CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

Well-structured, actionable content with excellent progressive disclosure and strong workflow guidance backed by validation emphasis. The main weakness is conciseness: the overview explains concepts Claude already knows and an inlined BEP status table adds time-sensitive bulk.

Suggestions

Trim the Overview's explanation of what BIDS is and how it originated — Claude already knows this; keep only the modality list and tooling pointers.

Move the full BEP status table into a reference file (or beps.yml-derived summary) and keep only a one-line pointer in the body, since the status data is time-sensitive and verbose.

Inline one or two short executable snippets for the highest-frequency workflows (e.g., a minimal PyBIDS query and a dcm2bids invocation) so the body is self-sufficient for common cases without opening references.

DimensionReasoningScore

Conciseness

Mostly efficient but padded in places — the Overview explains BIDS basics Claude already knows ('a community standard for organizing and describing... datasets') and the large BEP status table is time-sensitive bulk that could be tightened or externalized.

3 / 5

Actionability

Provides concrete executable commands (uv pip install lines, the PyBIDS database_path caching snippet) and points to 12 worked workflows; minor gaps because most executable guidance lives in referenced files rather than inline.

4 / 5

Workflow Clarity

'When to Use' gives clear triggers, the 12-area Core Workflows list is sequenced, and validation is repeatedly emphasized ('Validate early and often', validator after every conversion); detailed multi-step workflows are deferred to references, leaving minor gaps.

4 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references (core_workflows.md, bids_specification.md, metadata_fields.md, conversion_tools.md, beps.yml) — all real files — and a dedicated Reference Materials section for easy navigation.

5 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

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

An exemplary description: concrete capabilities, comprehensive natural trigger terms, an explicit 'Use when' clause, and a distinct niche with low conflict risk. Every dimension lands on the top anchor.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'organizing neuroscience and biomedical data', 'querying BIDS layouts', 'validating compliance', 'converting DICOM to BIDS', 'writing metadata sidecars', 'creating BIDS derivatives' — giving comprehensive coverage of multiple specific capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (the enumerated actions) and 'when' via the 'Use this skill when working with Brain Imaging Data Structure (BIDS) datasets' trigger clause, matching the top anchor.

5 / 5

Trigger Term Quality

Natural terms a user would say are comprehensive, including the BIDS acronym and modality synonyms (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, EMG, DICOM), plus concrete phrases like 'metadata sidecars' and 'BIDS derivatives'.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (the BIDS standard) with distinct, modality-specific triggers and minimal overlap risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
Reviewed

Table of Contents

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.