Skip to content
Back to skills

Data Configuration

ASecurity

"Configure MMSegmentation configs, datasets, transforms, class

  • 247 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 8, 2026
devopstestingapi

Works with

  • api

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill data-configuration --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Data Configuration?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Data Configuration
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-data-configuration/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-data-configuration)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: data-configuration
description: "Configure MMSegmentation configs, datasets, transforms, class
  palettes, and safe dataset layout checks."
disable-model-invocation: true
metadata:
  disco-role: operating
license: Apache 2.0
---

# Data Configuration

Use this sub-skill when an MMSegmentation task is about experiment config files, MMEngine config inspection, dataset layout preparation, dataset classes, transform pipelines, class metadata, palettes, or dataset conversion planning.

## Route Here For

- Inspecting a config, expanding `_base_` inheritance, checking config naming, or applying `--cfg-options` overrides before a run.
- Preparing semantic segmentation dataset directories, suffixes, split files, `data_prefix`, `ann_file`, and `BaseSegDataset` arguments.
- Choosing or editing `LoadAnnotations`, augmentation transforms, `PackSegInputs`, class subsets, palettes, `ignore_index`, or `reduce_zero_label`.
- Understanding packaged config catalogs, `model-index.yml`, `dataset-index.yml`, and native dataset converter patterns without depending on source checkout scripts.

## Stay Out Of

- Launching training, validation, testing, distributed jobs, checkpoint resume, and metric interpretation; use the training/evaluation sub-skill.
- Implementing segmentors, heads, losses, backbones, registries, or custom model components; use the model customization sub-skill.
- Running inference APIs, visualization of model predictions, or deployment runtimes; use the inference sub-skill.

## First Moves

1. Read `references/configuration.md` for config inheritance, naming, inspection, and override rules.
2. Read `references/datasets-and-transforms.md` for dataset layout, `BaseSegDataset`, transform, class, palette, and label-index contracts.
3. Read `references/dataset-conversion.md` before converting raw datasets; converters are dataset-specific and reference-only here.
4. Use `scripts/inspect_mmseg_config.py --help` and `scripts/check_dataset_layout.py --help` to inspect configs and validate dataset file pairing safely.
5. If behavior is surprising, check `references/troubleshooting.md` before editing configs or data files.

## Bundled Tools

- `scripts/inspect_mmseg_config.py` expands an MMEngine config, applies optional `--cfg-options`, prints selected keys, and only writes output when `--dump` is explicitly provided.
- `scripts/check_dataset_layout.py` checks image/annotation directory existence, suffix counts, expected image-to-mask pairing, optional split files, and label-index notes without importing MMSegmentation.

Files in this skill

  • SKILL.md2.5 KB
  • references/configuration.md5.4 KB
  • references/dataset-conversion.md4.7 KB
  • references/datasets-and-transforms.md7.6 KB
  • references/troubleshooting.md4.6 KB
  • scripts/check_dataset_layout.py7.4 KB
  • scripts/inspect_mmseg_config.py5.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.