pubchem-database

Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/pubchem-database/SKILL.md

Quality

Content

75%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 thorough, highly actionable skill body with executable examples and real bundle-file references. The main weaknesses are verbosity (repetition and routine explanations) and inlining of detail that the reference file already covers.

Suggestions

Trim repetition: consolidate the repeated `import pubchempy as pcp` and near-identical `get_compounds` calls into one canonical example per capability rather than restating each time.

Move the long inline property list and PUG-View/REST URL patterns to references/api_reference.md, keeping only a key example inline with a pointer.

Add an explicit validation/verification checkpoint after batch and download operations (e.g. confirm file exists / response.status_code == 200 before processing) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable examples, but the 570-line body re-explains fairly routine PubChemPy usage and repeats patterns (imports, search calls) across many near-identical sections, which could be tightened.	3 / 5
Actionability	Code is concrete, executable, and copy-paste ready across all nine capability sections plus workflows; specific calls, parameters (Threshold, MaxRecords), and URLs are given throughout.	5 / 5
Workflow Clarity	Workflows 1-5 are clearly sequenced with concrete steps and per-compound error handling, and best-practice/rate-limit guidance is explicit; minor validation gaps (e.g. no explicit verify step after batch/download) keep it just below 5.	4 / 5
Progressive Disclosure	Clear overview with one-level-deep references to real files (references/api_reference.md, scripts/compound_search.py, scripts/bioactivity_query.py) that exist in the bundle; the body still inlines a lot that could live in the reference, so not a 5.	4 / 5
	Total	16 / 20 Passed

Description

75%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 specific, third-person, low-conflict description that enumerates concrete capabilities well. Its main weakness is the absence of an explicit trigger/"Use when" clause, which limits completeness.

Suggestions

Add an explicit 'Use when ...' clause, e.g. 'Use when searching PubChem for compounds by name/CID/SMILES, retrieving molecular properties, or running similarity/substructure/bioactivity queries.'

Include a few natural user-facing synonyms (e.g. 'chemical structure', 'molecular properties', 'drug-likeness') alongside the technical terms.

Keep the description as-is for brevity—avoid padding; the trigger clause is the main missing piece.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity"—plus the API stack and scale, giving comprehensive coverage.	5 / 5
Completeness	The "what" is clearly and thoroughly answered, but there is no explicit "when should Claude use it" / "Use when" clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural terms (PubChem, SMILES, bioactivity, cheminformatics) but lacks common user phrasings like "chemical structure," "molecular properties," or a "Use when" trigger phrase.	4 / 5
Distinctiveness Conflict Risk	PubChem/PUG-REST/PubChemPy and cheminformatics form a clear, narrow niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (574 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/pubchem-database/SKILL.md
Commit: 3a6c3a9

Reviewed: about 24 hours 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.