tooluniverse-regulatory-genomics

Transcription factor binding, cis-regulatory elements (cCREs), chromatin accessibility, and regulatory annotation using JASPAR (motifs), ENCODE (cCREs, ChIP-seq), RegulomeDB (regulatory variant scoring), UCSC — plus sequence-based deep-learning prediction of regulatory activity and non-coding variant effects (AlphaGenome, Enformer, Borzoi, ChromBPNet, Evo 2). Use for regulatory element annotation, TF-binding-site prediction, regulatory-region functional impact assessment, and predicting how a non-coding variant or a raw DNA sequence affects expression/chromatin/accessibility. Use this whenever a user asks what regulates a gene, whether a SNP hits a regulatory element, or to predict a non-coding variant's functional effect from sequence.

Quality

83%

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

78%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 reference for a tool-heavy genomics domain: concrete parameters, exact controlled vocabulary, fallbacks, and limitations are all present. The main structural weakness is that all lookup material lives inline in a single long file with no progressive disclosure, and validation/retry guidance is not woven into the workflow phases as explicit checkpoints.

Suggestions

Split the bulk lookup tables — the 'Tool Parameter Reference' table and the RegulomeDB rank-interpretation table — into a references/ file (e.g., references/tool_reference.md) and link to it from SKILL.md, keeping only the most-used tools inline.

Move retry/validation guidance out of Limitations and into the workflow phases as explicit checkpoints, e.g. after ENCODE searches: 'If @graph is empty, relax biosample/assay filters and retry' — building the existing fallback table into the step sequences.

Trim the 'Domain Reasoning' section and the opening paragraph (which restates the frontmatter description) down to the one non-obvious rule — 'a high-confidence regulatory element requires at least two independent evidence types' — to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense with tool-specific knowledge Claude could not know (exact tool names, parameter vocabularies, cCRE type definitions, RegulomeDB rank semantics), and nearly every token earns its place. It slips slightly with the 'Domain Reasoning' paragraph and the opening line, which re-state general regulatory-biology concepts and duplicate the frontmatter description.	4 / 5
Actionability	Concrete, copy-paste-ready tool calls with exact arguments appear throughout (e.g., 'jaspar_search_matrices(name="CTCF")', 'UCSC_get_encode_cCREs(chrom="chr8", start=37966000, end=37967000)', 'RegulomeDB_query_variant(rsid="rs4994")'), plus exact-value parameter tables, fallback strategies, and worked patterns like 'Pattern 2: Regulatory Variant Interpretation'. Not the level below (4) because the guidance covers the common cases completely, not just mostly.	5 / 5
Workflow Clarity	Phases 1–4 give a clear, ordered sequence (JASPAR motif → ENCODE experiments → cCRE annotation → RegulomeDB scoring) with a per-phase 'When asked about...' entry condition and a fallback table for failures. It is not a 5 because validation/retry guidance is implicit or parked in Limitations (e.g., the '@graph field may be empty... relax filters and retry' note) rather than being explicit checkpoints inside the workflow steps.	4 / 5
Progressive Disclosure	The file is well-sectioned and navigable, but no reference files exist (no references/, scripts/, or assets/ directories) and everything is inlined in one ~330-line SKILL.md — including the 14-row Tool Parameter Reference table and the 14-row RegulomeDB rank table, which is exactly the bulk API-reference content the rubric says belongs in a separate file. This matches anchor 3 ('some structure... content that should be separate is inline'), not 4, because there are no well-signaled external references at all.	3 / 5
	Total	16 / 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 description: concrete, third-person, comprehensive on both what it does and when to use it, with explicit user-facing trigger phrases. The only weaknesses are a few missing natural synonyms (enhancer, promoter, GWAS) and slight breadth-induced overlap with general variant-effect skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions with comprehensive coverage of the skill's surface: 'regulatory element annotation, TF-binding-site prediction, regulatory-region functional impact assessment, and predicting how a non-coding variant or a raw DNA sequence affects expression/chromatin/accessibility', each grounded in named tools (JASPAR, ENCODE, RegulomeDB, UCSC, AlphaGenome, Enformer, Borzoi, ChromBPNet, Evo 2). Not 4 because there are no meaningful gaps in the action inventory.	5 / 5
Completeness	Both halves are explicit: the 'what' enumerates the four annotation capabilities and the sequence-prediction capability with named tools and databases, and the 'when' gives two explicit trigger clauses ('Use for regulatory element annotation, TF-binding-site prediction...' and 'Use this whenever a user asks what regulates a gene, whether a SNP hits a regulatory element...'). This matches the anchor-5 example's what+when structure with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-phrase coverage: 'what regulates a gene', 'whether a SNP hits a regulatory element', 'predict a non-coding variant's functional effect from sequence', plus 'expression', 'chromatin accessibility', 'ChIP-seq'. It falls short of 5 because common user phrasings like 'enhancer', 'promoter', 'TF binding sites near a gene', or 'GWAS/fine-mapping' are absent.	4 / 5
Distinctiveness Conflict Risk	The regulatory-genomics niche is clear and triggers like 'SNP hits a regulatory element' or 'non-coding variant effect from sequence' are unlikely to fire the wrong skill. It is not 5 because the description spans both database annotation and general sequence-based variant-effect prediction (AlphaGenome, Evo 2), creating minor overlap risk with a generic variant-annotation or coding-variant skill.	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: plugins/tooluniverse/skills/tooluniverse-regulatory-genomics/SKILL.md
Commit: 164aaf1

Reviewed: 6 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.