smj-edison
smj-edison/zicl
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/smj-edison/zicl --skill proofread-comments命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Scan file(s) for repeated code patterns and suggest functions to encapsulate them
Scan utility files for public helper functions and update .claude/helpers.md so future sessions know about them
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR, or read/interpret a crit review JSON file. Covers crit comment, crit share, crit unpublish, crit pull, crit push, review file format, and resolution workflow. Not for invoking an interactive review loop — that's the `crit` skill.
基于 SOC 职业分类
正在显示 SKILL.md
| name | proofread-comments |
| description | Proofread comments in the given file(s) against the Style guide in CLAUDE.md |
| argument-hint | <file or glob> |
Read CLAUDE.md and extract the "Style guide" section. Then read $ARGUMENTS and proofread every comment against those rules. For each violation, show the file and line number, quote the offending comment, explain which rule it breaks, and suggest a corrected version. Do not flag comments that are already correct.