cpp-pro

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.

Quality

49%

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 ./skills/cpp-pro/SKILL.md

Quality

Content

32%Scale 1-5

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

This skill is a generic, high-level overview of C++ best practices that provides almost no information Claude doesn't already know. It lacks concrete code examples, executable guidance, and meaningful workflows. The content reads more like a job description or capability summary than an actionable skill that would change Claude's behavior.

Suggestions

Add concrete, executable C++ code examples showing specific patterns (e.g., a RAII wrapper, a move-enabled class, a constexpr function, a CMakeLists.txt template) rather than just listing concepts.

Define a clear workflow with validation steps, e.g.: 1. Write code → 2. Build with CMake → 3. Run sanitizers → 4. Fix issues → 5. Run benchmarks, with specific commands for each step.

Remove the generic 'Use this skill when' / 'Do not use this skill when' boilerplate and the focus areas list of topics Claude already knows; replace with project-specific conventions or non-obvious patterns.

Either provide the referenced `resources/implementation-playbook.md` bundle file or remove the reference and inline the most critical content.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary boilerplate (generic 'Use this skill when' / 'Do not use this skill when' sections that add no value) and explains concepts Claude already knows well (what RAII is, what smart pointers are, what STL algorithms are). The focus areas section is essentially a list of C++ topics Claude is already deeply familiar with. However, it's not excessively verbose.	3 / 5
Actionability	The skill provides no executable code examples, no concrete commands, and no specific patterns. It lists high-level guidelines like 'Prefer stack allocation and RAII' and 'Use smart pointers when heap allocation is necessary' which are vague directions Claude already knows. There are no copy-paste ready snippets, no CMakeLists.txt examples, and no concrete template patterns despite claiming to cover these areas.	2 / 5
Workflow Clarity	The 'Approach' section provides a rough sequence of priorities but lacks any concrete workflow steps, validation checkpoints, or feedback loops. The 'Output' section lists expected deliverables but doesn't explain how to produce or validate them. There's no build-test-validate cycle described despite mentioning sanitizers and benchmarks.	2 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` but no bundle files exist to support this reference, making it a dead link. The content that is present is relatively flat with no meaningful structure beyond basic headers. There's no clear navigation to deeper resources, and the reference that does exist is vaguely described ('If detailed examples are required').	2 / 5
	Total	9 / 20 Passed

Description

66%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 does a good job listing specific C++ capabilities and uses relevant technical trigger terms that users would naturally mention. Its main weakness is the lack of an explicit 'Use when...' clause, which limits Claude's ability to know precisely when to select this skill. Adding trigger guidance and a few more keyword variations (e.g., file extensions, C++ standard versions) would strengthen it.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for help writing, reviewing, or optimizing C++ code, or mentions .cpp/.h files.'

Include common keyword variations such as 'cpp', '.cpp', '.h', 'C++17', 'C++20', 'memory management', and 'compile' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities: RAII, smart pointers, STL algorithms, templates, move semantics, and performance optimization. These are concrete C++ concepts, though it could be more specific about what actions it performs (e.g., 'refactors code to use RAII', 'converts raw pointers to smart pointers').	4 / 5
Completeness	The 'what' is clear — writing idiomatic C++ code with modern features. However, there is no explicit 'when' clause (e.g., 'Use when...'). The absence of a 'when' clause caps this at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes strong natural keywords like 'C++', 'smart pointers', 'RAII', 'STL', 'templates', 'move semantics', and 'performance optimization' that users would naturally mention. Missing some common variations like 'cpp', '.cpp', '.h', 'header files', 'memory management', 'C++17/20/23', or 'compile'.	4 / 5
Distinctiveness Conflict Risk	The description is clearly focused on C++ specifically, with domain-specific terms like RAII, smart pointers, move semantics, and STL that distinguish it from general coding skills. Minor overlap risk with a generic 'write code' or 'performance optimization' skill.	4 / 5
	Total	15 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/cpp-pro/SKILL.md
Commit: 57c135b

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.