neural-operator

Train neural operators (FNO, DeepONet) to learn solution maps for parametric PDE families. Once trained, solve new PDE instances in milliseconds. Use when you need to solve many instances of the same PDE with different parameters/ICs/BCs.

Quality

70%

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/neural-operator/SKILL.md

Quality

Content

57%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 highly actionable, well-organized skill body with strong executable examples, held back by inlined tangential code, absent validation gates, and no progressive disclosure into reference files.

Suggestions

Extract the pseudospectral Burgers data-generation helper into a scripts/ file and reference it, trimming the main body to the neural-operator-specific content.

Add an explicit validation checkpoint in the workflow, e.g. 'Only use the trained surrogate when relative L2 error < threshold; otherwise train longer or increase n_modes'.

Move extended material (architecture details, DeepONet implementation, hyperparameter guidance) into references/ files and link to them one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-and-tables format, but the ~40-line pseudospectral Burgers solver is tangential data-generation detail that could be trimmed or moved, and the Overview/Tips restate prior content.	3 / 5
Actionability	Provides multiple copy-paste-ready Python examples (data gen, FNO training, DeepONet class, evaluation/viz) plus concrete hyperparameter and troubleshooting tables, with only the DeepONet usage left partly as commented pseudocode.	4 / 5
Workflow Clarity	The numbered Core Workflows sequence data-gen → train → evaluate, but there are no explicit validation checkpoints gating the trained surrogate before use, which caps this dimension for an iterative/batch operation.	3 / 5
Progressive Disclosure	Clean section structure but everything is inlined in one ~250-line file with no references/ bundle; content like the data-generation solver and DeepONet class that could live in separate files is inline.	3 / 5
	Total	13 / 20 Passed

Description

82%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 strong, specific description that clearly states both capability and trigger conditions in third person. Trigger terms and distinctiveness are excellent; only specificity is slightly limited by the narrow action list.

Dimension	Reasoning	Score
Specificity	Names the domain (neural operators, FNO, DeepONet) and two concrete actions ('learn solution maps', 'solve new PDE instances in milliseconds'), but coverage is narrow rather than comprehensive.	3 / 5
Completeness	Explicitly answers both what ('Train neural operators... solve new PDE instances in milliseconds') and when ('Use when you need to solve many instances of the same PDE with different parameters/ICs/BCs') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Includes natural domain terms a user would say (PDE, neural operators, FNO, DeepONet, parameters/ICs/BCs) with good coverage including architecture synonyms, though a few common variations are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (neural-operator surrogates for parametric PDE families) with distinct triggers (FNO, DeepONet, PDE surrogate) and minimal overlap risk with a generic solver.	5 / 5
	Total	17 / 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/neural-operator/SKILL.md
Commit: 5f2a37b

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.