pde-solver

Solve partial differential equations — finite differences, spectral methods, and physics-informed neural networks (PINNs via DeepXDE). Supports 1D/2D/3D, steady/transient, linear/nonlinear PDEs with Dirichlet, Neumann, and periodic boundary conditions.

Quality

76%

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/pde-solver/SKILL.md

Quality

Content

82%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.

The body is a strong, self-contained PDE reference: executable code, a method-selection table, stability reference, and validation/troubleshooting sections. It loses minor points for plotting boilerplate and validation checkpoints being separated from the per-workflow sequence rather than woven into feedback loops.

Suggestions

Embed a brief validation checkpoint (e.g., 'Verify against analytical solution before trusting output') inside each workflow's numbered steps rather than only in the separate checklist.

Trim plotting boilerplate (fig, ax, savefig calls) from the core code examples to tighten token efficiency.

Consider extracting the stability reference and troubleshooting tables into a separate reference file so the main body leads with the workflows.

Dimension	Reasoning	Score
Conciseness	Largely dense executable code with minimal concept over-explanation, but some plotting boilerplate and docstrings could be trimmed to fully assume Claude's competence.	4 / 5
Actionability	Five fully executable copy-paste-ready Python examples plus a concrete install command and a method-selection table cover the common cases comprehensively.	5 / 5
Workflow Clarity	The method-selection table and a standalone Validation Checklist give a clear sequence with the first workflow including a CFL stability check, but checkpoints are not embedded as explicit stepwise feedback loops in each workflow.	4 / 5
Progressive Disclosure	Well-structured single-file skill with clear section headers and signaled external tool mentions (FEniCS, fluidsim); appropriately self-contained with no bundle files, with only minor organization gaps.	4 / 5
	Total	17 / 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.

The description is specific and well-keyworded with concrete methods and capabilities, but it omits an explicit 'Use when' trigger clause, capping its completeness at the midpoint. Distinctiveness is strong thanks to the named methods and library.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when solving PDEs like the heat, wave, Poisson, or Navier-Stokes equations, or when setting up PINNs with DeepXDE').

Include more common trigger synonyms (e.g., 'Navier-Stokes', 'diffusion', 'Laplace', 'Poisson') to push trigger term coverage toward comprehensive.

Tighten the boundary-condition list or move it to the body to keep the description focused on what + when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete methods (finite differences, spectral methods, PINNs via DeepXDE) plus concrete capabilities (1D/2D/3D, steady/transient, linear/nonlinear, Dirichlet/Neumann/periodic), giving comprehensive coverage.	5 / 5
Completeness	Provides a clear 'what' (solve PDEs via three named methods) but lacks any explicit 'Use when...' trigger clause, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Strong natural keyword coverage including synonyms (PDEs, PINNs, DeepXDE, boundary conditions), but falls just short of the comprehensive anchor due to a few common variations being absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (PDE solving with specific methods and named library DeepXDE) that is mostly distinct from ODE/FEM skills, with only minor overlap risk with closely related numerical solver skills.	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/pde-solver/SKILL.md
Commit: 7dabbf0

Reviewed: 3 days 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.