pubchem-database
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
79
75%
Does it follow best practices?
Impact
84%
1.47xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/pubchem-database/SKILL.mdQuality
Discovery
64%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 excels at specificity and domain-appropriate trigger terms, clearly identifying PubChem querying capabilities with technical precision. However, it critically lacks an explicit 'Use when...' clause, which is essential for Claude to know when to select this skill. The technical depth is strong but the missing trigger guidance significantly limits its effectiveness for skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about chemical compounds, molecular structures, drug properties, or needs to look up substances in PubChem.'
Include common user phrasings like 'look up a chemical', 'find compound information', 'chemical database search' to capture non-expert queries.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity' - these are clear, actionable capabilities. | 3 / 3 |
Completeness | While the 'what' is well-covered with specific capabilities, there is no explicit 'Use when...' clause or equivalent trigger guidance. The description only implies when to use it through domain context. | 1 / 3 |
Trigger Term Quality | Excellent coverage of natural terms: 'PubChem', 'compounds', 'SMILES', 'CID', 'bioactivity', 'cheminformatics', 'similarity/substructure searches' - these are terms users in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: PubChem-specific, chemistry domain terms (SMILES, CID, bioactivity, cheminformatics) make it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and clear workflow documentation. The code examples are comprehensive and executable, covering the full range of PubChem capabilities. The main weakness is some verbosity in introductory sections that could be trimmed, but overall the skill effectively teaches Claude how to interact with PubChem's API.
Suggestions
Remove or significantly condense the 'When to Use This Skill' section - Claude can infer appropriate use cases from the capabilities described
Consolidate the Overview section to avoid repeating information that appears in the core capabilities
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as the 'When to Use This Skill' section that largely restates what Claude would infer from the overview. The 'Overview' section also repeats information. However, most content is useful and not padded with basic explanations. | 2 / 3 |
Actionability | Excellent actionability with fully executable Python code examples throughout. All code snippets are copy-paste ready with proper imports, and the skill covers multiple use cases with concrete, working examples including batch processing, similarity searches, and property retrieval. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit steps. The 'Common Workflows' section provides 5 well-structured workflows with clear progression. Error handling is explicitly covered with try/except patterns, and the troubleshooting section addresses common failure modes. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from core capabilities to advanced workflows. References to external files (references/api_reference.md, scripts/) are clearly signaled and one level deep. Helper scripts are documented with usage examples without overwhelming the main content. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (573 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
71add64
- 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.