tooluniverse-population-genetics

Population genetics analysis — allele frequencies (gnomAD, 1000 Genomes), Hardy-Weinberg equilibrium testing, Fst between populations, GWAS associations, evolutionary constraint scores. Use for cross-population variant comparison, ancestry-aware allele frequency lookups, and population-level evolutionary analysis.

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 dense, highly actionable skill with exact tool parameters, CLI commands, and specialized formulas, but it is bloated with textbook genetics and test-taking advice Claude already knows and is organized as a monolithic inline document with redundant trap sections. Splitting reference material into separate files and pruning known-concept explanations would lift both conciseness and progressive disclosure.

Suggestions

Move the formula reference (Theoretical Reasoning) and the trap collections (Common Genetics Reasoning Traps, Advanced Genetics Traps v2) into separate reference files linked from SKILL.md to improve progressive disclosure and shrink the main file.

Prune textbook explanations Claude already has — Punnett-square mechanics, HWE genotype-frequency basics, broad-sense vs narrow-sense heritability definitions — and de-duplicate content repeated across sections (PGS-vs-heritability, LD blocks, neofunctionalization/subfunctionalization).

Add explicit validation/error-recovery checkpoints to the core tool Workflow Patterns (e.g., verify VEP/ClinVar response shape, retry-once on gnomad timeout, confirm ratios sum to 1.0) so the primary workflows match the rigor of the Mendelian framework.

Dimension	Reasoning	Score
Conciseness	The 355-line body mixes genuinely specialized content (tool gotchas, delta-q formulas, the broken gwas_search_snps note) with substantial textbook explanation Claude already knows (Punnett-square basics, HWE genotype frequencies, heritability definitions) and redundant sections — PGS-vs-heritability appears at both line 144 and lines 309-310, LD blocks at lines 122-126/291-295/322-323, neofunctionalization at lines 264 and 297-303 — so it is mostly useful but could be tightened considerably; not a 3 because of the padding and repetition.	2 / 3
Actionability	Highly actionable: a tool table with exact required parameters, concrete workflow chains, and copy-paste CLI invocations such as 'popgen_calculator.py --type hwe --AA N1 --Aa N2 --aa N3' plus precise gotchas (variant_id 'CHR-POS-REF-ALT' format, gwas_search_associations takes trait names only).	3 / 3
Workflow Clarity	Sequences exist (numbered Mendelian steps 1-6 'IN ORDER', the compute-then-match strategy, Step 5 'Verify ratios sum to 1.0'), but the primary tool 'Workflow Patterns' are flat arrow-chains with no validation checkpoints or error-recovery feedback loops, leaving validation gaps in the core workflows.	2 / 3
Progressive Disclosure	The one bundle file (scripts/popgen_calculator.py) is real and clearly signaled one level deep, but the body is a monolithic wall of text where large swaths that could be separate references — theoretical formula tables, 'Common Genetics Reasoning Traps', 'Advanced Genetics Traps v2' — are inlined into SKILL.md rather than split out.	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.

A strong, third-person description that names concrete capabilities and data sources and pairs them with an explicit 'Use for' trigger clause, covering both what and when. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'allele frequencies (gnomAD, 1000 Genomes), Hardy-Weinberg equilibrium testing, Fst between populations, GWAS associations, evolutionary constraint scores' — each naming a specific operation rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the listed analyses) and when via the 'Use for cross-population variant comparison, ancestry-aware allele frequency lookups, and population-level evolutionary analysis' clause — a present 'Use when...' trigger.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'allele frequencies', 'gnomAD', '1000 Genomes', 'GWAS', 'Hardy-Weinberg', 'Fst', 'evolutionary constraint', 'cross-population variant comparison', 'ancestry-aware allele frequency lookups' — terms a population-genetics user would actually say.	3 / 3
Distinctiveness Conflict Risk	The population-genetics niche with named data sources (gnomAD, 1000 Genomes, GWAS) and specific analyses (Fst, HWE, constraint) is a clear, distinct trigger set unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-population-genetics/SKILL.md
Commit: 089eb8e

Reviewed: about 9 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.