agentmods.dev

dataset-preprocessing

dataset-preprocessing is a skill for Claude Code, Codex from aizech/clinical-skills. It costs 48 tokens per session (553 once invoked), scanned A, original, MIT.

A set of preprocessing methods for radiology data used to train AI systems. It covers formats such as DICOM and NIfTI, medical image normalization, resizing, artifact checks, and task-specific preparation.

In plain words
What is it for?
Use it to prepare radiology datasets, normalize or resample images, detect artifacts, generate masks, assess quality, and harmonize data from multiple sites or vendors.
Why use it?
Medical scans can differ in format, intensity, resolution, and quality across machines or hospitals. Preprocessing makes those inputs more suitable for detection, segmentation, classification, or regression models.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

not rated 6repo 4mo ago A scan 48 tokens original MIT

Good fit Use it to prepare radiology datasets, normalize or resample images, detect artifacts, generate masks, assess quality, and harmonize data from multiple sites or vendors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aizech/clinical-skills/dataset-preprocessing
View source ↗ aizech/clinical-skills corpusanalytica.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add aizech/clinical-skills --skill dataset-preprocessing
Clone the repo
git clone --depth 1 https://github.com/aizech/clinical-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dataset-preprocessing

README.md
[![agentmods](https://agentmods.dev/badge/skills/aizech/clinical-skills/dataset-preprocessing/github.svg)](https://agentmods.dev/skills/aizech/clinical-skills/dataset-preprocessing)
Your own site
<a href="https://agentmods.dev/skills/aizech/clinical-skills/dataset-preprocessing"><img src="https://agentmods.dev/badge/skills/aizech/clinical-skills/dataset-preprocessing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dataset-preprocessing

Your own site · 80×15
<a href="https://agentmods.dev/skills/aizech/clinical-skills/dataset-preprocessing"><img src="https://agentmods.dev/badge/skills/aizech/clinical-skills/dataset-preprocessing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00553
Opus 5.5 $0.00019 $0.00221
Sonnet 5.5 $0.00010 $0.00111
Haiku 4.5 $0.00005 $0.00055

Measured 1mo ago against content hash daffcf0e4cca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dataset-preprocessing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/dataset-preprocessing/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dataset Preprocessing Skill

Triggers

  • "preprocess radiology data"
  • "DICOM preprocessing"
  • "image normalization"
  • "data augmentation"
  • "quality control pipeline"
  • "mask generation"
  • "multi-site harmonization"
  • "training data preparation"

Parameters

  • input_format (required): Source data format
    • dicom - DICOM files
    • nifti - NIfTI volumes
    • metadata - Header/excel data
    • mixed - Multiple formats
  • task_type (required): Downstream ML task
    • detection - Object/bounding box detection
    • segmentation - Pixel-level segmentation
    • classification - Image classification
    • regression - Continuous value prediction
  • modality (optional): Imaging modality
  • multi_vendor (optional): Boolean for multi-site/multi-vendor data
  • dataset_scale (optional): Small (<1K), medium (1K-100K), large (>100K)

Preprocessing Components

Image Processing

  • Intensity normalization (z-score, min-max, percentile-based)
  • Windowing/leveling for CT/MRI
  • Resampling to isotropic voxel size
  • Brain extraction (skull stripping)
  • Bias field correction for MRI

Quality Control

  • Automated quality scoring
  • Artifact detection
  • Contrast-to-noise ratio
  • Resolution verification
  • Human-in-the-loop review for edge cases

Augmentation

  • Geometric: rotation, flip, scale, elastic deformation
  • Intensity: noise, contrast, brightness
  • Modality-specific: CT windowing variants, MRI sequence mixing
  • Generative: synthetic data augmentation

Format Conversion

  • DICOM to NumPy/PyTorch/TensorFlow
  • DICOM to NIfTI for volumetric data
  • Annotation format conversion (CSV, COCO, YOLO, Pascal VOC)

Output Format

Returns structured JSON with:

  • Processing pipeline steps
  • Code snippets for each transformation
  • Validation checks and statistics
  • Expected output specifications
  • Common pitfalls and mitigations

Usage Examples

input_format: dicom
task_type: detection
modality: CT
multi_vendor: true

input_format: nifti
task_type: segmentation
dataset_scale: large

Read the full file on GitHub · 83 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 83 lines · 48 tokens per session scan A daffcf0e4cca

Subscribe to this mod's changes

dataset-preprocessing is a skill published in the GitHub repository aizech/clinical-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 553 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AIScientificagent-skillsai-agentsclinical-aiclinical-decision-supporthealthcare-aillm-agents
Related

Other skills, from other repositories

cv-classification

Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.

aiming-lab/AutoResearchClaw · 26 tokens

cv-detection

Best practices for object detection tasks. Use when working on COCO, VOC, or detection architectures like YOLO and DETR.

aiming-lab/AutoResearchClaw · 30 tokens

experimental-design

Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.

aiming-lab/AutoResearchClaw · 25 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens

evo-simpo-code-reproduction

Implements the SimPO (Simple Preference Optimization) loss function and handles environment setup, execution, and result saving for code reproduction tasks.

OpenLAIR/OpenSkill · 36 tokens

evo-clinical-data-cleaning

Utility functions for cleaning raw clinical lab CSV data - handling decimal comma formats, scientific notation normalization, missing value detection, and numeric coercion of mixed-type columns.

OpenLAIR/OpenSkill · 41 tokens