CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-chemical-compound-retrieval

Retrieve chemical compound data from PubChem and ChEMBL with disambiguation, cross-referencing, and stereochemistry handling. Use for resolving compound names to SMILES/InChI/CID/ChEMBL IDs (including OPSIN deterministic IUPAC-name-to-structure parsing), fetching molecular properties, distinguishing isomers/stereo forms, and cross-validating identity across databases. Always use English compound names; flags ambiguous queries (e.g., Vitamin D has multiple forms).

77

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable retrieval workflow with concrete tool calls, clear sequencing, and validation checkpoints. Its main gap is progressive disclosure — everything lives inline in one file with no external reference structure despite exceeding the single-file threshold.

Suggestions

Move the Tool Reference catalog (PubChem/ChEMBL/Name-parsing tool lists) into a references/TOOLS.md file and link to it from the relevant phases, keeping the inline body focused on the workflow.

Consider extracting the Evidence Grading and Fallback Chains tables into a references/DISAMBIGUATION.md with a one-line pointer, so the main SKILL.md stays a concise overview.

Verify the referenced src/tooluniverse/tools/smiles_verifier.py path resolves within the bundle or note it as an external codebase dependency to avoid a broken inline reference.

DimensionReasoningScore

Conciseness

Lean and information-dense — it never explains concepts Claude already knows (no definitions of SMILES, PubChem, or stereochemistry) and every section (principles, workflow, fallbacks, grading) earns its place; only minor tool-name repetition between Phase 1 and the Tool Reference index.

3 / 3

Actionability

Provides fully executable tool calls with real example values ('OPSIN_name_to_structure(name="2-acetoxybenzoic acid")'), a concrete verification command ('python3 src/tooluniverse/tools/smiles_verifier.py --smiles ...'), and specific fallback mappings — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

A clear four-phase sequence (Clarify → Disambiguate → Retrieve → Report) with an explicit 'Verify: CID + ChEMBL ID + canonical SMILES + stereochemistry + salt forms' checkpoint and fallback-chain tables serving as error-recovery feedback loops.

3 / 3

Progressive Disclosure

Sections are well-organized and navigable, but the skill is a single monolithic file over 50 lines with no one-level-deep reference files, and the inline Tool Reference catalog is material that could live in a separate reference file.

2 / 3

Total

11

/

12

Passed

Description

100%

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 description that answers both what and when, lists several concrete capabilities, and uses third-person voice throughout. Trigger terms are well-aligned with how a user would request chemical compound lookups.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Retrieve chemical compound data', 'resolving compound names to SMILES/InChI/CID/ChEMBL IDs', 'fetching molecular properties', 'distinguishing isomers/stereo forms', and 'cross-validating identity' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

States what ('Retrieve chemical compound data from PubChem and ChEMBL with disambiguation, cross-referencing, and stereochemistry handling') and when via an explicit 'Use for resolving compound names... fetching molecular properties... distinguishing isomers/stereo forms' clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Covers natural domain terms a user would say — 'chemical compound', 'PubChem', 'ChEMBL', 'compound names', 'SMILES', 'molecular properties', 'isomers', 'Vitamin D' — giving good trigger coverage; the IUPAC/OPSIN jargon is additive specificity rather than the sole signal.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — chemical compound retrieval from PubChem and ChEMBL with stereochemistry handling — with distinctive triggers unlikely to overlap with other skills.

3 / 3

Total

12

/

12

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.