tooluniverse-gwas-finemapping

Statistical fine-mapping of GWAS loci using credible sets (SuSiE, FINEMAP) and locus-to-gene scoring (Open Targets L2G). Identifies likely causal variants and target genes — distinct from positional 'nearest gene' which is often wrong. Use for prioritizing causal variants at GWAS hits, comparing fine-mapping methods, and converting lead SNPs to target genes.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-gwas-finemapping/SKILL.md

Quality

Content

60%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.

A well-structured, domain-specific reasoning guide with strong workflow sequencing and useful decision thresholds, weakened by concept re-explanation and the absence of any executable code or example tool invocations despite a compute mandate.

Suggestions

Trim the Overview and Key Concepts sections to assume Claude's knowledge of LD, credible sets, and posterior probabilities — keep only the skill-specific thresholds and reasoning rules.

Add at least one executable example: a Python snippet showing a ToolUniverse tool call followed by pandas/scipy analysis of the returned credible-set table, to honor the 'COMPUTE, DON'T DESCRIBE' header.

Show one or two tool invocations with concrete arguments and expected output fields (e.g. OpenTargets_get_variant_credible_sets with a variant id) so Claude knows how to call and parse them.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the Overview and Key Concepts sections re-explain LD, credible sets, posterior probability, and L2G — concepts Claude already knows — adding padding around the genuinely useful thresholds and reasoning rules.	3 / 5
Actionability	Concrete tool names, query→tool mappings, and numeric decision thresholds (PP<0.5, L2G>0.7) are given, but despite the 'COMPUTE, DON'T DESCRIBE' mandate there is no executable Python example and tool calls are never shown with arguments or sample output.	3 / 5
Workflow Clarity	A clear five-step reasoning framework with explicit conditional checkpoints ('If the posterior probability is < 0.5... examine other variants') and a prioritization tiebreaker checklist; this is interpretive analysis rather than a destructive/batch operation so the validation cap does not apply.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Overview, Reasoning Framework, Tools, Interpretation, FAQ, Limitations) with no nested references and no bundle files; the inlined FAQ and academic References could arguably be split out but inline placement is reasonable.	4 / 5
	Total	14 / 20 Passed

Description

88%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, specific description that clearly states capabilities and use cases in third person with explicit trigger guidance. Minor room to add a few more natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Statistical fine-mapping of GWAS loci using credible sets', 'locus-to-gene scoring (Open Targets L2G)', 'prioritizing causal variants', 'comparing fine-mapping methods', 'converting lead SNPs to target genes' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Statistical fine-mapping... Identifies likely causal variants and target genes') and when ('Use for prioritizing causal variants at GWAS hits, comparing fine-mapping methods, and converting lead SNPs to target genes') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural domain terms users would say — 'causal variants', 'GWAS hits', 'lead SNPs', 'fine-mapping methods', 'target genes' — though a few common variants like 'association signals' or 'summary statistics' are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (credible-set fine-mapping + L2G) and explicitly contrasts the common wrong default ('distinct from positional nearest gene which is often wrong'), with only minor overlap risk against related colocalization/gene-prioritization skills.	4 / 5
	Total	18 / 20 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-gwas-finemapping/SKILL.md
Commit: 1b02920

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.