code-review

Audit a codebase for safety, determinism, and integrity issues with severity-ranked findings.

12|5|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/Clyra-AI/gait --skill code-review-clyra-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/Clyra-AI/gait/tree/main/.agents/skills/code-review
Command: npx skills add https://github.com/Clyra-AI/gait --skill code-review-clyra-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audit a codebase for safety, determinism, and integrity issues across the entire repository, producing ranked findings.

Core Features & Use Cases

  • Full-repo risk discovery and severity-ranked findings for production AI tool boundaries.
  • Contract-driven evaluation of safety, determinism, and docs/CLI correctness.
  • Produce structured, evidence-backed findings with remediation guidance for CI/CD.
  • Use cases include security reviews, incident retrospectives, and release-readiness checks.

Quick Start

Run a full repository risk review to generate a severity-ranked findings report for the Gait codebase.

Frequently Asked Questions about code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit a codebase for safety and determinism issues?

Run a full repository risk review to discover safety, determinism, and integrity issues across the codebase. The audit produces severity-ranked findings with evidence and remediation guidance aligned to baseline diagnostics.

Can I generate structured code review findings for CI/CD pipelines?

Yes, code review findings are structured with evidence, severity mapping, and remediation guidance designed for CI/CD integration. This supports security reviews, incident retrospectives, and release-readiness checks.

What does a full-repo risk review cover besides core subsystem code?

A full-repo risk review covers core subsystems, CLI behavior, documentation contracts, and testing workflows. It evaluates both current and historical changes for safety, determinism, and correctness.

How do I assess release readiness for production AI tool boundaries?

Perform a contract-driven evaluation of safety, determinism, and documentation correctness across the repository. This generates ranked, evidence-backed findings that map severity and guide remediation for production boundaries.

Does the code review skill require any external dependencies to run?

No external dependencies are required. The skill operates independently to audit the codebase and produce structured findings with severity mapping and remediation guidance.

When should I use a full-repo risk review instead of a targeted security scan?

Use a full-repo risk review when you need comprehensive coverage of determinism, safety, and integrity across subsystems, CLI, docs, and testing workflows, rather than isolated vulnerability scanning.