curated-bio-datasets

Guide to accessing curated biological datasets for computational biology. COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology. For specific database APIs use individual database skills (cosmic-database, gwas-database, etc.).

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/curated-bio-datasets/SKILL.md

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 thorough, highly actionable reference with real endpoints and copy-paste code, but it is verbose and monolithic: workflows lack validation checkpoints and the existing scripts/ bundle files are never linked from the body.

Suggestions

Move the long per-dataset code blocks into scripts/ (e.g. download_cosmic.py, parse_msigdb.py, build_ppi_network.py) and reference them from the body so SKILL.md stays a lean overview.

Add explicit validation checkpoints to the workflows (e.g. verify downloaded file size/row count before parsing; assert expected columns exist).

De-duplicate parse_gmt and strip the per-function print() debugging to reduce token load.

Dimension	Reasoning	Score
Conciseness	The ~560-line body is mostly efficient but padded with print-debugging in nearly every example and a duplicated parse_gmt function (Quick Start vs. section 6), so it could be tightened to earn its tokens.	2 / 3
Actionability	Code is concrete and copy-paste ready with real endpoints (e.g. "https://gtexportal.org/api/v2", QuickGO URL), actual column names, and documented download URLs, giving specific executable guidance throughout.	3 / 3
Workflow Clarity	Three "Typical Workflows" give a sequence, but none include validation checkpoints, and batch/large-data operations (30GB COSMIC, network builds) lack explicit verify-then-proceed loops, capping this at 2.	2 / 3
Progressive Disclosure	Section structure is clear, but all code is inline (monolithic) while three scripts/ bundle files exist and are never referenced or signaled from the body, so content that should be separate stays inline and the bundle is orphaned.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, well-scoped description that names concrete datasets and routes API-specific work to sibling skills. Its main gap is the absence of an explicit "Use when..." trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when accessing curated biological datasets like COSMIC, GTEx, GWAS Catalog, or MSigDB for computational biology analysis."

Lead with the core action verbs (download, parse, query) before the dataset list to sharpen the "what" statement.

Dimension	Reasoning	Score
Specificity	It enumerates concrete capabilities across eight named resources ("COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology"), listing multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Terms a computational-biology user would naturally say are well covered ("cancer data", "GTEx expression", "GWAS catalog", "gene sets", "disease-gene associations", "GO ontology"), matching the domain's natural vocabulary.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche and explicitly routes overlapping work elsewhere ("For specific database APIs use individual database skills (cosmic-database, gwas-database, etc.)"), making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (570 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/curated-bio-datasets/SKILL.md
Commit: 52845c3

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.