tooluniverse-biomedical-fact-lookup

Answer biomedical FACTUAL / recall / multiple-choice questions by querying ToolUniverse database tools instead of answering from memory. Triggers on any 'which gene/drug/variant/disease/pathway/miRNA/TF...' lookup, any question phrased 'according to <database>' (DisGeNet, OMIM, MSigDB, miRDB, GTRD, MGI, Ensembl, ClinVar, ChEMBL, OpenTargets, Reactome, GtoPdb, UniProt...), and multiple-choice biology/medicine knowledge questions where one option must be verified against an authoritative source. NOT for analyzing user-supplied data files (CSV/VCF/h5ad → use the data-analysis router) and NOT for open-ended literature synthesis. Use whenever a single correct answer exists in a public biomedical database and could be looked up rather than guessed.

Quality

94%

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

88%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 body is highly actionable and tightly focused on domain-specific knowledge Claude would not reliably have, with well-sequenced workflows and explicit validation checkpoints. Minor gains are available in conciseness (trimming justificatory prose) and progressive disclosure (offloading some reference material into bundle files).

Suggestions

Tighten justificatory sentences like 'Mental arithmetic on these is the #1 avoidable error: the model reliably mis-counts' to bare imperatives to lift conciseness.

Consider moving the three code snippets or the full routing table into files under references/ so SKILL.md reads as an overview pointing one level deep, improving progressive_disclosure.

The Limitations section's key-gated-source note could be condensed; the fallback path is already implied by the routing table.

Dimension	Reasoning	Score
Conciseness	Dense, skill-specific procedural knowledge with no generic concept padding, but a few justificatory sentences (e.g. 'the model reliably mis-counts or mis-multiplies') could be trimmed; mostly efficient with minor over-explanation.	4 / 5
Actionability	Fully executable guidance: a pattern→tool→params routing table, exact set-name conventions, and three complete runnable Python snippets with worked examples in comments — copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	Multi-step procedures (MCQ procedure, DisGeNet differential recipe, computational procedures) are clearly sequenced with explicit validation/feedback checkpoints such as 'Exactly one option should be supported', re-run-on-error guidance, and final-answer-discipline error recovery.	5 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with no deep nested references, but a routing table and several full code blocks that could plausibly live in separate reference files are inlined; no bundle files exist, so structure is inline-only.	4 / 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.

The description is highly specific, trigger-rich, and clearly distinguishes this skill's niche via explicit inclusion and exclusion criteria. It answers both what the skill does and when to use it with concrete, natural trigger phrases.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions (querying ToolUniverse database tools for factual biomedical lookup), plus explicit exclusions (not for user-supplied data files or literature synthesis) — comprehensive coverage matching the top anchor.	5 / 5
Completeness	Clearly answers both 'what' (query ToolUniverse database tools instead of answering from memory) and 'when' via explicit 'Triggers on...' and 'Use whenever a single correct answer exists...' clauses.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including 'which gene/drug/variant/disease/pathway/miRNA/TF...' lookups, 'according to <database>' phrasing, and a long synonym list of specific database names users would actually cite.	5 / 5
Distinctiveness Conflict Risk	Clear niche (database-grounded factual lookup) with explicit 'NOT for...' carve-outs that distinguish it from the data-analysis router and open-ended literature synthesis, minimizing conflict risk.	5 / 5
	Total	20 / 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: plugin/skills/tooluniverse-biomedical-fact-lookup/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.