一键导入
backlink-analyzer
Use when analyzing backlink profiles, link authority, toxic links, link-building opportunities, or competitor link gaps. 外链分析/反向链接
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when analyzing backlink profiles, link authority, toxic links, link-building opportunities, or competitor link gaps. 外链分析/反向链接
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no p
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
Audit Flowser context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.
Audit active Flowser plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.
Audit agent harness health: Claude/Codex agent parity, skill registry consistency, README.md sync, and protocol file wiring. Use when agents, skills, README.md, or development-protocol files move, split, or drift.
Autonomous iterative optimization loop for measurable metrics like coverage, performance, or bundle size. Use when repeated experiments can be judged by a mechanical score.
| name | backlink-analyzer |
| description | Use when analyzing backlink profiles, link authority, toxic links, link-building opportunities, or competitor link gaps. 外链分析/反向链接 |
| version | 9.9.9 |
| license | Apache-2.0 |
| compatibility | Claude Code, skills.sh, ClawHub, Vercel Labs, Cursor, Windsurf, Codex CLI, Amp, Gemini CLI, Kimi Code, Qwen Code, CodeBuddy |
| homepage | https://github.com/aaron-he-zhu/seo-geo-claude-skills |
| when_to_use | Use when analyzing backlink profiles, link quality, toxic links, referring domains, or anchor text distribution. |
| argument-hint | <domain or URL> |
| metadata | {"author":"aaron-he-zhu","version":"9.9.9","geo-relevance":"low","tags":["seo","backlinks","link-building","link-profile","toxic-links","off-page-seo","link-audit","referring-domains","disavow","ahrefs-alternative","外链分析","被リンク","백링크","backlinks-seo"],"triggers":["analyze backlinks","check link profile","find toxic links","link building opportunities","backlink audit","who links to me","I have spammy links","how do I get more backlinks","disavow links","how to build backlinks","外链分析","反向链接","有毒链接","链接建设","外链怎么做","有垃圾外链","谁链接到我","友链","互换友链","外链建设","被リンク分析","バックリンク","リンク構築","백링크 분석","링크 빌딩","누가 내 사이트 링크해?","백링크 어떻게 늘려?","análisis de backlinks","enlaces entrantes","análise de backlinks"]} |
Analyzes backlink profiles for quality, risk, competitive gaps, and link-building opportunities.
Analyze backlink profile for [domain]
Find link building opportunities by analyzing [competitor domains]
Expected output: a backlink report or delta summary plus the standard handoff summary for memory/monitoring/.
memory/open-loops.md.Emit the standard shape from skill-contract.md §Handoff Summary Format.
All integrations optional (see CONNECTORS.md). With tools, pull backlink profiles from ~~link database and competitor data from ~~SEO tool. Without tools, ask for backlink CSVs, referring domains, competitor domains, and link changes. Respect robots.txt and TOS per SECURITY.md.
When a user requests backlink analysis:
Reference: See references/analysis-templates.md for the compact output templates used in all seven steps.
When running domain-authority-auditor after this analysis, the following data feeds directly into CITE scoring:
| Backlink Metric | CITE Item | Dimension |
|---|---|---|
| Referring domains count | C01 (Referring Domain Volume) | Citation |
| Authority distribution (DA breakdown) | C02 (Referring Domains Quality) | Citation |
| Link velocity | C04 (Link Velocity) | Citation |
| Geographic distribution | C10 (Link Source Diversity) | Citation |
| Dofollow/Nofollow ratio | T02 (Dofollow Ratio Normality) | Trust |
| Toxic link analysis | T01 (Link Profile Naturalness), T03 (Link-Traffic Coherence) | Trust |
| Competitive link intersection | T05 (Profile Uniqueness) | Trust |
Sample outcome: a link-intersection table, top immediate opportunities, and an estimated impact model. Keep the full structure in references/analysis-templates.md.
Prioritize quality, monitor regularly, diversify anchors and link types, and disavow cautiously.
Reference: See references/link-quality-rubric.md for the scoring matrix, toxic-link criteria, benchmarks, and disavow guidance.
Reference: See references/outreach-templates.md for outreach frameworks, subject lines, response benchmarks, follow-up sequences, and templates.
Ask "Save these results?" If yes, write memory/monitoring/YYYY-MM-DD-<topic>.md with headline finding, actions, and open loops. If toxic ratio exceeds 15%, recommend domain-authority-auditor.
Toxic ratio > 15% → domain-authority-auditor. Otherwise → Terminal. Visited-set rule applies per skill-contract.md.