frontend-performance-audit
分析前端页面性能并输出结构化优化报告。适用于页面速度慢、lighthouse 指标差、core web vitals 不达标、首屏慢、交互卡顿、bundle 过大、阻塞渲染资源过多等场景。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/cnoder-wgh/frontend-performance-audit前端性能优化
当用户提供页面地址、构建配置或前端项目文件,并希望分析性能问题、输出优化建议时,使用本技能。
执行流程
- 先识别已有输入:
- 页面 URL
- Lighthouse 指标
- Network 瀑布图
- Bundle 分析
- 技术栈信息
- 读取
references/metrics.md,确定必须输出的性能指标。 - 读取
references/diagnosis-rules.md,根据症状匹配原因和建议。 - 按
references/report-template.md输出正式报告。
规则
- 有核心 Web 指标时,优先输出核心 Web 指标。
- 明确区分“已观测证据”和“推断结论”。
- 优先给出高收益、低改动成本的建议。
- 不要轻易建议重构,除非轻量优化不足以解决问题。
- 数据不完整时,要明确说明缺失项和结论置信度。
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-cnoder-wgh-frontend-performance-audit": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
openviking-context
OpenViking context database for AI agents — layered context loading (L0/L1/L2), semantic search, file-system memory management. Use when setting up OpenViking, managing agent memory/resources, performing semantic search, browsing context filesystem, or comparing token consumption. Triggers on: 'openviking', 'context database', 'viking memory', 'layered context', 'token saving', 'L0/L1/L2', 'viking://', 'memsearch', 'memread', 'context setup'.
save-all-resource
打开一个可见浏览器,让用户手动浏览目标网站,并在浏览过程中持续监听同域原始响应内容,实时落盘到本地桌面目录。
doc-diff
Compare two documents or files and generate a structured diff report. Use when: user asks to compare files, find differences between documents, generate diff report, or check what changed between two versions.