Tessl • The package manager for agent skills

SkillPublic

tooluniverse-gwas-finemapping

Identify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions. Computes posterior probabilities for causal variants, links variants to genes via L2G predictions, annotates functional consequences, and suggests validation strategies. Use when asked to fine-map GWAS loci, prioritize causal variants, identify credible sets, or link GWAS signals to causal genes.

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

63%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 well-structured and action-oriented with solid worked examples and a clear end-to-end workflow, but it is padded with conceptual explanations Claude already knows and is monolithic rather than progressively disclosing detail via bundle files.

Suggestions

Trim the Overview and Key Concepts sections to remove textbook definitions of GWAS, LD, credible sets, posterior probability, and L2G that Claude already knows; keep only the operational thresholds and method-selection guidance.

Move the Data Classes, Tools Used, and Fine-Mapping Methods Compared sections into reference files under references/ (e.g. reference.md, tools.md) and link to them from SKILL.md, leaving a lean overview with one-level-deep pointers.

Replace the placeholder 'from python_implementation import ...' with the real import path (or document it as the MCP tool entry point) so the code examples are genuinely copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body mixes genuinely operational material with notable conceptual teaching Claude already knows — the Overview re-explains GWAS and LD, Key Concepts defines credible sets/posterior probability/L2G, and the Methods Compared table explains SuSiE/FINEMAP/PAINTOR/CAVIAR — so it could be tightened considerably.	3 / 5
Actionability	Concrete code examples (prioritize_causal_variants, get_credible_sets_for_study, search_gwas_studies_for_disease) with documented data-class fields and tool listings give mostly executable guidance, though the 'from python_implementation import' placeholder keeps it just short of copy-paste ready.	4 / 5
Workflow Clarity	The 'Complete Fine-Mapping Analysis' section lays out a clear 5-step sequence (find studies → get loci → filter by gene → prioritize → summarize/validate), and as a read-only analysis skill it reasonably lacks hard validation checkpoints, leaving only minor gaps.	4 / 5
Progressive Disclosure	Section headers give reasonable structure, but with no references/scripts/assets bundle files present, the ~310-line SKILL.md inlines content (data-class API, tools reference, methods table, interpretation thresholds) that would benefit from being split into separate referenced files.	3 / 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, third-person description that clearly states both capabilities and trigger conditions with concrete, domain-appropriate language. The only minor gap is a few missing synonyms and slight overlap risk against sibling GWAS skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Identify and prioritize causal variants', 'Computes posterior probabilities', 'links variants to genes via L2G predictions', 'annotates functional consequences', and 'suggests validation strategies' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	It explicitly answers both 'what' (the first two sentences enumerating actions) and 'when' ('Use when asked to fine-map GWAS loci...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use when asked to fine-map GWAS loci, prioritize causal variants, identify credible sets, or link GWAS signals to causal genes' clause supplies natural phrasings a genomics user would say, though a few synonyms (e.g. 'posterior probability', 'colocalization') are absent.	4 / 5
Distinctiveness Conflict Risk	The fine-mapping/L2G niche is clearly demarcated with distinct triggers, but the existence of sibling skills (gwas-explorer, eqtl-colocalization, gene-prioritization) creates minor overlap risk on closely related queries.	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: wu-yc/LabClaw
Path: skills/bio/tooluniverse-gwas-finemapping/SKILL.md
Revision: df37802

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.

tooluniverse-gwas-finemapping

Table of Contents

Is this your skill?