CtrlK
BlogDocsLog inGet started
Tessl Logo

geomaster

Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, cloud-native workflows (STAC, COG, Planetary Computer), and 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 highly actionable with extensive executable code and a well-organized reference layer, but it is verbose for a SKILL.md (much content could live in references) and lacks a clearly sequenced workflow with validation checkpoints. Progressive disclosure is good but slightly weakened by inlined reference-grade material and one orphaned file.

Suggestions

Move several full code examples (e.g. Earth Engine time series, image classification, STAC/COG workflows) into the corresponding reference files and keep the SKILL.md body to a single Quick Start plus concise pointers, reducing token load.

Add an explicit end-to-end workflow with validation checkpoints (e.g. load data -> verify CRS -> process -> validate output) for at least one representative task so multi-step sequencing is clear.

Either link the unreferenced specialized-topics.md from the Detailed Documentation list or remove it from the bundle so all reference files are discoverable from the body.

DimensionReasoningScore

Conciseness

The body is largely efficient code blocks with minimal padding, but it inlines a large volume of reference-grade example code (NDVI, GeoPandas, Earth Engine, terrain, classification, STAC, COG, performance) that partly belongs in the reference files and could be tightened given Claude's existing familiarity with these libraries.

3 / 5

Actionability

Provides fully executable, copy-paste-ready code covering the common cases (NDVI computation, spatial join with CRS handling, terrain metrics, RF image classification, STAC search/load, COG read-write), with concrete library calls and parameters rather than vague direction.

5 / 5

Workflow Clarity

Content is organized topically (Installation, Quick Start, Core Concepts, Common Operations, Best Practices) rather than as a sequenced multi-step workflow, and there are no explicit validation checkpoints or feedback loops between steps; it is closer to a reference catalog than a guided process.

3 / 5

Progressive Disclosure

Good structure with 13 clearly signaled one-level-deep references listed in a 'Detailed Documentation' section with short descriptions, all pointing to real files; minor gaps include a substantial amount of inlined example code and one unreferenced bundle file (specialized-topics.md).

4 / 5

Total

15

/

20

Passed

Description

92%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 is strong: it states concrete capabilities across many sub-domains and provides an explicit 'Use for...' trigger clause. It is comprehensive and clearly distinct, with only minor gaps in natural trigger term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities across domains — 'satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral)', 'vector and raster data operations', 'spatial statistics', 'point cloud processing', 'network analysis', 'cloud-native workflows (STAC, COG, Planetary Computer)' — giving comprehensive coverage rather than abstract language.

5 / 5

Completeness

Clearly answers 'what' (the comprehensive capability list) and explicitly answers 'when' with the 'Use for remote sensing workflows, GIS analysis, spatial ML, ... and any geospatial computation task' trigger clause containing concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage including 'remote sensing', 'GIS analysis', 'spatial ML', 'Earth observation data processing', 'terrain analysis', 'hydrological modeling', and 'marine spatial analysis'; a few common terms/file extensions (e.g. .tif, .geojson, satellite names) that users might say are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear geospatial-science niche with distinct triggers (remote sensing, GIS, spatial ML, Earth observation) and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.