skill-reviewer

6.8

102

126

Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills), and auto-PR (fork, improve, submit). Use when checking skill quality, reviewing skill repositories, or contributing improvements to open-source skills.

code-review

6.8

Rating

Installs

AI & LLM

Quick Review

Excellent skill that addresses a clear need in the Claude Code ecosystem. The description is comprehensive with trigger conditions across three distinct modes. Task knowledge is strong with concrete workflows, validation commands, and templates in reference files. Structure is well-organized with mode separation and quick-reference tables. The 'Additive Only' principle and tone guidelines demonstrate sophisticated understanding of open-source collaboration. Novelty is good - while code review is common, the combination of self-review automation, external review guidelines, and auto-PR workflow with respect-driven constraints creates meaningful value beyond what a CLI agent could easily replicate. Minor improvement areas: could benefit from example outputs and the dependency auto-install pattern adds some complexity.