Review git diffs against coding standards and completeness criteria.
npx skills add https://github.com/ievo-ai/skills --skill deep-review-ievo-ai
Please help me install this Agent Skill. Skill: deep-review Source: https://github.com/ievo-ai/skills/tree/main/plugins/ievo/skills/deep-review Command: npx skills add https://github.com/ievo-ai/skills --skill deep-review-ievo-ai
This Skill provides a thorough code review of the diff before committing, catching issues missed by automated tools but discovered in human PR review.
Run the command /ievo:deep-review in your project directory to initiate a deep code review.
High-intent search queries and answers about installing and using this skill.
Review code diffs for commit safety by running a comprehensive 11-point code review that analyzes staged changes or working tree diffs to ensure compliance with predefined coding standards and completeness criteria before execution.
A deep code review is a structured 11-point analysis of a git diff that catches completeness, consistency, and correctness issues typically missed by automated tools but found in human PR review.
Yes, you need git CLI installed to generate diffs for the pre-commit review, which supports analyzing staged changes, the working tree, or a specified git range for error path analysis.
Yes, you can analyze error paths and code quality on a specific git commit range by providing the range to the review process, which then evaluates the diff against coding standards using Sonnet-level reasoning.
Get an unbiased code review of a refactor by spawning an independent deep-reviewer subagent, which provides context-independent analysis of the diff to verify correctness and completeness before you commit.
Use a structured code review instead of standard linters after a significant change or refactor, when you need Sonnet-level reasoning to evaluate compliance with predefined coding standards and uncover issues missed by automated tools.
aurabxGenerate Conventional Commits messages from working tree or staged diffs.
ollieb89Evaluate LLM outputs with automated metrics and LLM-as-Judge workflows.
R2W1csLint and validate JavaScript and Python code for syntax and style issues.
julianobarbosaAutomate Git commits with pre-commit security scans and Conventional Commits enforcement.
