ucsc-conservation-and-tfbs

Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).

Quality

86%

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

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with copy-paste executable commands and well-organized, properly progressive structure that points to real bundle scripts. It loses points for some redundant concept/motivation explanation and for lacking explicit output-validation feedback loops in its workflows.

Suggestions

Trim the conceptual explanations of phastCons/phyloP and the pathogenicity motivation in the opening paragraphs; assume Claude's domain knowledge and keep only the non-obvious track/collection reference tables.

Add an explicit validation checkpoint for script output (e.g., check the JSON for an error/empty field and retry with list_tracks.py if a track name fails), giving a clear validate-fix-retry loop.

Reference references/citation.bib from the body (e.g., a 'Citation' note) so the bundled reference file is discoverable and not orphaned.

Dimension	Reasoning	Score
Conciseness	Quotes 'It retrieves scores from the PHAST package — specifically phastCons ... and phyloP ... calculated from multiple alignments' and 'a strong signal for pathogenicity' explain concepts and motivations Claude largely already knows, though the collection/track tables are genuinely non-obvious reference data, fitting the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Quotes fully executable commands such as 'uv run scripts/get_conservation.py --coordinates ... --output /tmp/cons_output.json' plus '--collection mammal', '--analyze', and '--tf-filter TP53' with real flags and concrete arguments, making examples copy-paste ready.	3 / 3
Workflow Clarity	Quotes 'ALWAYS execute the provided helper scripts' and 'Always pass --output' show a present sequence, but there are no explicit validate-then-fix-then-retry checkpoints; validation of parsed output is left implicit, fitting the 'steps listed but validation gaps' anchor.	2 / 3
Progressive Disclosure	The body is organized into clear sections (Prerequisites, Core Rules, Utility Scripts, per-use-case subsections, Anti-Patterns) with one-level-deep, clearly signaled references to the real scripts/ files (get_conservation.py, get_tfbs.py, list_tracks.py), matching the well-signaled reference anchor.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concise, and explicitly states both what it does and when to use it, with concrete capabilities (phyloP/phastCons, TFBS) and natural trigger terms including project names. It is among the strongest examples and requires no changes.

Dimension	Reasoning	Score
Specificity	Quotes 'Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS)' lists multiple concrete actions with specific data types, matching the highest anchor; not below because it names domain and actions comprehensively.	3 / 3
Completeness	Quotes 'Fetch ... scores ... from the UCSC Genome Browser' (what) and 'Use when analyzing whether genomic variants or regions are evolutionarily conserved...' (explicit when trigger), clearly answering both what and when.	3 / 3
Trigger Term Quality	Quotes 'evolutionarily conserved, functionally important, or bounded by TF regulators' plus 'genomic variants or regions' and project names 'ENCODE, JASPAR, ReMap' give good coverage of natural terms a genomics user would say, matching the highest anchor.	3 / 3
Distinctiveness Conflict Risk	Quotes 'UCSC Genome Browser', 'phyloP, phastCons', 'TFBS', and 'ENCODE, JASPAR, ReMap' carve a clear niche that is unlikely to trigger for unrelated skills, matching the highest anchor.	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: google-deepmind/science-skills
Path: skills/ucsc_conservation_and_tfbs/SKILL.md
Commit: 0b42509

Reviewed: 7 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.