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.

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

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.

A highly actionable, well-sequenced workflow skill with concrete executable tool calls and useful fallback chains. Its main weaknesses are redundancy (two overlapping tool tables) and the absence of progressive disclosure — all reference material is inlined rather than split into bundle files.

Suggestions

Consolidate the two overlapping tool tables ("Key Tools" and "Tool Parameter Reference") into a single table to remove redundancy and tighten conciseness.

Move the bulk tool-reference material into a references/REFERENCE.md file and keep SKILL.md as a concise overview with one-level-deep pointers.

Add explicit validation checkpoints in the workflow (e.g. verify canonical SMILES was retrieved before calling ADMET tools) to make the sequence's gating explicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tool calls, but the two overlapping tool tables ("Key Tools" and "Tool Parameter Reference") and restated principles ("LOOK UP DON'T GUESS" vs "KEY PRINCIPLES") duplicate content that could be consolidated.	3 / 5
Actionability	Provides fully executable, copy-paste-ready tool calls with real parameters throughout (e.g. PubChem_get_CID_by_compound_name(compound_name="imatinib") and ChEMBL_search_activities with pchembl_value__gte=6) plus complete end-to-end patterns covering common cases.	5 / 5
Workflow Clarity	A clear six-phase sequence with an ID-resolution priority and a fallback-chains table; as a read-only retrieval skill no destructive-cap applies, but explicit validation checkpoints (e.g. confirm SMILES was obtained before proceeding) are mostly implicit rather than stated.	4 / 5
Progressive Disclosure	No bundle files exist and everything is inlined into one ~350-line SKILL.md; section headers provide structure, but the long tool-reference tables are reference material that could live in a separate REFERENCE.md.	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 concretely covers the small-molecule discovery pipeline and names its data sources while giving explicit usage guidance. The only gap is a few additional natural trigger synonyms that users might say.

Suggestions

Add a few more natural trigger phrases users would actually say, such as "find compounds", "check drug-likeness", or "source/buy compounds", to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions spanning the full pipeline — "identification, characterization, and procurement" and "compound name to structure to activity to ADMET properties to commercial sourcing" — with named data sources, giving comprehensive coverage.	5 / 5
Completeness	Explicitly states both what it does (identify, characterize, procure across the named tools) and when to use it (chemical biology, lead identification, probe selection, discovery pipeline) with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use for chemical biology, lead identification, probe selection, and the full small-molecule discovery pipeline" provides good natural keyword coverage, but a few common user phrases (e.g. "find compounds", "drug-likeness", "buy/source compounds") are missing.	4 / 5
Distinctiveness Conflict Risk	A clearly scoped niche (small-molecule discovery via specific chemistry databases) with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	19 / 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-small-molecule-discovery/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.