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

72%

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

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with executable main code and genuine validation checkpoints, but it is weakened by a non-functional placeholder 'Core Workflow' and a monolithic single-file structure with no progressive disclosure.

Suggestions

Replace or remove the '### 3 Flow Past a Cylinder' placeholder with either a complete executable example or move it out of the numbered 'Core Workflows' so it is not presented as a working workflow.

Move the full lid-driven cavity solver into a scripts/ file (e.g., scripts/lid_driven_cavity.py) and keep a concise invocation snippet plus results-interpretation in SKILL.md to improve progressive disclosure.

Trim the plotting boilerplate to the essential lines, or relocate it to a reference, to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code with no concept lectures, but the 'cylinder_flow_simple' block is a low-value placeholder ('This is a simplified placeholder — real cylinder flows need proper immersed boundary') and the plotting boilerplate is lengthy; not a 1 because there is no padded explanation of concepts Claude knows, not a 3 because of the placeholder and boilerplate that could be tightened.	2 / 3
Actionability	The lid-driven cavity solver and centerline code are fully executable and copy-paste ready, but '### 3 Flow Past a Cylinder' is a Core Workflow whose code does not actually simulate anything ('... (full NS solver needed for proper simulation)'); not a 3 because a presented core workflow is incomplete placeholder code, not a 1 because the primary workflow is concrete and runnable.	2 / 3
Workflow Clarity	Workflows are numbered, the cavity solver includes inline validation (CFL/diffusion stability check, periodic divergence monitoring), and a 'Validation Checklist' plus 'Troubleshooting' table provide explicit checkpoints and error-recovery guidance; not a 2 because validation is explicit rather than implicit.	3 / 3
Progressive Disclosure	The file is well-sectioned (Overview, When to Use, Do NOT Use, Core Workflows, Reference, Validation, Troubleshooting) with no nested references, but there are no bundle files at all and a ~110-line full solver is inlined in a ~220-line SKILL.md that could be offloaded to a script; not a 1 because organization is good, not a 3 because content that should be separate is inline and there are no one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, specific description with good natural trigger terms and a clear niche, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g., 'Use when simulating incompressible or compressible flow, computing drag/lift, or analyzing turbulence') to lift completeness to 3.

Include a few more conversational trigger variations a user might say (e.g., 'CFD', 'flow simulation', 'fluid solver') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Quotes 'Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation' — a list of multiple specific concrete capabilities matching the score-3 anchor; not a 2 because it is comprehensive rather than naming only a domain and some actions.	3 / 3
Completeness	It clearly answers 'what' (solvers, flow types, computations) but has no 'Use when...' or equivalent explicit trigger clause, so per the judging guideline completeness is capped at 2; not a 1 because the 'what' is strong, not a 3 because 'when' is only implied.	2 / 3
Trigger Term Quality	Natural CFD terms a user would say appear directly: 'Computational fluid dynamics', 'Navier-Stokes', 'lid-driven cavity', 'channel flow', 'turbulence', 'drag/lift'; not a 2 because coverage spans the common variations a practitioner would invoke, not just a single keyword.	3 / 3
Distinctiveness Conflict Risk	The CFD/Navier-Stokes niche with concrete flow types is clearly distinct (the body even carves out a sibling 'fluidsim' skill), unlikely to trigger the wrong skill; not a 2 because the triggers are specific rather than merely 'somewhat specific'.	3 / 3
	Total	11 / 12 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: 52845c3

Reviewed: about 10 hours 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.