Agent Skills › MiniMax-AI/skills › pr-review

pr-review

GitHub

用于审查 MiniMax Skills 仓库的拉取请求，通过运行自动化验证脚本检查结构合规性，并依据质量指南进行人工内容审核，确保技能提交符合规范。

.claude/skills/pr-review/SKILL.md MiniMax-AI/skills

触发场景

PR review pull request validate skill check skill

安装

npx skills add MiniMax-AI/skills --skill pr-review -g -y

更多选项

非标准路径

npx skills add https://github.com/MiniMax-AI/skills/tree/main/.claude/skills/pr-review -g -y

不安装直接使用

npx skills use MiniMax-AI/skills@pr-review

指定 Agent (Claude Code)

npx skills add MiniMax-AI/skills --skill pr-review -a claude-code -g -y

安装 repo 全部 skill

npx skills add MiniMax-AI/skills --all -g -y

预览 repo 内 skill

npx skills add MiniMax-AI/skills --list

SKILL.md

Frontmatter

{
    "name": "pr-review",
    "license": "MIT",
    "metadata": {
        "version": "1.0",
        "category": "tooling"
    },
    "description": "Review pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or checking existing skills for compliance. Run the validation script first for hard checks, then apply quality guidelines for content review. Triggers: PR review, pull request, validate skill, check skill.\n"
}

PR Review Skill

Review pull requests against repository standards. Two-phase process: automated validation, then manual content review.

Phase 1: Automated Validation (Hard Rules)

Run the validation script to check structural requirements:

python .claude/skills/pr-review/scripts/validate_skills.py

The script checks:

SKILL.md exists in every skill directory
YAML frontmatter is parseable
Required fields present: name, description
name matches directory name
No hardcoded secrets detected

All ERROR-level checks must pass. WARNING-level items (missing license, metadata) should be flagged but are not blockers.

See references/structure-rules.md for the complete hard rules specification.

Phase 2: Content Review (Soft Guidelines)

After automated checks pass, review the PR against quality guidelines:

Skill scope — Does it overlap with existing skills? Is the boundary clear?
Description quality — Does the description include clear trigger conditions?
File size — Are reference docs reasonably sized for context window consumption?
API key handling — If external APIs are used, are credentials read from environment variables?
Script quality — Do scripts have shebang, requirements.txt, and error handling?
Language — Are SKILL.md and code written in English?
README sync — Are README.md and README_zh.md updated for new skills?