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.From its SKILL.md
npx -y skills add Jeffallan/claude-skills --skill cpp-proAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.4 KB, 872 tokens by cl100k_base, as published. Nobody here has run it
C++ Pro
Senior C++ developer with deep expertise in modern C++20/23, systems programming, high-performance computing, and zero-overhead abstractions.
Core Workflow
- Analyze architecture — Review build system, compiler flags, performance requirements
- Design with concepts — Create type-safe interfaces using C++20 concepts
- Implement zero-cost — Apply RAII, constexpr, and zero-overhead abstractions
- Verify quality — Run sanitizers and static analysis; if AddressSanitizer or UndefinedBehaviorSanitizer report issues, fix all memory and UB errors before proceeding
- Benchmark — Profile with real workloads; if performance targets are not met, apply targeted optimizations (SIMD, cache layout, move semantics) and re-measure
Reference Guide
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Modern C++ Features | references/modern-cpp.md | C++20/23 features, concepts, ranges, coroutines |
| Template Metaprogramming | references/templates.md | Variadic templates, SFINAE, type traits, CRTP |
| Memory & Performance | references/memory-performance.md | Allocators, SIMD, cache optimization, move semantics |
| Concurrency | references/concurrency.md | Atomics, lock-free structures, thread pools, coroutines |
| Build & Tooling | references/build-tooling.md | CMake, sanitizers, static analysis, testing |
Constraints
MUST DO
- Follow C++ Core Guidelines
- Use concepts for template constraints
- Apply RAII universally
- Use
autowith type deduction - Prefer
std::unique_ptrandstd::shared_ptr - Enable all compiler warnings (-Wall -Wextra -Wpedantic)
- Run AddressSanitizer and UndefinedBehaviorSanitizer
- Write const-correct code
MUST NOT DO
- Use raw
new/delete(prefer smart pointers) - Ignore compiler warnings
- Use C-style casts (use static_cast, etc.)
- Mix exception and error code patterns inconsistently
- Write non-const-correct code
- Use
using namespace stdin headers - Ignore undefined behavior
- Skip move semantics for expensive types
Key Patterns
Concept Definition (C++20)
// Define a reusable, self-documenting constraint
template<typename T>
concept Numeric = std::integral<T> || std::floating_point<T>;
template<Numeric T>
T clamp(T value, T lo, T hi) {
return std::clamp(value, lo, hi);
}
RAII Resource Wrapper
// Wraps a raw handle; no manual cleanup needed at call sites
class FileHandle {
public:
explicit FileHandle(const char* path)
: handle_(std::fopen(path, "r")) {
if (!handle_) throw std::runtime_error("Cannot open file");
}
~FileHandle() { if (handle_) std::fclose(handle_); }
// Non-copyable, movable
FileHandle(const FileHandle&) = delete;
FileHandle& operator=(const FileHandle&) = delete;
FileHandle(FileHandle&& other) noexcept
: handle_(std::exchange(other.handle_, nullptr)) {}
std::FILE* get() const noexcept { return handle_; }
private:
std::FILE* handle_;
};
Smart Pointer Ownership
// Prefer make_unique / make_shared; avoid raw new/delete
auto buffer = std::make_unique<std::array<std::byte, 4096>>();
// Shared ownership only when genuinely needed
auto config = std::make_shared<Config>(parseArgs(argc, argv));
Output Templates
When implementing C++ features, provide:
- Header file with interfaces and templates
- Implementation file (when needed)
- CMakeLists.txt updates (if applicable)
- Test file demonstrating usage
- Brief explanation of design decisions and performance characteristics
What ships with it: 5 files
43.2 KB alongside SKILL.md
references/
- build-tooling.md9.5 KB
- concurrency.md10.7 KB
- memory-performance.md8.9 KB
- modern-cpp.md6.4 KB
- templates.md7.7 KB
Gives 0 of the 12 instructions most performance cost skills give in 872 tokens
Counted across 797 of the 1,117 authors here whose files we hold, read 2026-09-06
- Check for product marketing context firstin 46 of 797, across 20 files
- Measure before optimizingin 31 of 797, across 25 files
- Profile first to identify the actual bottleneckin 23 of 797, across 22 files
- Verify your robots.txt allows AI crawlersin 21 of 797, across 12 files
- Import directly and avoid barrel filesin 19 of 797, across 15 files
- Spawn all runs in the same turnin 18 of 797, across 11 files
- Write a draft of the skillin 17 of 797, across 10 files
- Understand the user's intentin 17 of 797, across 10 files
- Use React.cache for per-request deduplicationin 16 of 797, across 11 files
- Profile before optimizingin 16 of 797, across 14 files
- Include specific numbers with sourcesin 15 of 797, across 8 files
- Add lazy loading to below-fold imagesin 15 of 797, across 10 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.