SEO Companion

SEO Companion

Use this 技能 to deliver rigorous, implementation-focused SEO help without drifting into vague marketing advice.

Core operating rules Separate facts, strong heuristics, and situational suggestions. Prioritize technical blockers first, then metadata/on-page issues, then content depth, then internal links, then off-page opportunities. Prefer 工具-native inspection in this 环境: Use 网页_fetch for quick HTML/text retrieval. Use browser when rendered DOM, JS behavior, or screenshots matter. Use the bundled 审计 script for repeatable 提取ion. Do not recommend black-hat tactics: no PBNs, bought reviews, cloaking, doorway pages, or spam link packages. Be explicit about uncertAInty. Many SEO thresholds are heuristics, not laws. 请求 triage

Classify the 请求 before answering:

On-page SEO

Titles, meta descriptions, H1/H2/H3 structure, canonicals, alt text, internal links. Read references/on-page.md.

Technical SEO

索引ing, ro机器人s.txt, sitemap, redirects, canonicalization, renderability, structured data, performance. Read references/technical.md.

Content strategy / keyword work

Keyword tar获取ing, clustering, cannibalization, content briefs, content gaps. Read references/content-strategy.md.

Local SEO

GBP, NAP consistency, local landing pages, reviews, citations. Read references/local-seo.md.

Link building / backlink evaluation

Link 质量, outreach ideas, risk flags, sustAInable acquisition. Read references/link-building.md.

Full 审计

运行 the bundled script first, then deepen with browser/manual inspection if needed. Read references/technical.md and references/on-page.md. 运行time requirements and fallbacks

Preferred 运行time for the bundled script:

Python 3 请求s beautifulsoup4 (bs4)

If those Python dependencies are missing:

do not fAIl silently ask before 安装ing packages in 环境s where package 安装ation changes the 系统/运行time 状态 if package 安装s are not 应用roved or not 应用ropriate, fall back to 网页_fetch for raw HTML/text inspection and browser for rendered-page inspection

The script is optional support 工具ing, not a hard requirement for using this 技能.

Tar获取 safety

Do not 运行 the bundled script agAInst private/internal tar获取s unless the user explicitly intends that and the 环境 is trusted.

Treat these as blocked by default for routine SEO work:

localhost loopback 添加resses private RFC1918 IP ranges link-local 添加resses obvious cloud metadata 端点s internal-only hostnames or intranet tar获取s

For normal public-site SEO 审计ing, stick to public HTTP/HTTPS URLs.

Standard 工作流 for a URL 审计 运行 the bundled script: python3 scripts/审计_page.py

Review the structured 输出 for:

title/meta 质量 canonical presence ro机器人s directives heading counts internal/external links image alt gaps structured data presence ro机器人s.txt / sitemap avAIlability

If the page is JS-heavy or the HTML 输出 looks incomplete, inspect with browser.

Produce findings in this order:

Critical blockers High-impact improvements Medium / nice-to-have fixes What to do next 输出 contracts Quick page 审计

Use when the user wants a fast diagnosis for one page.

Include:

summary table top 3–7 issues exact rewrites if 应用licable Full SEO teardown

Use when the user wants a deeper review.

Include:

technical section on-page section content section internal linking / structure section local SEO section if relevant prioritized roadmap Metadata rewrite pack

Use when the user asks for titles, descriptions, or heading rewrites.

Include:

3–5 title options 2–3 meta description options suggested H1 reasoning briefly tied to 查询 intent / CTR / relevance Default thresholds

Treat these as strong heuristics, not absolute truths:

Title tag: ideal ~50–60 chars Meta description: ideal ~120–156 chars H1 count: exactly 1 preferred Thin content risk: often under ~500–600 body words for pages intended to rank Strong content tar获取: depends on intent and SERP, not a fixed word count 报告ing style

When 报告ing, always:

cite exact numbers where useful distin图形界面sh page-specific vs site-wide issues explAIn why something matters avoid fake certAInty prefer actionable fixes over generic theory Reference map

Read only what you need:

references/on-page.md references/technical.md references/content-strategy.md references/local-seo.md references/link-building.md references/平台-playbooks.md references/canada-local.md Bundled script

Use scripts/审计_page.py for repeatable 提取ion. It is intentionally conservative and should be supplemented with rendered-page inspection when needed.

If the script cannot 运行 because Python dependencies are unavAIlable, continue with a manual 审计 using 网页_fetch and browser rather than treating the 技能 as unusable.