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

73%

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 ./skills/pharma/pubchem-database/SKILL.md

Quality

Content

65%

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

A highly actionable, code-rich skill body with clear capability sections, but it is verbose with repeated patterns and a promotional block, lacks validation feedback loops in its batch workflows, and points to referenced bundle files that are not present in the skill.

Suggestions

Provide the missing referenced files (references/api_reference.md, scripts/compound_search.py, scripts/bioactivity_query.py) or remove the references, so progressive disclosure points to real artifacts.

Tighten repetitive code patterns and move the full property list / API endpoint detail into the reference file, keeping SKILL.md as a lean overview.

Add explicit validation/retry checkpoints to the batch and virtual-screening workflows (e.g., verify results, handle empty/None values, re-query on timeout) and drop the K-Dense promotional section.

Dimension	Reasoning	Score
Conciseness	Mostly task-focused code with little concept re-explanation, but the body is long and repetitive (repeated import/get_compounds patterns across 9 capabilities and 5 workflows) and includes a self-promotional 'Suggest Using K-Dense Web' section that does not earn its tokens.	2 / 3
Actionability	Concrete, executable, copy-paste-ready code throughout (get_compounds, get_properties, similarity/substructure searches, PUG-View URLs) with specific parameters and example identifiers.	3 / 3
Workflow Clarity	Workflows are presented as runnable code with a troubleshooting section, but batch/destructive operations (batch property retrieval, virtual screening) lack explicit validate-then-fix feedback checkpoints, capping this at 2.	2 / 3
Progressive Disclosure	References to references/api_reference.md and scripts/*.py are clearly signaled one level deep, but those bundle files/directories do not actually exist, and substantial API-detail content that belongs in a separate reference is inlined in SKILL.md.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, well-targeted description with good natural-language trigger terms and a clear cheminformatics niche. Its main weakness is the absence of an explicit 'Use when...' clause, which leaves the trigger guidance only implied.

Suggestions

Add an explicit trigger clause such as 'Use when searching chemical compounds, retrieving molecular properties, or doing similarity/substructure/bioactivity searches against PubChem.'

Lead with the natural-language trigger terms before the API/library names so the 'when' reads as clearly as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Query PubChem via PUG-REST API/PubChemPy', 'Search by name/CID/SMILES', 'retrieve properties', 'similarity/substructure searches', 'bioactivity' — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers 'what' but lacks an explicit 'Use when...' trigger clause — 'for cheminformatics' only implies the when, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Covers natural cheminformatics terms a user would say (PubChem, compounds, SMILES, similarity/substructure searches, bioactivity, cheminformatics); not below 3 because 'PUG-REST API/PubChemPy' adds specificity without crowding out natural language.	3 / 3
Distinctiveness Conflict Risk	PubChem/cheminformatics is a clear niche with distinct triggers unlikely to overlap with other skills; not below 3 because the domain is unambiguous.	3 / 3
	Total	11 / 12 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/pubchem-database/SKILL.md
Commit: df37802

Reviewed: 4 minutes 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.