> 发布前质量关卡:合规风险检测(敏感词、绝对化用语、平台规则) + 产物质量审核(完整性、可读性、平台适配度)。一次检查,两道把关。 当用户说"检查合规"、"质量检查"、"能不能发"、"有没有敏感词"、 "审核一下"、"发布前检查"、"质量够不够"时使用。 合并了原 skill-check-compliance 和 skill-review-deliverable 的能力。
npx skills add https://github.com/ZJU-REAL/Easel --skill skill-quality-gate
> 一个 SKILL 完成两道把关:合规风险检测 + 产物质量审核。
用户提供待检查内容:文本、图片路径、视频路径、或混合。
可选:目标发布平台。
{
"overall_verdict": "✅ 可发布 | ⚠️ 需修改 | ❌ 不达标",
"platform": "平台名或 generic",
"compliance": {
"risk_level": "low|medium|high",
"issues": [{ "type": "", "severity": "", "text": "", "reason": "", "suggestion": "" }],
"passed_checks": []
},
"quality": {
"score": "✅|⚠️|❌",
"dimensions": [{ "name": "", "score": "", "note": "" }]
},
"top_fixes": ["修改建议1", "修改建议2", "修改建议3"]
}
references/general-rules.mdreferences/platform-xiaohongshu.mdreferences/platform-douyin.mdreferences/platform-bilibili.mdreferences/review-dimensions.mdreferences/review-levels.mdreferences/rework-rules.md 给出返工指引Take zju-real/skill-quality-gate from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.