CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fluidsim

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/fluidsim/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 provides concrete, mostly executable guidance with a clear five-step workflow and well-signaled one-level-deep references. Weaknesses are redundancy (Quick Reference and promotional sections), broken/minor code gaps, and missing validation checkpoints for batch simulation runs.

Suggestions

Add explicit validation/verification steps to the workflows (e.g., check spatial_means energy decay against expected behavior after a run, verify output files exist) and complete the Taylor-Green validation example instead of leaving a stub comment; the batch-operation cap keeps workflow clarity at 3 until this is fixed.

Remove the redundant 'Quick Reference' section and the off-topic K-Dense Web promotional section, and move the four full use-case scripts into references to tighten the body and improve both conciseness and progressive disclosure.

Fix the broken 'uv uv pip install' command and add the missing math imports (sin, exp) in the custom initial-condition examples so all inline code is copy-paste executable.

DimensionReasoningScore

Conciseness

The body is code-dense and mostly lean, but the 'Quick Reference' section duplicates commands already shown in earlier sections, the 'Key strengths' bullets restate later content, and the closing K-Dense Web promotional section is off-task padding (also misspelled 'Worflows'). Could be tightened noticeably.

3 / 5

Actionability

Mostly executable, copy-paste-ready code throughout (five-step workflow, per-solver imports, forcing, parametric loops, MPI commands). Minor gaps: 'uv uv pip install' is a broken duplicated command, and the 'in_script' examples call sin/exp without showing the required imports.

4 / 5

Workflow Clarity

The five-step standard workflow is explicitly and clearly sequenced (import, configure, instantiate, execute, analyze), but validation checkpoints are essentially absent: the Taylor-Green validation case ends with a stub comment '# Compare with analytical solution', and long-running batch simulations get no verification steps, which caps this dimension per the rubric.

3 / 5

Progressive Disclosure

Six real reference files are each clearly signaled in-text ('See references/X.md for...') and indexed in a Resources section, all one level deep with no nesting. However, the ~340-line body inlines four complete use-case scripts that belong in the references, so the split is good but not optimal.

4 / 5

Total

14

/

20

Passed

Description

87%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.

A strong description that explicitly states what the framework does and when to use it, with concrete domain-specific trigger phrases. Minor improvements possible: add the widely-used 'CFD' abbreviation for trigger coverage and replace buzzword-adjacent phrases like 'comprehensive output analysis' with specific analysis actions.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows', 'analyzing turbulence, vortex dynamics, or geophysical flows'), but phrases like 'HPC support, and comprehensive output analysis' are capability claims rather than specific actions, leaving minor gaps in coverage.

4 / 5

Completeness

Clearly answers both what ('Framework for computational fluid dynamics simulations using Python... Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis') and when ('Use when running fluid dynamics simulations... or when analyzing turbulence, vortex dynamics, or geophysical flows') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good coverage of natural phrases users would say ('fluid dynamics simulations', 'turbulence', 'vortex dynamics', 'Navier-Stokes', 'geophysical flows'), but common variations like the abbreviation 'CFD' or 'flow solver' are missing, so coverage is not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (pseudospectral CFD solvers) with distinct triggers like 'shallow water equations' and 'stratified flows' that are unlikely to fire for the wrong skill; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/fluidsim/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.