tooluniverse-natural-product-dereplication

Dereplicate a putative natural product and assign its chemical taxonomy. Use to answer "is [compound] a known natural product", "what microbe/organism produces [compound]", "what chemical class is [compound]", "dereplicate this metabolite (by formula/exact mass/InChIKey/SMILES)", or "classify this molecule into ChemOnt". Searches NPAtlas for known microbial natural products (producing organism + literature reference), assigns the ChemOnt kingdom→superclass→class→subclass hierarchy via ClassyFire, resolves systematic IUPAC names to structure via OPSIN, and cross-references identity in PubChem. NOT for general drug/compound identity or ADMET (use tooluniverse-chemical-compound-retrieval / tooluniverse-small-molecule-discovery) and NOT for metabolomics pathway/enrichment analysis (use tooluniverse-metabolomics skills).

Quality

94%

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

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.

A strong, highly actionable body with executable code, real worked examples, explicit validation checkpoints, and a checklist. The main weakness is redundancy between the Interpretation Guidance and Limitations sections, and a long single-file layout that could offload some detail to reference files.

Suggestions

Consolidate the overlapping guidance between 'Interpretation Guidance' and 'Limitations' (formula/exact-mass candidates, classified:false, parsed:false, microbial-only scope) into a single section to remove duplicated tokens.

Move the two worked examples and/or the per-phase code into a one-level-deep reference file (e.g. references/examples.md) referenced from the main workflow, leaving SKILL.md as a tighter overview.

Trim the Limitations restatements that simply repeat the interpretation bullets, keeping only the reporting-relevant framing.

Dimension	Reasoning	Score
Conciseness	Efficient and free of generic padding (no 'what is a natural product' filler), but the Interpretation Guidance and Limitations sections substantially overlap — formula/exact-mass candidates, classified:false, parsed:false, and microbial-only scope are each restated — and could be consolidated. Not a 5 because those redundant tokens do not all earn their place.	4 / 5
Actionability	Provides copy-paste-ready Python for every phase (OPSIN/PubChem InChIKey resolution, NPAtlas search + get_compound, ClassyFire classify), a tool table with exact inputs/returns, and two fully-worked examples with real NPAIDs/InChIKeys/DOIs covering the common cases.	5 / 5
Workflow Clarity	Phases 0–5 are explicitly sequenced with validation checkpoints (parsed:false ⇒ fall through to PubChem; classified:false ⇒ report unavailable; NPAtlas-vs-PubChem formula disagreement as a red-flag check), feedback loops for routing failures, and a terminal completeness checklist — matching the top anchor.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and cohesive single-file structure, but no external references are used and the file exceeds 50 lines, so the simple-skill exception does not apply; the worked examples and detailed interpretation logic are candidates for one-level-deep reference files. Good structure with minor organization gaps rather than a fully split overview-plus-refs layout.	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.

An exemplar description: concrete multi-tool actions, natural trigger phrases, explicit what-and-when guidance, and hard boundary routing to sibling skills. Voice is correctly third person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Searches NPAtlas for known microbial natural products', 'assigns the ChemOnt kingdom→superclass→class→subclass hierarchy via ClassyFire', 'resolves systematic IUPAC names to structure via OPSIN', 'cross-references identity in PubChem' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what ('Dereplicate a putative natural product and assign its chemical taxonomy' plus per-tool actions) and when ('Use to answer ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Embeds natural user phrasings — 'is [compound] a known natural product', 'what microbe/organism produces [compound]', 'dereplicate this metabolite (by formula/exact mass/InChIKey/SMILES)', 'classify this molecule into ChemOnt' — giving comprehensive coverage of how a user would actually request this.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (microbial NP dereplication + ChemOnt) and adds explicit 'NOT for ... (use tooluniverse-chemical-compound-retrieval / tooluniverse-small-molecule-discovery)' and 'NOT for metabolomics pathway/enrichment analysis' routing, 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-natural-product-dereplication/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.