From neo-skills
Analyzes git diffs or code files for security vulnerabilities, performance issues, logic bugs, style violations, and improvements in TypeScript, Python, C#, React. Outputs structured Traditional Chinese reports.
How this skill is triggered — by the user, by Claude, or both
Slash command
/neo-skills:neo-code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. **Input Handling**:
Input Handling:
git diff HEAD to retrieve all staged and unstaged changes.git diff returns empty, inform the user: "No changes detected." and stop.Scope Identification:
Context Gathering:
tsconfig.json, .eslintrc, security policies) if available in the provided context.Evaluate the code against the following dimensions:
Correctness & Logic:
Security (Critical):
Performance:
Maintainability & Readability:
Style & Standards:
Generate a structured Code Review Report in Traditional Chinese (Taiwan) with the following sections:
🔍 審查摘要 (Summary):
🔴 嚴重問題 (Critical Issues):
🟡 改進建議 (Suggestions):
🟢 優秀之處 (Praise) (Optional):
❓ 疑問 (Questions) (Optional):
Style Guidelines for the Report:
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub benknightdark/neo-skills --plugin neo-skills