Skip to content
SkillModel-led908 tokens in use

C++ Pro

Writes and tunes modern C++20/23 with concepts, RAII, smart pointers and move semantics, verified with sanitizers and benchmarks.

12,471 stars on the repository MIT LicenseJeffallan/claude-skills · skills/cpp-pro
/plugin marketplace add jeffallan/claude-skills /plugin install fullstack-dev-skills@fullstack-dev-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing C++ Pro costs

79tokens idle
908tokens in use
12,266tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure22/25
  • Examples9/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity36
  • Momentum40

C++ Pro gives Claude a working method for high-performance C++ code. It reviews the build system and compiler flags, designs interfaces with concepts, implements with RAII and constexpr, then checks quality with sanitizers and static analysis.

Performance work is measured: benchmark with real workloads, apply targeted changes such as SIMD, cache layout or move semantics, and measure again.

What You Get

  • Header files with interfaces and constrained templates
  • Implementation files when needed
  • CMakeLists.txt updates
  • A test file that demonstrates usage
  • A short explanation of design decisions and performance characteristics

Common Use Cases

  • Constraining templates with C++20 concepts
  • Wrapping a C resource in an RAII class
  • Fixing memory errors found by sanitizers
  • Speeding up a hot path with SIMD or better cache layout
  • Configuring CMake builds with warnings and sanitizers

What Makes It Unique

Verification is built into the workflow: sanitizer reports must be fixed before moving on, and unmet performance targets lead to targeted changes and a new measurement. Reference files cover modern features, templates, memory and performance, concurrency and build tooling.

Under The Hood

The skill is a SKILL.md with five reference files and no scripts. It tells the agent to build the project and run sanitizers, static analysis and benchmarks, so it executes shell commands and compiler tools on your machine and writes C++ and CMake files in your project. It does not fetch web pages or call outside APIs.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers