CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-small-molecule-discovery

Small molecule identification, characterization, and procurement — PubChem, ChEMBL, BindingDB, ADMET-AI, SwissADME, eMolecules, Enamine. Covers compound name to structure to activity to ADMET properties to commercial sourcing. Use for chemical biology, lead identification, probe selection, and the full small-molecule discovery pipeline.

66

Quality

79%

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-small-molecule-discovery/SKILL.md

The canonical home for this skill is tooluniverse-small-molecule-discovery in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

Highly actionable and well-sequenced content with concrete tool-call examples and useful fallback chains, but it is over-long for a single file: it re-explains known chemistry concepts and carries two overlapping tool tables that could be consolidated or moved to a reference file.

Suggestions

Trim or remove the 'Domain Reasoning' section — Lipinski's Rule of 5 and its exceptions are concepts Claude already knows; retain only the skill-specific directive ('focus on target/route requirements, not rigid rules').

Merge the 'Key Tools' and 'Tool Parameter Reference' tables into a single reference table to eliminate redundant tool listings and reduce token cost.

Move the detailed tool parameter reference and Common Patterns flows into a separate file (e.g., references/tool_reference.md) and link from SKILL.md, keeping the body a lean overview that satisfies progressive disclosure for a skill this long.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete tool calls, but the 'Domain Reasoning' section re-explains Lipinski's Rule of 5 and drug-likeness exceptions Claude already knows, and the 'Key Tools' and 'Tool Parameter Reference' tables duplicate much of the same tool listing.

3 / 5

Actionability

Workflow phases and patterns give concrete, copy-paste-ready tool invocations with real example values (e.g., compound_name="imatinib" -> CID: 5291) and expected outputs covering the common cases comprehensively.

5 / 5

Workflow Clarity

Six clearly sequenced phases with an ID-resolution priority list and a Fallback Chains table providing error-recovery feedback loops, but inter-phase validation checkpoints are implicit rather than explicit.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, but the ~344-line body is a monolith with no bundle files or external references, and the large tool tables and detailed pattern flows are inlined rather than split into a reference file.

3 / 5

Total

15

/

20

Passed

Description

87%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, third-person description that clearly states capabilities, names the data sources, and provides an explicit 'Use for' trigger clause covering the full discovery pipeline. It is comprehensive and distinct, with only minor room to add a few more colloquial trigger synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions ('identification, characterization, and procurement') and maps the full pipeline ('compound name to structure to activity to ADMET properties to commercial sourcing'), with only minor abstraction in the verb phrasing keeping it just below a 5.

4 / 5

Completeness

Explicitly answers both 'what' (identification/characterization/procurement pipeline) and 'when' via a concrete 'Use for chemical biology, lead identification, probe selection...' trigger clause.

5 / 5

Trigger Term Quality

Strong natural domain terms ('chemical biology, lead identification, probe selection, ADMET properties, commercial sourcing, small-molecule discovery pipeline') match what users say, though a few common variants ('drug discovery', 'med chem') are absent.

4 / 5

Distinctiveness Conflict Risk

The named tool chain (PubChem, ChEMBL, BindingDB, ADMET-AI, SwissADME, eMolecules, Enamine) carves a clear small-molecule-discovery niche with minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.