Tessl • The package manager for agent skills

SkillPublic

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

Quality

81%

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%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.

Highly actionable content with executable code throughout and a clear core workflow, but it is over-long for a SKILL.md: duplicated SQL guidance, inlined reference material, a missing referenced bundle file (clinical_data_guide.md), and no validation checkpoint in batch-download workflows.

Suggestions

Add an explicit validation step to batch-download workflows (e.g., after each batch, verify expected file count or pydicom-readability before downloading the next batch) to satisfy the batch-operation validation requirement.

Remove or create references/clinical_data_guide.md — it is listed in the Reference Documentation section but does not exist in the bundle.

Consolidate the repeated 'consult indices_overview' instructions and move the join-column table and 'Common SQL Query Patterns' section into a reference file (e.g., a new sql_patterns or indices reference), keeping SKILL.md to the core workflow and key examples.

Dimension	Reasoning	Score
Conciseness	The ~1180-line body is dense with domain specifics but includes notable redundancy: the 'consult indices_overview' instruction is repeated in at least four sections, join/seg_index SQL examples appear twice, and 'Common SQL Query Patterns' repeats material from Core Capabilities. Some reference-table material (join columns, key columns, SQL pattern library) belongs in bundle files.	3 / 5
Actionability	Nearly every section provides copy-paste-ready executable Python/Bash (client.sql_query, download_from_selection, idc download, pydicom validation), plus concrete parameter tables, real collection IDs, and actual viewer-URL workflows.	5 / 5
Workflow Clarity	The core query → download → visualize sequence is stated up front and a Troubleshooting section covers failure recovery, but the batch-download loops (§6 and Use Case 1) contain no inline validation checkpoint (e.g., verifying downloaded file counts/integrity per batch before proceeding). Per the rubric, batch operations without validation steps cap workflow clarity at 3.	3 / 5
Progressive Disclosure	Four well-signaled, one-level-deep reference files exist (bigquery, cli, cloud_storage, dicomweb guides), but the body cites 'clinical_data_guide.md' which is not present in references/ — a broken reference. Additionally, large schema/join-column/SQL-pattern reference material is inlined in SKILL.md rather than split into bundle files.	3 / 5
	Total	14 / 20 Passed

Description

92%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.

A strong description: concrete actions, explicit 'Use for' trigger guidance, third-person voice, and a distinct niche. Only minor gap is omission of 'DICOM' and other common synonyms users would naturally say.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Query and download public cancer imaging data', 'Query by metadata, visualize in browser, check licenses' — covering the tool's main capabilities comprehensively with no vague filler.	5 / 5
Completeness	Explicitly answers both: what ('Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index') and when ('Use for accessing large-scale radiology... and pathology datasets for AI training or research'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('cancer imaging data', 'radiology (CT, MR, PET)', 'pathology datasets', 'AI training or research'), but misses common variations users would say such as 'DICOM', 'medical images', or 'Imaging Data Commons' spelled out beyond the NCI acronym.	4 / 5
Distinctiveness Conflict Risk	A clear niche — public cancer imaging data from NCI IDC via idc-index — with unique trigger terms; minimal overlap with generic data or file skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1186 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/imaging-data-commons/SKILL.md
Revision: 6a85742

Reviewed: 22 days ago

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.

imaging-data-commons

Table of Contents

Is this your skill?