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

65%

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

61%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.

The content is highly actionable with executable, dataset-specific code and clear per-section structure. Its weaknesses are duplicated/inflated code, missing validation checkpoints in batch download workflows, and orphaned bundle scripts that are never surfaced via progressive disclosure.

Suggestions

Reference the existing bundle scripts from the relevant sections (e.g., 'See scripts/download_cosmic.py for the full download workflow') instead of inlining all code.

Add validation checkpoints to the download workflows (e.g., verify file integrity, check expected row counts, handle partial downloads) to lift workflow_clarity above 3.

De-duplicate parse_gmt (it appears in both Quick Start and section 6) and trim debug print() statements to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code with brief comments and no concept padding, but the ~560-line body duplicates parse_gmt (defined in both Quick Start and section 6) and is inflated by debug print() statements that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready Python functions with real download URLs, file formats, and exact column names across all eight datasets, fully covering common cases.	5 / 5
Workflow Clarity	A Typical Workflows section sequences concrete examples, but large-data batch downloads (COSMIC ~30GB, GTEx ~2GB) have no validation checkpoints or error-recovery feedback loops, which the rubric caps at 3 for batch operations.	3 / 5
Progressive Disclosure	The body is a monolithic ~560-line wall with all code inlined; the provided bundle scripts (scripts/build_ppi_network.py, download_cosmic.py, parse_msigdb.py) exist but are never referenced or linked from the body.	2 / 5
	Total	13 / 20 Passed

Description

70%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.

The description is specific and distinctive, naming eight concrete data sources and explicitly scoping itself against per-database skills. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when downloading or parsing curated biological datasets across multiple databases') so Claude knows when to invoke this skill.

Replace the generic verb 'accessing' with concrete actions like 'download, parse, and integrate' to lift specificity.

Include file extensions or format names (e.g., GMT, TSV, OBO) as trigger terms for better keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists eight concrete named data sources (COSMIC, GTEx, GWAS catalog, GeneBass, BioGRID, MSigDB, DisGeNET, GO) but the action verb is the generic 'accessing' rather than specific verbs like parse, load, or query.	4 / 5
Completeness	Clearly states the 'what' (accessing curated biological datasets) but lacks an explicit 'Use when...' trigger clause for invoking this skill; the only 'when' guidance is a redirect to other skills.	3 / 5
Trigger Term Quality	Natural domain keywords a computational biology user would say ('COSMIC cancer data', 'GTEx expression', 'GWAS catalog', 'MSigDB gene sets') are well covered; missing file extensions and a few synonyms.	4 / 5
Distinctiveness Conflict Risk	Named databases give it a clear niche and it explicitly disambiguates from related per-database skills ('For specific database APIs use individual database skills'), minimizing conflict risk.	5 / 5
	Total	16 / 20 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: 3a6c3a9

Reviewed: 1 day 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.