numerical-patterns

Numerical computing patterns for C++20 including matrix operations, iterative solvers, numerical stability, data pipelines, and HPC I/O with MPI-IO and HDF5.

Install with Tessl CLI

npx tessl i github:ysyecust/everything-claude-code --skill numerical-patterns

What are skills?

Quality

64%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/numerical-patterns/SKILL.md

SKILL.md

Review

Evals

Discovery

50%

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 excels at specificity and distinctiveness by clearly defining a technical niche with concrete capabilities. However, it critically lacks explicit trigger guidance ('Use when...') which would help Claude know when to select this skill, and the trigger terms are heavily technical jargon that users may not naturally use.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about scientific computing in C++, numerical algorithms, parallel I/O, or mentions HDF5/MPI.'

Include more natural user terms alongside technical jargon, such as 'scientific computing', 'linear algebra', 'parallel processing', 'high-performance computing', or 'number crunching in C++'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'matrix operations, iterative solvers, numerical stability, data pipelines, and HPC I/O with MPI-IO and HDF5'. These are concrete, technical capabilities.	3 / 3
Completeness	Describes 'what' (numerical computing patterns and specific capabilities) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Contains relevant technical keywords (C++20, matrix operations, MPI-IO, HDF5, HPC) but these are specialized jargon. Missing more natural user terms like 'scientific computing', 'linear algebra', 'parallel computing', or 'high-performance'.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: C++20 + numerical computing + HPC + specific libraries (MPI-IO, HDF5). Unlikely to conflict with general C++ skills or other document processing skills.	3 / 3
	Total	9 / 12 Passed

Implementation

79%

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

This is a strong, actionable skill with excellent code quality and efficient token usage. The main weaknesses are the lack of explicit validation/error-handling workflows for HPC operations (where failures can be costly) and the monolithic structure that could benefit from progressive disclosure to separate reference files for advanced topics like HDF5 and MPI-IO.

Suggestions

Add explicit error checking and validation steps to MPI-IO and HDF5 examples (e.g., check return codes, verify file integrity after writes)

Split HPC I/O section into a separate REFERENCE.md file and link from the main skill, keeping only a brief overview inline

Add a validation workflow for iterative solvers showing how to verify convergence and handle non-convergence cases

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, providing code examples without unnecessary explanations of basic concepts. It assumes Claude understands C++, numerical computing, and HPC concepts, focusing only on implementation patterns.	3 / 3
Actionability	All code examples are complete, executable C++20 code with proper includes, class definitions, and usage examples. The MPI-IO, HDF5, and solver implementations are copy-paste ready with clear function signatures.	3 / 3
Workflow Clarity	While individual code patterns are clear, the skill lacks explicit validation steps for numerical operations (e.g., checking convergence, verifying file writes succeeded, handling MPI errors). The Key Principles mention testing but don't integrate validation into workflows.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers, but it's a monolithic document (~400 lines) that could benefit from splitting advanced topics (HDF5, MPI-IO) into separate reference files. No external file references are provided.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed: 5 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.