cpp-pro

Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimization, or careful memory management — or when addressing performance bottlenecks, concurrency issues, and build system configuration with CMake.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%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, actionable body that keeps the overview tight while offloading detail to verified reference files, and pairs its workflow with explicit sanitizer/benchmark feedback loops. Trimming the persona intro and a few obvious directives would push conciseness higher.

Suggestions

Remove or compress the 'Senior C++ developer with deep expertise...' opening line; it is persona padding rather than actionable guidance.

Prune MUST-DO items that restate C++ knowledge Claude already has (e.g., 'Apply RAII universally', 'Use auto with type deduction') and keep only skill-specific directives.

Add one or two inline executable snippets to the Core Workflow steps (e.g., the exact sanitizer/static-analysis commands) so the workflow section is self-contained.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's C++ competence, with executable code and terse directives; the promotional opening line ('Senior C++ developer with deep expertise...') and a few self-evident MUST-DO items (RAII, smart pointers) could be trimmed.	4 / 5
Actionability	Provides concrete, copy-paste-ready code (concept, RAII wrapper, smart-pointer usage), specific compiler flags, and clear output deliverables; the high-level Core Workflow steps describe intent without inline code in that section, a minor gap covered by the Key Patterns block.	4 / 5
Workflow Clarity	The 5-step Core Workflow has an explicit sequence with validation checkpoints and feedback loops: step 4 fixes all ASan/UBSan errors before proceeding, and step 5 re-measures when performance targets are unmet.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with a Reference Guide table pointing to five real, one-level-deep reference files, each with a clear 'Load When' condition — easy navigation with no nested indirection.	5 / 5
	Total	18 / 20 Passed

Description

95%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, well-structured description that names concrete capabilities and gives explicit, multi-clause trigger guidance in third person. Minor room to sharpen the lead action verbs, but overall it closely matches the top reference examples.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Writes, optimizes, and debugs') paired with specific techniques (concepts, ranges, coroutines, SIMD, template metaprogramming, CMake), but the lead verbs are slightly broad compared to the fully enumerated anchor-5 example.	4 / 5
Completeness	Explicitly answers both 'what' (writes/optimizes/debugs C++ using modern features and systems techniques) and 'when' ('Use when building or refactoring C++ code requiring... or when addressing performance bottlenecks, concurrency issues, and build system configuration with CMake') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural terms a C++ user would actually say — 'C++', 'C++20', 'C++23', 'modern C++', 'template metaprogramming', 'SIMD', 'memory management', 'concurrency', 'CMake' — including version synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear C++20/23 systems niche with distinct triggers (concepts, ranges, coroutines, SIMD, CMake); minimal overlap risk with related rust/embedded skills noted in metadata.	5 / 5
	Total	19 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Jeffallan/claude-skills
Path: skills/cpp-pro/SKILL.md
Commit: 882ef55

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.