CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

88

Quality

85%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly communicates specific capabilities, uses natural trigger terms that C++ developers would use, and explicitly states both what the skill does and when to use it. The description is concise yet comprehensive, covering the domain thoroughly without being verbose or vague.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'Writes, optimizes, and debugs C++ applications' along with specific techniques like 'template metaprogramming', 'SIMD optimization', 'memory management', 'concurrency issues', and 'build system configuration with CMake'.

3 / 3

Completeness

Clearly answers both 'what' (writes, optimizes, debugs C++ applications using modern features and high-performance techniques) and 'when' with an explicit 'Use when...' clause covering building/refactoring C++ code with specific features, addressing performance bottlenecks, concurrency issues, and CMake configuration.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a user would say: 'C++', 'C++20/23', 'template metaprogramming', 'concepts', 'ranges', 'coroutines', 'SIMD', 'memory management', 'performance bottlenecks', 'concurrency', 'CMake'. These are all terms developers naturally use when seeking C++ help.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche in modern C++ development. The specific mention of C++20/23 features, template metaprogramming, SIMD, and CMake makes it very unlikely to conflict with skills for other languages or general programming tasks.

3 / 3

Total

12

/

12

Passed

Implementation

70%

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

This is a well-structured skill with strong progressive disclosure and clear workflow sequencing including validation checkpoints. Its main weaknesses are moderate verbosity in the constraints section (listing things Claude already knows) and actionability that leans more toward principles than concrete, executable commands. The code examples that are present are good quality but the skill could be tighter overall.

Suggestions

Trim the MUST DO/MUST NOT DO lists to only non-obvious, project-specific constraints — remove items like 'prefer smart pointers' and 'ignore compiler warnings' that Claude already knows.

Add concrete commands to the workflow steps, e.g., specific sanitizer invocation flags (`-fsanitize=address,undefined`) and example CMake configuration commands rather than just naming the tools.

Remove the role description opening line ('Senior C++ developer with deep expertise...') as it wastes tokens on persona framing that doesn't change behavior.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary content. The role description line ('Senior C++ developer with deep expertise...') adds no value for Claude. The MUST DO/MUST NOT DO lists contain items Claude already knows well (e.g., 'prefer smart pointers', 'ignore compiler warnings'). The smart pointer example is trivially obvious. However, the overall structure is reasonably tight.

2 / 3

Actionability

Code examples are executable and concrete (concept definition, RAII wrapper), which is good. However, much of the guidance is at the level of principles and constraints rather than specific executable steps. The workflow is high-level ('Analyze architecture', 'Design with concepts') without concrete commands. The output templates section describes what to provide but doesn't show a concrete example of the deliverable structure.

2 / 3

Workflow Clarity

The core workflow has a clear 5-step sequence with explicit validation checkpoints: step 4 requires running sanitizers and fixing all issues before proceeding, and step 5 includes a feedback loop (re-measure if targets not met). This is well-structured for a skill covering a broad domain, with appropriate gating between steps.

3 / 3

Progressive Disclosure

Excellent use of progressive disclosure with a clear reference table mapping topics to specific files with 'Load When' guidance. The main skill provides a concise overview, key patterns, and constraints while deferring detailed guidance to five well-organized reference files. References are one level deep and clearly signaled.

3 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
jeffallan/claude-skills
Reviewed

Table of Contents

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.