows |## How it worksStep-by-step description of the transformation:1. Step 12. Step 2Optional pipeline diagram:```Input A ─┐Input B ─┼─→ [processing] ─→ OutputInput C ─┘```## Caveats- Document non-obvious behaviors, edge cases, permission quirks.## Known pitfalls| Symptom | Cause | Fix ||---|---|---|| `KeyError: ...` | Wrong column name in input parquet | Use `--column-name` to override |

Frequently asked questions