- Home
- Skills
- Code Quality & Review
- cpp code quality
cpp code quality
Automated C++ static analysis and formatting with incremental diff support and Google-style standards.
Free
Works with the AI Agents you already use
cpp code quality
Example session with this skill installed
Run an incremental check on my recent changes and fix any formatting issues found.
- Read your context and instructions
- Compiled the cpp code quality
I have initiated the incremental code quality check. The system identified 4 modified files in the current git diff, excluded 2 third-party headers, and applied formatting fixes to the detected changes.
C++ Quality Report (Incremental)
| File Path | Check Type | Status | Action Taken |
|---|---|---|---|
src/network/session.cpp | clang-format | Fixed | Realigned pointers to right-side; fixed line length. |
src/network/session.cpp | clang-tidy | Warning | bugprone-unhandled-self-assignment detected in operator=. |
include/core/buffer.h | clang-format | Fixed | Adjusted indentation for nested namespace. |
src/main.cpp | clang-tidy | Passed | No issues found in modified lines. |
third_party/json.hpp | Skip | Ignored | File matches pattern in .clang-format-ignore. |
Next steps
- Review the
bugprone-unhandled-self-assignmentwarning insession.cppas it requires manual logic verification. - Run a full scan using
./scripts/run_check.sh --mode=allif you want to verify the entire module. - Commit the formatting changes applied by the
--fixflag.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual C++ code reviews are slow, inconsistent, and often derail projects with noise from legacy code or third-party libraries. This skill automates the entire quality pipeline, providing environment verification, configuration scaffolding, and intelligent static analysis that distinguishes between fresh code and technical debt.
What it does
- Environment Verification checks for local installations of clang-format, clang-tidy, and cppcheck, providing specific installation commands for missing dependencies.
- Config Initialization generates standardized
.clang-formatand.clang-tidyfiles based on Google C++ style with 120-character column limits. - Incremental Analysis targets only modified lines in a
git diffto prevent legacy warnings from cluttering new development. - Noise Suppression automatically excludes
build/,third_party/, andvendor/directories from scans and formatting tasks. - Automated Remediation applies style fixes and safe static analysis corrections directly to the source files when requested.
How it works
- Pre-flight Check uses
env_check.shto ensure the local toolchain is ready. - Project Scaffolding runs
init_config.shto populate the root directory with performance-focused linting rules. - Execution Choice triggers
run_check.shwith--mode=difffor PR-ready incremental checks or--mode=allfor full project audits.
Frameworks & tools
This skill utilizes clang-format, clang-tidy, cppcheck, and cmake. It is optimized for C++ projects managed via git.
Why this beats prompting it yourself
Writing prompts to review C++ often results in generic advice or hallucinated syntax. This tool executes industry-standard binaries with strict, battle-tested configuration files, ensuring zero-latency formatting and verifiable static analysis results.
Use cases
- Initialize a new C++ project with modern linting and Google-style formatting.
- Perform a "clean-only" check on new commits within a large legacy codebase.
- Bulk-fix formatting issues across an entire repository without touching third-party code.
Known limitations
Requires a local installation of Clang tools. Performance depends on the presence of a compile_commands.json for complex C++ projects.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Requires local Clang toolchain (clang-format, clang-tidy). Effective static analysis often needs a compile_commands.json generated by CMake.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 13 days ago
- Free with an Agensi account
- Software
Git