CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

astropy

Astropy is the core Python package for astronomy, providing essential functionality for astronomical research and data analysis.

53

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/astropy/SKILL.md
SKILL.md
Quality
Evals
Security

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 a strong, code-heavy overview: executable Quick Start, four complete workflows, and per-module summaries with well-signaled one-level-deep references. The main weaknesses are duplicated sections (Overview and Reference Files repeat content already stated inline) and the fact that every referenced references/*.md file is missing from the bundle, so the disclosed detail layer is absent. Trimming the redundant sections and shipping the reference files would make this an exemplar.

Suggestions

Ship the referenced bundle files (references/units.md, coordinates.md, cosmology.md, fits.md, tables.md, time.md, wcs_and_other_modules.md) — currently none exist, so every "See:" pointer in the body is a dead end.

Delete or fold the "Reference Files" section into the inline per-module pointers (it duplicates all seven) and drop the verbatim repetition of the description in the Overview.

Add lightweight validation guidance to the workflows (e.g. check hdul[1].data is not None, verify header keywords exist before access) to reach explicit-checkpoint quality.

DimensionReasoningScore

Conciseness

The body is mostly efficient — capability lists are dense with concrete API names and code dominates over prose — but there is measurable redundancy: the Overview paragraph repeats the frontmatter description verbatim, the "Reference Files" section restates all seven per-module "See:" pointers already given inline, and "Additional Capabilities" re-describes content the wcs_and_other_modules.md reference covers. This fits the 'mostly efficient but could be tightened' anchor; it is not a 4 because two full sections are duplicative, and not a 2 because there is no tutorial-style padding explaining concepts Claude already knows.

3 / 5

Actionability

The body provides fully executable, copy-paste-ready code: a Quick Start exercising units, coordinates, time, FITS, tables, and cosmology; a working install command; and four Common Workflows (coordinate transforms, FITS analysis, cosmological distances, catalog cross-matching) using real APIs with correct imports (SkyCoord, match_to_catalog_sky, Planck18.luminosity_distance). The common cases are covered concretely, matching the top anchor.

5 / 5

Workflow Clarity

The Common Workflows present clear, ordered, self-contained steps with printed outputs (e.g. cross-matching includes a separation threshold check and filtered matched catalogs), and the operations are read-only so destructive-operation validation is not required. It is not a 5 because there are no explicit validation checkpoints or error-recovery guidance (e.g. verifying a FITS file opened correctly or handling missing header keywords), leaving minor validation gaps per the score-4 anchor.

4 / 5

Progressive Disclosure

The body is structured as an overview with each of the seven modules getting a short summary plus a clearly signaled one-level-deep pointer ("See: references/units.md for ..."), which is textbook progressive-disclosure structure. However, the bundle contains no references/ directory — none of the seven referenced files (units.md, coordinates.md, cosmology.md, fits.md, tables.md, time.md, wcs_and_other_modules.md) exist alongside SKILL.md, so navigation as shipped is broken and the detailed content is unreachable. This lands between 'good structure, minor organization gaps' (4) and 'clear overview with well-signaled one-level-deep references' (5); the missing bundle files keep it at 4.

4 / 5

Total

16

/

20

Passed

Description

48%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 correctly identifies the domain but wastes the rest of its budget on generic phrasing. It lists zero concrete capabilities and provides no 'Use when...' trigger guidance, so both specificity and completeness underperform what the body's capability list could have supported. A one-line enumeration of key capabilities (FITS, coordinates, units, cosmology, tables, WCS) plus a trigger clause would move this to the top of the scale.

Suggestions

Replace "providing essential functionality for astronomical research and data analysis" with 2-4 concrete capabilities, e.g. "for FITS file I/O, celestial coordinate transformations, unit/quantity calculations, cosmological calculations, and time handling".

Add an explicit trigger clause, e.g. "Use when working with FITS files (.fits), celestial coordinates, astronomical units and quantities, cosmology, or astronomical tables/".

Include natural synonyms and file extensions users would actually say (FITS, .fits, sky/celestial coordinates, redshift) to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("core Python package for astronomy") but the only actions offered are generic: "providing essential functionality for astronomical research and data analysis". No concrete capability (FITS handling, coordinate transforms, units, cosmology) is stated, matching the 'names the domain but actions are minimal or generic' anchor. It is not a 3 because no specific concrete action is listed, and not a 1 because the domain is explicitly named rather than pure abstract language.

2 / 5

Completeness

The 'what' is present but weakly specified ("providing essential functionality for astronomical research and data analysis"), and a 'when should Claude use it' clause is entirely absent. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3. It is not a 2 because the 'what' is not purely vague, and not a 4 because 'when' guidance is wholly missing rather than just under-specified.

3 / 5

Trigger Term Quality

Natural terms present are "astronomy", "Python package", and "astronomical research", but the description misses the phrases users would most naturally say for this skill's actual capabilities: FITS/FITS files, .fits, coordinates, units, cosmology, celestial, WCS, tables. Some relevant keywords with missing common variations matches the score-3 anchor; not a 4 because several of the highest-frequency natural terms are absent.

3 / 5

Distinctiveness Conflict Risk

"Core Python package for astronomy" carves out a clear niche with minimal conflict risk against non-astronomy skills. It is not a 5 because the generic trailing phrase "data analysis" creates minor overlap risk with general data-analysis skills, and the absence of astronomy-specific trigger terms weakens distinct triggering. It is clearly above the 3 anchor, which assumes overlap with similar skills.

4 / 5

Total

12

/

20

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 — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 15 missing

Warning

Total

13

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/astropy/SKILL.md

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.