CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-target-research/SKILL.md

The canonical home for this skill is tooluniverse-target-research in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

62%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 research orchestration skill with strong workflow checkpoints and concrete tool-level guidance, but its actionability and progressive disclosure are undermined because all five referenced bundle files (IMPLEMENTATION.md, EVIDENCE_GRADING.md, REPORT_FORMAT.md, REFERENCE.md, EXAMPLES.md) are missing, and some reasoning prose could be trimmed.

Suggestions

Add the referenced bundle files (IMPLEMENTATION.md, EVIDENCE_GRADING.md, REPORT_FORMAT.md, REFERENCE.md, EXAMPLES.md) to the skill bundle — currently every 'see [FILE].md' link is broken.

Consolidate the 'Target Evaluation Reasoning Framework' prose with the later 'Synthesis: Target Assessment Framework' section; the four-question narrative overlaps the scoring dimensions and could be shortened.

Inline at least one full executable code example per PATH in SKILL.md (or ensure IMPLEMENTATION.md exists) so guidance is copy-paste ready rather than deferred to a missing file.

DimensionReasoningScore

Conciseness

Largely assumes Claude's competence (no explaining of what GPCR/ClinVar are) and tool lists are dense, but the 'Target Evaluation Reasoning Framework' and synthesis prose are long and partially redundant with the PATH sections, so it could be tightened.

3 / 5

Actionability

Names concrete tools with parameters and explicit fallback chains ('ChEMBL_get_target_activities fails → GtoPdb_search_ligands → OpenTargets drugs'), but most executable code is deferred to [IMPLEMENTATION.md] which is referenced and does not exist in the bundle, leaving a real gap.

3 / 5

Workflow Clarity

Clear sequence (identifier resolution → PATH 0 → PATHs 1-8 → completeness audit → synthesis) with explicit validation checkpoints: 'BEFORE calling ANY tool', 'Completeness Audit (REQUIRED before finalizing)', and 'NEVER silently skip failed tools'.

5 / 5

Progressive Disclosure

The reference table cleanly signals one-level-deep references to IMPLEMENTATION.md, EVIDENCE_GRADING.md, REPORT_FORMAT.md, REFERENCE.md, and EXAMPLES.md, but none of these files exist in the bundle, so the well-signaled navigation resolves to nothing.

3 / 5

Total

14

/

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 names concrete capabilities with real databases and provides explicit 'when to use' triggers including a natural user phrasing. Minor room to add a few more trigger synonyms, but it cleanly answers both what and when.

DimensionReasoningScore

Specificity

Enumerates multiple concrete capabilities with specific databases — 'tissue expression (GTEx, HPA)', 'protein interactions (STRING)', 'variant landscape (ClinVar, gnomAD)', 'druggability (DGIdb, ChEMBL approved drugs)' — giving comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what (drug-target intelligence across 9 research paths with named sources) and when ('Use for full target profile reports, target characterization for drug discovery, and tell me about target X queries'), matching the highest anchor.

5 / 5

Trigger Term Quality

Includes natural user phrasings like 'tell me about target X' and 'target characterization for drug discovery', but a few common synonyms (e.g. 'drug target', 'what do we know about') are absent, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clearly delineated drug-target-intelligence niche with specific database triggers and a 'tell me about target X' phrasing that is unlikely to fire for unrelated skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
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.