bids

Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars, or creating BIDS derivatives.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A comprehensive, highly actionable BIDS skill with strong code examples and well-organized reference bundles, but it carries redundant inline content that overlaps its own reference files and lacks integrated validation feedback loops in the batch conversion workflows.

Suggestions

Move the BEP table and entity/suffix tables out of SKILL.md into the existing references/beps.yml and references/bids_specification.md, keeping only a brief pointer inline to reduce duplication.

Add an explicit validate->fix->retry checkpoint inside the HeuDiConv and dcm2bids conversion step sequences (e.g., 'Step 4: run bids-validator; if errors, fix and re-convert').

Trim the Overview's adoption details (repositories, journals, funding agencies) and the related-tools ecosystem table, which add context without aiding execution.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete, executable code, but the Overview's adoption narrative, the 25-row BEP table (already in references/beps.yml), and the related-tools table repeat reference-grade material that could be trimmed.	2 / 3
Actionability	Install commands, PyBIDS query snippets, dataset_description.json generation code, and bids-validator/heudiconv/dcm2bids/docker invocations are concrete, executable, and copy-paste ready.	3 / 3
Workflow Clarity	Conversion workflows are sequenced (Step 1/2/3) and validation has its own section plus a 'validate early and often' best practice, but the batch DICOM-to-BIDS steps lack an inline validate->fix->retry checkpoint, which caps this at 2 per the batch-operations rule.	2 / 3
Progressive Disclosure	Five reference files plus a script are clearly signaled via a Reference Materials section and inline pointers (one level deep), but the entity/suffix tables and BEP table are duplicated inline despite having dedicated reference files, which is the 'content that should be separate is inline' case.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, complete, and clearly distinct: it names concrete capabilities and an explicit 'Use this skill when' trigger tied to the BIDS domain.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — organizing data, querying layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars, and creating derivatives — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both 'when' ('Use this skill when working with BIDS datasets') and 'what' (the enumerated organizing/querying/validating/converting/writing/derivatives actions), matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	It covers natural terms users would say — 'BIDS', 'BIDS datasets', 'DICOM to BIDS', 'metadata sidecars', 'BIDS derivatives' — alongside modality names, giving good coverage rather than jargon-only.	3 / 3
Distinctiveness Conflict Risk	BIDS is a sharply defined niche with distinct triggers (BIDS, DICOM-to-BIDS, BIDS derivatives) that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (756 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/bids/SKILL.md
Commit: 757b63b

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.