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.
90
86%
Does it follow best practices?
Impact
100%
3.70xAverage score across 3 eval scenarios
Passed
No known issues
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 defines a specific computational domain (CFD), lists concrete capabilities and methods, and includes an explicit 'Use when' clause with rich trigger terms. It uses proper third-person voice throughout and would be easily distinguishable from other skills in a large collection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, turbulence analysis, vortex dynamics, geophysical flows, pseudospectral methods with FFT, HPC support, and output analysis. | 3 / 3 |
Completeness | Clearly answers both 'what' (computational fluid dynamics simulations with pseudospectral methods, FFT, HPC support, output analysis) and 'when' (explicit 'Use when' clause listing specific trigger scenarios like running fluid dynamics simulations, Navier-Stokes equations, turbulence analysis, etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'fluid dynamics simulations', 'Navier-Stokes', 'shallow water equations', 'turbulence', 'vortex dynamics', 'geophysical flows', 'CFD', 'pseudospectral', 'FFT', 'HPC'. These are the exact terms domain users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — computational fluid dynamics is a very specific domain. The combination of Navier-Stokes, shallow water equations, pseudospectral methods, and geophysical flows makes it extremely 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 strong actionability and excellent progressive disclosure. The main weaknesses are moderate verbosity (some redundancy between the workflow section and use cases, plus unnecessary descriptive text) and the lack of validation/error-handling checkpoints in the workflow, which is important for computationally expensive simulations. There's also a repeated typo ('uv uv pip install') that would cause installation failures.
Suggestions
Fix the 'uv uv pip install' typo (should be 'uv pip install') which appears three times in the installation section.
Add validation checkpoints to the workflow: e.g., verify FFT backend is available before running, check simulation output directory exists, validate that energy is conserved/decaying as expected during runs.
Trim the overview paragraph and 'Key strengths' bullet list — Claude doesn't need marketing copy about the framework's advantages. Jump straight to capabilities.
Consider consolidating the 'Common Use Cases' section with the workflow section to reduce redundancy, or move use cases to a reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary explanatory text (e.g., 'delivering performance comparable to Fortran/C++', 'Python's ease of use', listing key strengths that Claude doesn't need). The 'uv uv pip install' typo appears multiple times. Some sections like the overview paragraph and capability descriptions could be tightened. The use cases section is extensive and somewhat repetitive with the workflow section. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code throughout. Every solver has concrete import paths, parameter configuration is shown with specific values, and complete end-to-end examples are provided for multiple use cases including 2D turbulence, stratified flows, 3D MPI simulations, and Taylor-Green vortex validation. | 3 / 3 |
Workflow Clarity | The five-step workflow is clearly sequenced and easy to follow. However, there are no validation checkpoints — no guidance on checking if the simulation is running correctly, no error handling for common failures (e.g., FFT not installed, memory issues with high resolution), and no feedback loops for verifying output integrity. For a computational simulation framework where runs can be expensive, this is a notable gap. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to six specific reference files (installation, solvers, simulation workflow, parameters, output analysis, advanced features). Each section ends with a clear pointer to the relevant reference file. | 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.