bold5000-skill

Orchestrates BOLD5000 dataset download, BIDS validation, and task-fMRI processing workflows.

89|5|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill bold5000-skill-cuhk-aim-group
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bold5000-skill
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/bold5000-skill
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill bold5000-skill-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, and includes scripts (resource) components.

What problem does it solve? Working with the BOLD5000 visual fMRI dataset requires coordinating multiple steps: downloading from OpenNeuro, validating BIDS structure, extracting stimulus metadata, and running modality-specific preprocessing. This Skill orchestrates that entire pipeline so researchers can go from raw data to analysis-ready outputs without manually chaining tools. ## Core Features & Use Cases - End-to-End Dataset Orchestration: Coordinates download from OpenNeuro, BIDS staging and validation, and delegation to structural MRI and task-fMRI processing pipelines. - Stimulus Metadata Extraction: Generates per-image metadata CSVs linking 5,000 visual stimuli to fMRI event onsets, durations, and category labels. - QC Summary Generation: Produces per-subject quality control reports from fMRIPrep confounds with framewise displacement thresholds and exclusion lists. - Use Case: A vision neuroscience researcher wants to analyze BOLD5000 data. The Skill downloads the dataset, validates its BIDS structure, extracts stimulus metadata, runs fMRIPrep-based processing, and outputs QC summaries under a unified bold5000_output/ directory. ## Quick Start Ask the agent to download the BOLD5000 dataset from OpenNeuro and run the full BIDS staging and task-fMRI processing workflow.

Frequently Asked Questions about bold5000-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download and process the BOLD5000 dataset?

The Skill downloads BOLD5000 from OpenNeuro (dataset ds002785) using the openneuro CLI or datalad, then validates the BIDS structure and delegates processing to structural MRI and task-fMRI pipelines. Outputs are organized under a bold5000_output/ directory.

How to extract BOLD5000 stimulus metadata for fMRI analysis?

Run the extract_bold5000_stimulus.py script with the stimulus directory path to generate a metadata CSV. It detects image categories from filenames and links stimuli to event file onsets, durations, and trial types.

Is BOLD5000 data already in BIDS format?

Yes, BOLD5000 from OpenNeuro is already BIDS-formatted, so re-staging is often unnecessary. The reorganize script validates the structure by checking dataset_description.json, participants.tsv, and subject anat/func directories.

What QC metrics does the BOLD5000 pipeline check?

The QC script parses fMRIPrep confounds files to compute mean and max framewise displacement per subject. Subjects exceeding the default 0.3mm mean FD or 5.0mm max FD thresholds are flagged in an exclusion list.

What are the limitations of BOLD5000 for group analysis?

BOLD5000 has only 4 participants, which limits statistical power for group-level analyses. Its high-density repeated image presentations also require analysis methods that handle repeated measures designs.