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 specialized computational fluid dynamics framework. It excels across all dimensions: it lists specific capabilities, includes natural domain-specific trigger terms, explicitly states both what it does and when to use it, and occupies a distinct niche unlikely to conflict with other skills. The use of third person voice is correct throughout.
| 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 framework with pseudospectral methods, FFT, HPC, output analysis) and 'when' (explicit 'Use when...' clause listing specific trigger scenarios like running fluid dynamics simulations, analyzing turbulence, etc.). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'fluid dynamics simulations', 'Navier-Stokes equations', 'shallow water equations', 'turbulence', 'vortex dynamics', 'geophysical flows', 'FFT', 'HPC'. These are the exact terms domain users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — computational fluid dynamics with specific equation types (Navier-Stokes, shallow water) and methods (pseudospectral, FFT) make it very unlikely to conflict with other skills. The domain is narrow and well-defined. | 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 (redundant examples between the workflow section and use cases, plus the Quick Reference repeating earlier content) and missing validation/error-handling checkpoints in the workflow. The `uv uv pip install` typo in the installation section is a notable error.
Suggestions
Add validation checkpoints to the workflow: verify parameter sanity before running (e.g., check resolution vs viscosity for numerical stability), check for simulation divergence, and verify output files exist after completion.
Reduce redundancy by either trimming the 'Common Use Cases' section to only show patterns not already demonstrated in the workflow, or removing the Quick Reference section which largely duplicates the step-by-step workflow.
Fix the `uv uv pip install` typo in the installation section — should be `uv pip install`.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. The overview section explains what FluidSim is and its strengths in a way that could be more concise. The 'Common Use Cases' section largely repeats patterns already shown in the workflow section. The Quick Reference at the end is somewhat redundant with earlier content. Also, the `uv uv pip install` appears to be a typo/duplication. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code throughout. Every solver has a concrete import statement, 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 or error recovery steps. For a simulation framework where misconfiguration could waste significant compute time, there should be explicit validation steps (e.g., checking parameter validity before running, verifying output files were created, handling simulation divergence). The note about AttributeError for typos is helpful but insufficient. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The main file provides a clear overview with executable quick-start examples, and each section ends with a well-signaled reference to a deeper file (e.g., 'See references/solvers.md for complete solver list'). All references are one level deep and clearly organized in the Resources section at the end. | 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
25e1c0f
- 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.