Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.
78
70%
Does it follow best practices?
Impact
95%
1.13xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/pymatgen/SKILL.mdQuality
Discovery
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.
This is a strong description with excellent domain-specific terminology and concrete capabilities that clearly define a computational materials science toolkit. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The specificity and distinctiveness are excellent, making it unlikely to conflict with other skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about crystal structures, materials properties, CIF/POSCAR files, phase diagrams, band structure calculations, or Materials Project queries.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete capabilities: crystal structures with specific formats (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, and format conversion. These are concrete, identifiable actions/domains. | 3 / 3 |
Completeness | The 'what' is well covered with specific capabilities, but there is no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by listing the domain. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords that users in computational materials science would use: 'CIF', 'POSCAR', 'phase diagrams', 'band structure', 'DOS', 'Materials Project', 'crystal structures', 'format conversion', 'computational materials science'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in computational materials science with very specific triggers like CIF, POSCAR, band structure, DOS, and Materials Project that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels in actionability with comprehensive, executable code examples covering the full breadth of pymatgen functionality, and has excellent progressive disclosure with well-organized references. However, it is significantly too verbose - many sections explain things Claude already knows, list tools without actionable context, and include best practices that are generic programming advice. Workflows would benefit from explicit validation checkpoints, especially for multi-step computational workflows where convergence checking is critical.
Suggestions
Cut the 'When to Use This Skill' section entirely - Claude can infer applicability from the content itself. Remove the 'Overview' paragraph and 'Integration with Other Tools' list, which add no actionable value.
Trim 'Best Practices' to only non-obvious, pymatgen-specific guidance (e.g., symprec tolerance, IStructure usage) and remove generic advice like 'handle exceptions' and 'parallelize when possible'.
Add explicit validation/convergence checks within multi-step workflows, e.g., after relaxation: check OUTCAR for convergence before proceeding to static calculation.
Remove the 'Additional Resources' links section and 'Version Notes' - these consume tokens for information that's either easily discoverable or time-sensitive.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, explaining many concepts Claude already knows (what pymatgen is, what PDF-like format detection means, listing integration tools without actionable guidance). Sections like 'When to Use This Skill', 'Best Practices' bullet lists, 'Integration with Other Tools' list, and 'Additional Resources' links add significant token overhead with minimal unique instructional value. The overview paragraph restates what the description already covers. | 1 / 3 |
Actionability | The skill provides extensive executable code examples throughout - structure creation, file conversion, phase diagrams, band structure analysis, VASP input generation, surface analysis, and more. Code snippets are copy-paste ready with proper imports and realistic parameters. | 3 / 3 |
Workflow Clarity | Multi-step workflows like the band structure calculation workflow are clearly sequenced with numbered steps, but they lack explicit validation checkpoints. For example, the band structure workflow doesn't verify convergence between steps, and the surface energy calculation doesn't validate slab quality before proceeding. The 'Best Practices' section mentions checking convergence but doesn't integrate it into the workflows themselves. | 2 / 3 |
Progressive Disclosure | The skill has excellent progressive disclosure with a clear overview, quick start section, and well-signaled one-level-deep references to separate files (core_classes.md, io_formats.md, analysis_modules.md, materials_project_api.md, transformations_workflows.md). The bundled resources section clearly describes what each reference file contains. | 3 / 3 |
Total | 9 / 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 (690 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
b58ad7e
Table of Contents
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.