Token导航 LogoToken导航

Agent Skill · 研究检索

seo-backlinks(SEO backlinks 搜索)

seo-backlinks 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

seo-backlinks 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,674 个 Skill 里排第 66,285。

总安装 267周安装 11GitHub Stars 28下载 87核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:seo-backlinks(SEO backlinks 搜索)
来源仓库:https://github.com/mangollc/claude-seo-skill
仓库路径:skills/seo-backlinks
安装命令:
npx skills add https://github.com/mangollc/claude-seo-skill --skill seo-backlinks
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/mangollc/claude-seo-skill --skill seo-backlinks

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于需要根据关键词或任务场景进行信息检索的场景,如 SEO 外链查询。通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和是否触发联网操作。

建议结合原始 README 核验具体用法,注意检查维护状态和潜在的文件读写行为。安装前应评估是否需要执行外部命令或访问敏感数据,避免误改生产环境。

来源仓库内路径:skills/seo-backlinks

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/mangollc/claude-seo-skill --skill seo-backlink…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

seo-backlinks 怎么安装?

在终端执行 npx skills add https://github.com/mangollc/claude-seo-skill --skill seo-backlinks。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

seo-backlinks 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

seo-backlinks 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

seo-backlinks 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

seo-backlinks 用的人多吗?

公开数据是累计安装 267 次,近一周安装 11 次,下载 87 次,GitHub 28 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

seo-backlinks 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
seo-backlinks

SEO backlinks 搜索 · 本页

26728需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Backlinks & Reporting

Load client context first. See seo-keywords rules/client-setup.md.

File Organization

backlinks/
├── competitor-profiles/
│   └── {competitor-slug}.json     # Per-competitor backlink data
├── opportunities.json             # Scored link opportunities
├── outreach-plan-{date}.json      # 90-day outreach plan
├── toxic-links.json               # Toxic backlink report
├── unlinked-mentions.json         # Brand mentions without links
└── disavow.txt                    # Google disavow file format

reports/
├── monthly-{year}-{month}.md      # Monthly SEO reports
└── quarterly-{year}-q{n}.md       # Quarterly summaries

Competitor Backlink Profiling

For each competitor in client config, discover their link sources:

# Find pages linking to competitor
firecrawl search "link:{competitor-domain}" --limit 50 -o .seo/clients/{slug}/backlinks/.firecrawl/links-{comp}.json --json &

# Find brand mentions (potential link sources)
firecrawl search "\"{competitor-name}\" -{competitor-domain}" --limit 30 -o .seo/clients/{slug}/backlinks/.firecrawl/mentions-{comp}.json --json &

# Find guest posts by competitor
firecrawl search "\"{competitor-name}\" guest post OR contributed by OR written by" --limit 20 -o .seo/clients/{slug}/backlinks/.firecrawl/guest-{comp}.json --json &

wait

For each discovered link source, analyze:

  • Source domain and page
  • Link context: editorial mention, directory listing, guest post, resource page, forum, comment
  • Anchor text used
  • Follow vs nofollow
  • Topical relevance to client's industry
  • Domain signals: established site vs thin/spammy

Output Format

{
  "competitor": "Competitor Name",
  "domain": "competitor.com",
  "link_sources": [
    {
      "source_url": "https://referring-site.com/article",
      "source_domain": "referring-site.com",
      "link_type": "editorial|guest-post|directory|resource-page|forum|comment|partnership",
      "anchor_text": "anchor text used",
      "follow": true,
      "relevance": "high|medium|low",
      "replicable": true,
      "notes": "Blog post about industry topic, could pitch similar content"
    }
  ],
  "summary": {
    "total_sources_found": 45,
    "editorial_links": 20,
    "guest_posts": 8,
    "directories": 10,
    "resource_pages": 5,
    "other": 2
  }
}

Link Opportunity Scoring

Score each prospect on a 0-100 scale across 4 dimensions:

DimensionWeightCriteria
Relevance25 ptsIndustry match, topical alignment, audience overlap
Authority25 ptsDomain reputation, traffic indicators, content quality
Achievability25 ptsAccepts guest posts? Has resource pages? Responded to outreach before? Open contact info?
Traffic Potential25 ptsReferral traffic value, audience size, social engagement

Priority tiers:

  • Tier 1 (75-100): Pursue immediately — high relevance + achievable
  • Tier 2 (50-74): Include in outreach plan — good potential
  • Tier 3 (25-49): Secondary targets — nice to have
  • Tier 4 (0-24): Skip — low value or unachievable

90-Day Outreach Plan

Phase 1: Low-Hanging Fruit (Days 1-30)

Targets:

  • Directories and listings the client is missing but competitors have
  • Unlinked brand mentions (found via mention search — just need to ask for a link)
  • Broken link opportunities: find 404 links on resource pages, offer client content as replacement
  • Industry associations and chamber of commerce listings
  • Existing relationships (partners, vendors, clients who could link)

Actions:

  • Submit to 10-15 relevant directories
  • Send personalized outreach to 10 unlinked mention sites
  • Find 5-10 broken link opportunities
  • Claim all relevant association listings

Phase 2: Content-Based Link Building (Days 31-60)

Targets:

  • Guest post opportunities on industry blogs
  • Resource page inclusion (sites with "resources" or "useful links" pages)
  • HARO / journalist queries (Help a Reporter Out)
  • Podcast guest appearances
  • Expert roundup participation

Actions:

  • Pitch 15-20 guest post targets (send personalized pitch with topic ideas)
  • Submit client content to 10 resource pages
  • Sign up for HARO and respond to 2-3 relevant queries per week
  • Identify 5 industry podcasts accepting guests

Phase 3: Digital PR & Partnerships (Days 61-90)

Targets:

  • Data-driven content / original research that earns links naturally
  • Infographics and visual assets for link bait
  • Strategic partnerships with complementary businesses
  • Local sponsorships and community involvement
  • Industry award submissions

Actions:

  • Create 1-2 pieces of link-worthy content (data study, tool, comprehensive guide)
  • Develop 2-3 partnership link exchanges with complementary businesses
  • Submit to 5 industry award programs
  • Sponsor or participate in 2 local/industry events

Outreach Email Templates

Guest Post Pitch:

Subject: Content idea for {site_name}: {topic}

Hi {editor_name},

I noticed {site_name} covers {topic area} and thought your readers might enjoy an article on {specific topic idea}.

I'm {author_name}, {brief credential}. I'd cover:
- {Point 1}
- {Point 2}
- {Point 3}

I'll make sure the piece is original, well-researched, and a great fit for your audience. Would this be of interest?

{name}
{title}, {company}

Unlinked Mention:

Subject: Thanks for mentioning {brand}!

Hi {name},

I noticed you mentioned {brand} in your article "{article title}" — thank you!

Would you mind adding a quick link to {url} where you reference us? It helps our readers find us and would be a nice complement to your article.

Thanks!
{name}

Broken Link:

Subject: Broken link on {page title}

Hi {name},

I was reading your helpful resource page "{page title}" and noticed the link to {broken resource} appears to be broken (returns a 404).

We have a similar resource at {client url} that covers the same topic. Would you consider updating the link?

{name}

Toxic Backlink Identification

Search for links that could harm the client:

firecrawl search "link:{client-domain}" --limit 100 -o .seo/clients/{slug}/backlinks/.firecrawl/all-links.json --json

Toxic link patterns to flag:

  • PBN characteristics: thin content, generic design, excessive outbound links, exact-match anchor domains
  • Spammy directories: low-quality directories with no editorial standards
  • Irrelevant foreign-language sites linking with keyword anchor text
  • Comment spam: links from blog comments or forums
  • Link farms: sites that exist solely to sell/exchange links
  • Excessive exact-match anchors: unnatural anchor text profile

Disavow File Format

# Toxic backlinks identified on {date}
# Client: {client_name}
# Domain: {client_domain}

# Individual URLs
https://spammy-site.com/page-with-link
https://another-spam.com/article

# Entire domains
domain:spam-domain.com
domain:link-farm.net

Unlinked Mention Discovery

Find brand mentions without links:

# Search for brand mentions excluding own site
firecrawl search "\"{brand_name}\" -{client-domain}" --limit 50 -o .seo/clients/{slug}/backlinks/.firecrawl/brand-mentions.json --json

# Also search for common misspellings or variations
firecrawl search "\"{brand_variation}\" -{client-domain}" --limit 20 -o .seo/clients/{slug}/backlinks/.firecrawl/brand-variations.json --json

For each mention, scrape the page to verify:

  1. The mention exists and is relevant
  2. No link to client domain already exists
  3. The context is positive or neutral (not a complaint)
  4. The site is worth pursuing (not spammy)

Monthly Reporting Framework

Generate a reusable monthly report covering all SEO activities and results.

Report Template Structure

# Monthly SEO Report — {Month} {Year}
## {Client Name} | {Domain}

Prepared by {Agency Name} | {Date}

---

## Executive Summary
{2-3 sentences: key wins, changes in performance, top priority for next month}

## Technical Health
- Overall Score: {score}/100 (vs {previous_score}/100 last month)
- Issues Fixed: {count}
- New Issues Found: {count}
- Top remaining issue: {description}

## Keyword Performance
- Total keywords tracked: {count}
- Keywords in top 10: {count} ({change} vs last month)
- Keywords in top 3: {count} ({change} vs last month)
- New keyword opportunities identified: {count}
- Top keyword wins: {list top 3 improvements}

## Content
- New pages published: {count}
- Pages optimized/refreshed: {count}
- Average on-page score: {score}/100
- Content gaps remaining: {count}

## Local SEO (if applicable)
- GBP posts published: {count}
- GBP views: {metric if available}
- New reviews: {count} (avg rating: {stars})
- Citations updated: {count}

## Backlinks
- New links acquired: {count}
- Links lost: {count}
- Outreach emails sent: {count}
- Response rate: {percent}
- Top new links: {list top 3}

## AI Search Visibility (AEO)
- AI Overview appearances: {observed/not observed}
- Brand mentions in AI results: {count}
- Schema markup coverage: {percent of pages}

## Priorities for Next Month
1. {Priority 1}
2. {Priority 2}
3. {Priority 3}

---

## Appendix: Detailed Data
{Link to JSON data files in .seo/ directory}

Report Generation Steps

  1. Load all data from .seo/clients/{slug}/ subdirectories
  2. Compare against previous month's data (if available)
  3. Calculate trends and changes
  4. Highlight wins and regressions
  5. Generate action items for next month
  6. Save to .seo/clients/{slug}/reports/monthly-{year}-{month}.md

平台分布

Codex

38.02%
按下载量换算33

Claude

29.25%
按下载量换算25

Cursor

19.37%
按下载量换算17

Gemini CLI

9.78%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills