alphagenome

Look up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

Quality

93%

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

86%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 strong, highly actionable body with executable code, a clear routing decision table, and well-structured one-level-deep references that all resolve to real bundle files. It is efficient but not maximally lean, and the full validation checklist/feedback loop lives in a reference rather than inline.

Suggestions

Pull the core reporting checklist and a one-line validate-fix-retry loop for batch VCF runs inline from interpretation.md so workflow_clarity can reach 5 without requiring a file hop.

Trim the 'Citing Scientific Agent Skills' boilerplate to the essential fetch-and-cite instruction to tighten conciseness.

Consider condensing the 'Reading the numbers' prose into a compact table (raw vs quantile vs Phred, with the artefact rule) to reduce length without losing the interpretation guidance.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence — no basic-concept explanations, and prose is domain-specific actionable guidance (coordinate contract, interpretation rules, blind spots). It is efficient rather than lean: the document is substantial and a few passages (e.g., the citing section) could be trimmed, fitting the score-4 anchor better than 5.	4 / 5
Actionability	Fully executable, copy-paste-ready bash commands and Python with real imports, function names, and parameters covering the common cases (avi lookup, scoring, tracks, portal links, Python API), matching the score-5 anchor.	5 / 5
Workflow Clarity	A clear 'When to use which' decision table plus sequenced Atlas and model workflows with explicit checkpoints (setup 'proves key + network in one call', REF-check before lookup, per-variant error cells, client retries). Validation is present so the batch-operation cap at 3 does not apply, but the full reporting checklist and validate-fix-retry loop are partly deferred to interpretation.md rather than inline.	4 / 5
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references (references/atlas.md, model-api.md, interpretation.md) and scripts, all of which exist in the bundle; content is appropriately split with easy navigation, matching the score-5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

An exemplary description: specific, comprehensive, with explicit what-and-when guidance and rich natural trigger terms covering synonyms. Third-person/imperative voice is used throughout with no first/second person, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage — 'Look up precomputed AlphaGenome Atlas effects', 'score variants or scan windows on demand', 'in silico mutagenesis, REF-versus-ALT track prediction', 'build Atlas website deep links' — matching the score-5 anchor exactly.	5 / 5
Completeness	Explicitly answers both what (lookup precomputed effects, score variants on demand, build deep links) and when ('Use when the user mentions...') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms users in this domain actually say — 'AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction' plus 'SNVs from a VCF, credible set, or region'; not merely technical jargon.	5 / 5
Distinctiveness Conflict Risk	A clear named-tool niche (AlphaGenome / DeepMind variant effect prediction) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/alphagenome/SKILL.md
Commit: 49c6e97

Reviewed: 3 days 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.