tooluniverse-target-research

Comprehensive drug-target intelligence — tissue expression (GTEx, HPA), pathways, protein interactions (STRING), variant landscape (ClinVar, gnomAD), druggability (DGIdb, ChEMBL approved drugs). 9 parallel research paths with citations. Use for full target profile reports, target characterization for drug discovery, and 'tell me about target X' queries.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

70%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 well-sequenced workflow with strong validation and feedback loops, undermined by missing bundle files that the body repeatedly points to for essential implementation detail, plus some over-explanation of domain background Claude already knows.

Suggestions

Include the referenced bundle files (IMPLEMENTATION.md, EVIDENCE_GRADING.md, REPORT_FORMAT.md, REFERENCE.md, EXAMPLES.md) in the bundle, or inline the critical implementation code currently deferred to them so the skill is self-contained.

Trim the Target Evaluation Reasoning Framework prose to decision criteria and thresholds only; remove general background on what genetic evidence or druggability means, which Claude already knows.

Move the 225+-tool REFERENCE.md catalog fully out of the main body (it is already linked) and keep only the per-path tool short-lists inline to reduce token load.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-organized, but the Target Evaluation Reasoning Framework section explains domain concepts Claude already knows (e.g. "Genetic evidence is the strongest predictor of drug success", detailed druggability/safety primer prose) that could be trimmed; the body runs ~300 lines with several padded explanatory passages.	3 / 5
Actionability	Provides concrete tool names per path, explicit parameter corrections, and a worked `get_tool_info` call, but most path sections defer the actual executable code to IMPLEMENTATION.md rather than showing it inline, leaving minor gaps.	4 / 5
Workflow Clarity	Clear 9-path sequence with explicit ordering (identifier resolution first, PATH 0 always first), validation checkpoints (Phase 0 tool verification, MANDATORY report-first, retry/fallback chains, completeness audit) and feedback loops for error recovery.	5 / 5
Progressive Disclosure	Structure is good with five one-level-deep reference links, but the referenced bundle files (IMPLEMENTATION.md, EVIDENCE_GRADING.md, REPORT_FORMAT.md, REFERENCE.md, EXAMPLES.md) do not exist in the bundle — only SKILL.md is present — so the navigation points to missing material and core implementation guidance is absent from the skill.	3 / 5
	Total	15 / 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 strong, specific description that pairs concrete data sources with explicit use-when triggers and stays in third-person voice. Minor headroom only in broadening trigger-term synonyms for casual phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities with named sources — "tissue expression (GTEx, HPA)", "protein interactions (STRING)", "variant landscape (ClinVar, gnomAD)", "druggability (DGIdb, ChEMBL approved drugs)" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (the intelligence sources and 9 research paths with citations) and 'when' ("Use for full target profile reports, target characterization..., and 'tell me about target X' queries") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like "'tell me about target X' queries", "full target profile reports", and "target characterization for drug discovery", but misses common synonyms a casual user might say (e.g. "drug target", "protein summary") and file-type style triggers.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (comprehensive drug-target intelligence across specific databases) with distinct triggers unlikely to fire for simple protein lookups or disease-only queries, minimizing conflict risk.	5 / 5
	Total	19 / 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
relative_links	Relative link issues: 8 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-target-research/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.