pubchem-database-skill

Programmatic access to the PubChem database (via PUG-REST API and PubChemPy) for searching chemical compounds, retrieving physicochemical properties, performing structure similarity/substructure searches, and obtaining bioactivity data.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/pubchem-database-skill/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.

The body is highly actionable with executable examples and good structural organization, supported by real bundle files one level deep. It could be tightened by removing the duplicated bash/Python example pairs and pushing more detail into the existing reference file.

Suggestions

Drop the redundant bash one-liner variants and keep a single executable Python example per operation to save tokens.

Move the supported-operations, input-constraint, and troubleshooting detail into references/api_reference.md, leaving SKILL.md as a leaner overview with a clear pointer.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but each example is duplicated as both a bash one-liner and a Python block (six code blocks), and the Implementation Details section repeats the supported-operations list already covered in Key Features and the reference file.	3 / 5
Actionability	Provides fully executable, copy-paste-ready code covering all three common cases (get_properties, structure_search, get_bioactivity) with real function signatures matching scripts/pubchem_ops.py.	5 / 5
Workflow Clarity	Each operation is unambiguous with documented input constraints, error handling, and troubleshooting; these are read-only API calls so the destructive/batch validation cap does not apply, though there is no explicit multi-step workflow.	4 / 5
Progressive Disclosure	Well-organized sections with real one-level-deep references to scripts/pubchem_ops.py and references/api_reference.md, but the body inlines a fair amount of operation/error/troubleshooting detail that could live in the reference file.	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.

The description is specific and clearly distinct, listing concrete capabilities in third-person voice. Its main weakness is the absence of an explicit 'when to use' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when looking up PubChem compounds, retrieving chemical properties, or querying bioactivity/assay data').

Reduce technical jargon (PUG-REST, PubChemPy) in favor of natural user terms like 'molecule', 'drug compound', or 'CID/SMILES lookup'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'searching chemical compounds', 'retrieving physicochemical properties', 'performing structure similarity/substructure searches', and 'obtaining bioactivity data' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The description clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Captures natural terms users would say ('PubChem', 'chemical compounds', 'physicochemical properties', 'bioactivity data') but mixes in technical jargon ('PUG-REST API', 'PubChemPy') and omits common synonyms such as 'molecule' or 'drug'.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly distinct niche (programmatic PubChem/cheminformatics access) with specific triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/pubchem-database-skill/SKILL.md
Commit: f5ef65b

Reviewed: ~11 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.