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.

68

Quality

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable reference skill packed with executable code and a well-signaled reference index, but it is held back by redundant inline examples that duplicate bundle files, missing validation checkpoints on write operations, and one orphaned reference file.

Suggestions

De-duplicate NDVI: keep one canonical example in the body and point to references/code-examples.md for the others, removing the triplication across Quick Start, Spectral Indices, and STAC sections.

Add explicit validate→fix→retry feedback loops around destructive/batch writes (e.g. after cog_validate fails, loop back to fix and re-run; verify classified raster output before returning).

Link the orphaned references/specialized-topics.md from the Detailed Documentation section, or move its content into an already-linked file so every bundle file is discoverable.

DimensionReasoningScore

Conciseness

Prose is lean and assumes competence (no 'what is a CRS' explanations), but NDVI is computed in three separate sections and the inline Core Concepts CRS content duplicates references/coordinate-systems.md, so not every token earns its place.

2 / 3

Actionability

Nearly every section ships complete, executable, copy-paste-ready code — NDVI via rasterio, GeoPandas spatial joins, Earth Engine time series, STAC/Planetary Computer, COG reads/writes — matching the fully-executable anchor.

3 / 3

Workflow Clarity

Sections are clearly labeled and Best Practices are numbered, but the batch/destructive write operations (image classification output, COG write) lack explicit validate→fix→retry checkpoints, which caps clarity at 2 per the rubric.

2 / 3

Progressive Disclosure

The 'Detailed Documentation' section cleanly signals 13 one-level-deep references with descriptions, but one bundle file (specialized-topics.md) is never linked, and substantial inline content (CRS concepts, many code examples) overlaps the reference files, leaving content that could be separate inline.

2 / 3

Total

9

/

12

Passed

Description

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.

A strong, specific description that clearly states capabilities, provides natural trigger terms, and gives explicit 'Use for' guidance within a distinct geospatial niche. It uses third-person voice throughout and avoids vague padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'satellite imagery processing', 'vector and raster data operations', 'spatial statistics', 'point cloud processing', 'network analysis', 'cloud-native workflows' — matching the top anchor for enumerating specific capabilities.

3 / 3

Completeness

Explicitly answers both what (the enumerated capabilities) and when via a dedicated 'Use for remote sensing workflows, GIS analysis, spatial ML...' trigger clause, satisfying the highest completeness anchor.

3 / 3

Trigger Term Quality

The 'Use for' clause surfaces natural user phrasings — 'remote sensing workflows', 'GIS analysis', 'terrain analysis', 'hydrological modeling', 'marine spatial analysis' — alongside mission names (Sentinel, Landsat, MODIS), giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The geospatial/Earth-observation niche is sharply defined by domain-specific triggers (SAR, hyperspectral, STAC, COG, Planetary Computer) that are unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.