CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

alphagenome-atlas-website-links

Constructs deep-links and URLs for the AlphaGenome Atlas website. Supports generating single-variant exploration links (1-based VCF-style coordinates), genomic locus views (1-based closed chr:start-end), candidate summary tables, and AlphaGenome reference vs. alternate predictions. Use when visualizing, exploring, charting, or linking genetic variants and genomic loci on the AlphaGenome Atlas, or when asked to inspect, view, or link predictions for a genomic variant. Don't use for computing raw AlphaGenome variant predictions directly without Atlas URLs (use alphagenome-single-variant-analysis or alphagenome-variant-impact-score).

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable, domain-rich reference with executable commands and useful guardrail callouts. Its main weaknesses are structural: inconsistent section labeling/numbering and heavy inline reference material that would benefit from being split into a separate file.

Suggestions

Fix the section structure: rename 'Prerequisites' to a usage/quick-start heading and correct the numbering (sections jump from an unnumbered section straight to '2. URL Query Parameters').

Move the full URL query-parameter reference and the pinned-track key schema into a references/ file, keeping SKILL.md as a lean overview with pointers.

Add a verification step to the workflow, e.g. generate with '--format url' and sanity-check the assembled query string before presenting links to the user.

DimensionReasoningScore

Conciseness

The body is dense with domain-specific facts Claude would not know (filter boolean logic, pinned-track key schema, latency gotchas) rather than padding, but a few passages over-explain rationale — e.g. the NMD/cryptic-junction justification in the splicing co-plotting callout — and could be trimmed.

4 / 5

Actionability

Commands are copy-paste ready ('uv run scripts/alphagenome_atlas_links.py variant "chr9:128225994:G>A" --biosample K562 ...'), CLI options are documented with types and defaults, and exact URL formats (including percent-encoded examples) cover the common cases.

5 / 5

Workflow Clarity

The motif recipe is a clear numbered sequence and mandatory callouts act as guardrails, but the 'Prerequisites' section is actually a usage quick-start, section numbering begins at '2' with no '1', and there is no step to verify generated links (e.g. --format url) — though operations are non-destructive so the validation cap does not apply.

4 / 5

Progressive Disclosure

The bundle script (scripts/alphagenome_atlas_links.py, which exists) is well-signaled and repeatedly cross-referenced, and sections are clearly headed; however ~250 lines of URL-parameter and pinned-track-key reference material are inlined in SKILL.md where a references/ file would keep the overview leaner.

4 / 5

Total

17

/

20

Passed

Description

92%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 well-crafted description in third-person voice with concrete capabilities, explicit trigger guidance, and clear boundaries against sibling skills. The only minor gap is that a few natural trigger synonyms are absent.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'single-variant exploration links (1-based VCF-style coordinates)', 'genomic locus views (1-based closed chr:start-end)', 'candidate summary tables', and 'reference vs. alternate predictions' — with format-level detail and no coverage gaps, matching the comprehensive anchor.

5 / 5

Completeness

It explicitly answers both 'what' (constructs deep-links, locus views, summary tables, ref vs. alt predictions) and 'when' ('Use when visualizing, exploring, charting...'), with concrete trigger phrases and even an explicit negative boundary.

5 / 5

Trigger Term Quality

Natural phrases like 'visualizing, exploring, charting, or linking genetic variants and genomic loci' and 'inspect, view, or link predictions' are strong triggers, but a few plausible user phrasings (e.g. 'share', 'browse', 'open in Atlas') are missing, placing it just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Atlas URL construction) and explicitly disambiguates against sibling skills: 'Don't use for computing raw AlphaGenome variant predictions directly without Atlas URLs (use alphagenome-single-variant-analysis or alphagenome-variant-impact-score)'.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

google-deepmind/science-skills

Path

skills/alphagenome_atlas_website_links/SKILL.md

Reviewed

Table of Contents

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.