audit-speed 是做什么的？
深度核心网站指标和页面速度审计。当用户询问页面速度、核心网站指标、LCP、CLS、INP、FCP、TTFB、Lighthouse 分数、页面为何缓慢、性能优化或资源大小分析时使用。对于更广泛的技术 SEO 问题，请参阅 diagnose-seo。
深度核心网站指标和页面速度审计。当用户询问页面速度、核心网站指标、LCP、CLS、INP、FCP、TTFB、Lighthouse 分数、页面为何缓慢、性能优化或资源大小分析时使用。对于更广泛的技术 SEO 问题，请参阅 diagnose-seo。
这是一个深度核心网站指标和页面速度审计技能，旨在帮助开发者和AI代理用户快速诊断和优化网页性能。它专注于 Core Web Vitals（包括 LCP、CLS、INP、FCP、TTFB）以及 Lighthouse 评分，能分析页面为何加载缓慢、评估资源大小并提供性能优化建议。该技能适用于多种平台（如 Claude Code、Cursor、Codex 等），通过详细审计和具体建议帮助用户提升网站用户体验和搜索引擎排名。它通过模拟用户请求、分析网络性能数据、检查渲染路径和资源加载策略，最后生成可操作的优化方案。对于更广泛的技术 SEO 问题，该技能会引导用户参考 diagnose-seo 工具。
npx skills add https://github.com/calm-north/seojuice-skills/tree/main/skills/audit-speedInstalled? Explore more 研究与数据分析 skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →
深度核心网站指标和页面速度审计。当用户询问页面速度、核心网站指标、LCP、CLS、INP、FCP、TTFB、Lighthouse 分数、页面为何缓慢、性能优化或资源大小分析时使用。对于更广泛的技术 SEO 问题，请参阅 diagnose-seo。
This repo contains 13 individual skills — each has its own dedicated page.
Run a comprehensive SEO audit on a website covering technical health, on-page optimization, content quality, and backlink profile. Use when the user asks for an SEO audit, site review, SEO health check, "what's wrong with my SEO", website analysis, or a full diagnostic of their site's search performance. For speed-specific issues, see audit-speed. For technical crawl/index issues only, see diagnose-seo.
Turn competitor SEO data into a prioritized attack plan. Use when the user asks about competitor analysis, competitive gaps, how to outrank competitors, what competitors rank for, keyword overlap, or competitive positioning strategy. For building content to fill gaps, see brief and build-clusters.
Produce an editor-ready content brief for a target keyword or topic. Use when the user asks for a content brief, writing guidelines, article outline, SEO brief, what to include in a blog post, or how to structure content for a keyword. For choosing which topics to write about, see find-keywords. For a full site-wide SEO audit, see audit.
Build a topical authority cluster from a seed keyword or topic. Use when the user asks about topic clusters, content silos, pillar pages, topical authority, content architecture, or how to structure content around a theme. For finding the right keywords, see find-keywords. For writing individual pieces, see brief.
Design a link building campaign with prospect identification, asset creation, and outreach strategy. Use when the user asks about link building, backlinks, domain authority, how to get backlinks, outreach campaigns, digital PR, guest posting, or link acquisition. For internal linking, see fix-linking.
Structured diagnostic for technical SEO problems. Use when the user asks about crawl issues, indexation problems, why pages aren't being indexed, robots.txt questions, canonical errors, sitemap issues, rendering problems, or general technical SEO troubleshooting. For Core Web Vitals and page speed, see audit-speed.
Build a prioritized keyword list for a website, topic, or campaign. Use when the user asks about keyword research, finding keywords to target, building a keyword list, search demand, keyword difficulty, intent mapping, or which keywords to prioritize. For writing content around keywords, see brief. For grouping keywords into clusters, see build-clusters.
Design or audit internal link structure for a website. Use when the user asks about internal linking, link architecture, orphan pages, PageRank flow, anchor text, site structure, silo architecture, or why pages aren't ranking despite good content. For external link building, see build-links.
Guide a website migration without losing rankings — domain moves, CMS switches, URL restructures, HTTP to HTTPS, or redesigns. Use when the user asks about site migration, domain change, CMS migration, URL restructure, redesign SEO impact, redirect mapping, or how to move a site safely.
Optimize content for AI search engines — ChatGPT, Perplexity, Claude, Gemini, Google AI Overviews. Use when the user asks about AI SEO, AISO, getting cited by AI, appearing in AI answers, answer engine optimization, AEO, GEO, LLMO, AI Overviews, zero-click search, or how to appear in ChatGPT/Perplexity results. For traditional SEO, see diagnose-seo.
Build a local SEO strategy covering Google Business Profile, local citations, reviews, and NAP consistency. Use when the user asks about local SEO, Google Business Profile, Google Maps ranking, local pack, NAP consistency, local citations, review strategy, or ranking for "[service] near me" searches.
Diagnose and reverse traffic loss on existing pages. Use when the user asks about content decay, pages losing traffic, declining rankings, traffic drops, why a page stopped ranking, content refresh strategy, or when to consolidate vs redirect old content. For creating new content, see brief.
Identify and capture SERP features for target keywords — featured snippets, People Also Ask boxes, knowledge panels, and rich results. Use when the user asks about featured snippets, position zero, PAA optimization, rich results, schema markup for SERP features, or how to get more SERP real estate.
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agent skill repository discovered by 10x-chat research.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.