Analyze local git diffs for logic flaws and rule violations.
npx skills add https://github.com/erclx/aitk --skill claude-review-erclx
Please help me install this Agent Skill. Skill: claude-review Source: https://github.com/erclx/aitk/tree/main/claude/skills/claude-review Command: npx skills add https://github.com/erclx/aitk --skill claude-review-erclx
This skill solves the issue of ephemeral, inconsistent code reviews by providing a structured, persistent, and context-aware analysis of local changes before they are shipped.
Run the claude-review skill to analyze the current branch changes against the project context and generate a findings report.
High-intent search queries and answers about installing and using this skill.
You can automate local code review by running the skill against your current branch changes. It analyzes local git diffs against project-specific documentation and coding standards to generate a structured, severity-graded findings report.
Context-aware static analysis for local git diffs evaluates uncommitted or staged changes by incorporating project-specific rules and architecture documents. This ensures findings align with project standards rather than subjective feedback.
To generate a severity-graded code review report for uncommitted changes, run the skill on your local branch. It produces a persistent report on disk that serves as a reliable receipt for your ship process.
Yes, automated code review requires git access and adherence to defined project context files. These inputs ensure the analysis provides high-signal, non-subjective feedback based on your specific coding standards.
You can review staged changes without committing them by running the skill on staged or uncommitted modifications. It operates on these local git diffs to identify logic flaws and rule violations before they are shipped.
Automated static analysis should be used when you finish a feature branch and need to ensure changes comply with project rules. It avoids the need for manual, repetitive checklist reviews by providing a structured, persistent report.
ZoimbackCreate and edit the .github/copilot-instructions.md file for repository-wide GitHub Copilot standards.
DieStokOrchestrate multi-agent code review workflows and aggregate findings into merge-ready reports.
julianobarbosaReview code for quality, bugs, security issues, and best practices using Codex.
webdevtodayjasonReview code quality with static analysis and security scans before commits.
