Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

FluidSim CFD Simulation Assistant

A rigorous skill for planning, validating, restarting, and analyzing FluidSim computational fluid dynamics runs.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Guides safe, reproducible use of FluidSim 0.9.0, the Python pseudospectral CFD framework.

  • Enforces a required workflow: state equations, units/nondimensionalization, geometry, boundaries, forcing, observables, and acceptance criteria before anything runs
  • Helps pick a solver (ns2d, ns2d.strat, ns3d.bouss, and more) and inspect generated default parameters
  • Bundles local tools: strict-JSON config validator, CPU/RAM/disk/wall-time estimator, dry-run script generator, output inventory, budget summary, and restart-compatibility checker
  • Adds a scientific acceptance gate — no "converged", "DNS", or "validated" labels without spectra, CFL history, refinement, and budget residual evidence
  • Documents FFTW/PFFT/P3DFFT and MPI backend installation, ABI pitfalls, and refuses to claim GPU acceleration

Safety notes are explicit: it never submits MPI jobs automatically and never emits --modify-params, since the upstream CLI executes Python passed to that flag.

Who it's for

  • Researchers and grad students simulating 2D/3D periodic turbulence, stratified flows, or Boussinesq convection
  • HPC users who want a serial pilot and a resource budget before submitting cluster jobs
  • Teams that must preserve lock files, checksums, and restart lineage for paper reproducibility

Examples

  1. "Set up forced 2D turbulence at 256²" → the skill walks through solver choice, default-parameter inspection, a strict JSON plan, then solver_config_validator.py and grid_resource_estimator.py.
  2. Point it at an existing run directory and ask "is this resolution adequate?" → it uses output_inventory.py and budget_summary.py to check spectral tails, energy budget residuals, and time-step history.
  3. "Continue from this state file to t=20" → restart_compatibility.py compares solver, grid, versions, and forcing state before drafting a controlled restart.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/fluidsim folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/fluidsim/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && cp -r scientific-agent-skills/skills/fluidsim ~/.claude/skills/fluidsim

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Copy the skill into your Claude skills folder: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/fluidsim ~/.claude/skills/fluidsim
  3. Confirm Python 3.11+ is available (python3 --version); the bundled scripts use only the standard library.
  4. For real simulations, create a locked environment in a project folder: uv init --python 3.11, then uv add "fluidsim[fft]==0.9.0" "fluidfft==0.4.5" "pyFFTW==0.15.1", followed by uv lock && uv sync --frozen.
  5. Add uv pip install h5py if you want the HDF5/netCDF metadata tools. For MPI, verify a site-compatible MPI runtime and FFTW development headers with your cluster admin first.
  6. Restart Claude Code and try a prompt such as "Plan a 2D forced turbulence run with FluidSim".
View source on GitHub ↗License: MIT