astropy
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
87
86%
Does it follow best practices?
Impact
87%
1.70xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 skill description that clearly identifies its domain (astronomy/astrophysics Python library), lists specific capabilities comprehensively, and provides explicit 'Use when' guidance with natural trigger terms. It uses proper third-person voice throughout and covers both the 'what' and 'when' dimensions effectively. The only minor note is slight redundancy between the capability listing and the trigger clause, but this actually reinforces discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, WCS, coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, and astronomical data processing. | 3 / 3 |
Completeness | Clearly answers both 'what' (comprehensive Python library for astronomy covering coordinates, units, FITS, cosmology, etc.) and 'when' with explicit trigger guidance ('Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'astronomy', 'astrophysics', 'celestial coordinates', 'FITS files', 'cosmological calculations', 'WCS', 'coordinate transformations', 'unit conversions', 'time systems'. These are terms astronomers and data scientists would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in astronomy/astrophysics with domain-specific triggers like 'FITS files', 'celestial coordinates', 'cosmological distance calculations', and 'WCS' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent progressive disclosure and highly actionable code examples. Its main weakness is verbosity—there's substantial redundancy between the overview, 'When to Use' section, core capabilities summaries, and the common workflows. The content could be reduced by ~30% without losing any actionable information, particularly by trimming the 'When to Use' section and the generic best practices.
Suggestions
Remove or drastically shorten the 'When to Use This Skill' section since it largely duplicates the overview and core capabilities sections—this information is better conveyed by the YAML description field.
Trim the 'Best Practices' section to only non-obvious, astropy-specific advice; remove generic Python advice like 'use context managers' and 'prefer arrays over loops' that Claude already knows.
Consider merging the 'Core Capabilities' key operations lists with the 'Common Workflows' section to reduce redundancy—either show the operations as code or describe them, but not both.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant redundancy: the 'When to Use This Skill' section largely repeats the overview, the 'Core Capabilities' section repeats information already in the quick start and common workflows, and the best practices section includes generic advice Claude already knows (e.g., 'use context managers', 'prefer arrays over loops'). The content could be substantially tightened. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples across multiple common workflows (coordinate conversion, FITS file reading, cosmological calculations, catalog cross-matching). All examples use real imports, concrete values, and complete code blocks. | 3 / 3 |
Workflow Clarity | The common workflows show clear sequences of operations, but they lack validation checkpoints. For example, the FITS file workflow doesn't check if the file exists or if the HDU index is valid, and the cross-matching workflow doesn't validate that coordinate columns exist. For a library skill these are less critical than for destructive operations, but the workflows are presented as linear sequences without error handling or verification steps. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: a concise quick start at the top, summary descriptions of each core capability with clear 'See: references/X.md' pointers, and a consolidated reference files section at the bottom. All references are one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- 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.