fluid-dynamics

Computational fluid dynamics — Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation. Spectral and finite-difference methods for incompressible and compressible flows.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/physics/fluid-dynamics/SKILL.md

Quality

Content

56%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.

A well-organized, code-forward skill with a genuinely executable flagship workflow and thoughtful validation/troubleshooting sections. Its weaknesses are the non-functional cylinder placeholder, plotting boilerplate, and the total absence of progressive disclosure — everything is inlined in one long file.

Suggestions

Replace the cylinder placeholder with a working penalty/immersed-boundary implementation (or move it to a reference file until it works) so every advertised core workflow is executable.

Split the plotting blocks and the flow-regime/troubleshooting tables into a reference file (e.g. references/visualization.md) and link to it, shrinking SKILL.md to an overview plus the core solver.

Add a short feedback loop for the validation checklist: what to change (dt, grid, Poisson iterations) when the divergence or CFL check fails.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight, functional code, but it carries unnecessary weight: ~50 lines of matplotlib boilerplate for the cavity plots and a 'cylinder_flow_simple' placeholder whose loop body is literally '# ... (full NS solver needed for proper simulation)'. This fits the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the minor-trimming level 4 anchor.	3 / 5
Actionability	The lid-driven cavity workflow is genuinely executable and complete, but the second advertised workflow (flow past a cylinder) is a placeholder that returns a field forced to zero inside the mask — effectively pseudocode. With one of three core workflows non-functional, this sits at 'some concrete guidance but incomplete' rather than 'mostly executable with minor gaps'.	3 / 5
Workflow Clarity	Steps are clearly organized (When to Use / Do NOT Use / workflows / Validation Checklist / Troubleshooting) with real checkpoints: a CFL/diffusion-number stability check before iteration, in-loop divergence monitoring, and the Ghia et al. (1982) benchmark comparison. It is not a 5 because there is no fix-and-retry feedback loop telling Claude what to do when validation fails (e.g., how to adapt dt or grid when the divergence check fails).	4 / 5
Progressive Disclosure	The body has clear section headers but is a single ~220-line monolith with three large inline code blocks and no references to any separate files (no references/, scripts/, or assets/ exist in the bundle). This matches 'some structure but could be better organized; content that should be separate is inline' rather than the level 4 anchor, where most bulk content would live in appropriately placed separate files.	3 / 5
	Total	13 / 20 Passed

Description

71%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 specific, well-scoped technical description with strong capability vocabulary, but it omits any explicit 'use when' trigger guidance and misses the most common natural acronym 'CFD'. Adding a trigger clause and common synonyms would lift the two weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when simulating fluid flow, computing drag/lift, or when the user mentions CFD, Navier-Stokes, cavity/channel flow, or turbulence.'

Include natural synonyms and the 'CFD' acronym in the description itself (they currently appear only in the tags field), plus terms like 'flow simulation' and 'aerodynamics'.

Narrow the compressible claim or state its limits (the body says shocks are out of scope) so the description does not over-claim relative to the skill's actual capabilities.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete capabilities ('Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation') plus method families, matching the comprehensive-coverage anchor. It clearly exceeds the 'several specific actions; minor gaps' level 4 anchor since nothing significant in the skill's own scope is missing.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, so per the judging guideline completeness is capped at 3. It is not a 4 because the 'when' is entirely absent rather than merely weakly stated.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('Computational fluid dynamics', 'Navier-Stokes', 'turbulence', 'drag/lift', 'channel flow') but common user phrasings are missing: the ubiquitous acronym 'CFD' (only present in tags, not the description), 'flow simulation', and 'aerodynamics'. This fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive-synonyms level 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is well defined by specific solver and benchmark vocabulary (lid-driven cavity, vortex methods, Reynolds-stress statistics), giving mostly distinct triggers. It is not a 5 because the broad 'computational fluid dynamics' framing with both incompressible and compressible, spectral and finite-difference scope overlaps closely with related skills — the body itself acknowledges a competing 'fluidsim' skill.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/physics/fluid-dynamics/SKILL.md
Commit: 4082a2e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.