Token导航 LogoToken导航

Agent Skill · 研究检索

recover-content(恢复内容)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

recover-content 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,权限为执行命令;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 3,905。

总安装 38,339周安装 1,568GitHub Stars 7下载 12,989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:recover-content(恢复内容)
来源仓库:https://github.com/calm-north/seojuice-skills
仓库路径:skills/recover-content
安装命令:
npx skills add https://github.com/calm-north/seojuice-skills --skill recover-content
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/calm-north/seojuice-skills --skill recover-content

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。

使用衰减分类框架诊断并扭转现有页面上的流量丢失。

五个加权信号(流量下降、排名下降、点击率下降、内容新鲜度、竞争性替代)的综合衰减评分优先考虑哪些页面最需要采取行动 决策树根据主题相关性、意图转变和内容陈旧程度指导是否刷新、合并、重定向或废弃每个衰退页面 更新根据内容类型(博客文章、操作指南、数据综述)定制的手册,其中包含每种恢复方法的具体清单和时间估计 优先级矩阵根据流量价值、衰退严重程度、竞争机会以及首先将恢复工作集中在影响最大的页面上的努力对页面进行排名

来源仓库内路径:skills/recover-content

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/calm-north/seojuice-skills --skill recover-con…;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

    它需要执行命令,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

recover-content 怎么安装?

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

recover-content 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。

recover-content 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/calm-north/seojuice-skills --skill recover-content 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

recover-content 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。

recover-content 用的人多吗?

公开数据是累计安装 38,339 次,近一周安装 1,568 次,下载 12,989 次,GitHub 7 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。

recover-content 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 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

  • 不能接受 Skill 在你机器上执行命令的人。
  • 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
recover-content

恢复内容 · 本页

38,3397执行命令未明确通过

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

Recover Content

Diagnose and reverse traffic loss on existing pages using the decay triage framework: refresh, consolidate, redirect, or retire.

Before You Start

Gather this context (ask if not provided):

  1. Which pages are losing traffic? Specific URLs or a general "the whole blog is declining."
  2. How much traffic was lost? Percentage drop or absolute numbers.
  3. Over what timeframe? Gradual decline over months vs sudden drop.
  4. Any recent changes? Site redesign, CMS migration, content edits, algorithm update timing.

If the user doesn't know which pages are declining, suggest checking Google Search Console → Performance → Pages, sorted by click change over the last 6 months.

Identifying Decay

Content decay happens when a page gradually loses search traffic over time. Common signals:

  • Clicks declining month-over-month for 3+ months
  • Position slipping from page 1 to page 2+
  • Impressions stable but CTR dropping (competitors have better titles/snippets)
  • Impressions declining (Google no longer considers the page relevant)

Composite Decay Score

Score each page across 5 weighted signals to prioritize action:

SignalWeightHow to Score (0-100)
Traffic decline30%0 = no decline, 50 = 20-40% drop, 100 = >60% drop
Position drops25%0 = stable, 50 = lost 3-5 positions, 100 = dropped off page 1
CTR decline15%0 = stable, 50 = 20% decline, 100 = >40% decline
Content freshness15%0 = updated this quarter, 50 = 6-12 months stale, 100 = >2 years stale
Competitive displacement15%0 = no new competitors, 50 = new entrants on page 1, 100 = displaced from top 3
Composite Decay Score = (Traffic x 0.30) + (Position x 0.25) + (CTR x 0.15)
                      + (Freshness x 0.15) + (Displacement x 0.15)
ScoreStageResponse
0-20HealthyContinue monitoring
21-40Early decayAdd to refresh queue (next month)
41-60Active decaySchedule refresh this week
61-80Significant decayImmediate refresh or rewrite decision
81-100Terminal decayRewrite, redirect, or retire

Alert Priority Matrix

When multiple signals fire together, escalate:

Signal CombinationPriorityResponse Time
Traffic decline + Position dropP1 CriticalRefresh within 48 hours
Traffic decline + CTR declineP1 CriticalRewrite title/meta immediately
Position drop + Competitor displacementP2 HighRefresh within 1 week
CTR decline onlyP3 MediumRewrite title and meta this week
Freshness indicators onlyP3 MediumSchedule refresh within 2 weeks

The Decay Triage Framework

For each decaying page, apply this decision tree:

Decision 1: Is the topic still relevant?

  • Yes → proceed to Decision 2
  • No (product discontinued, event passed, technology obsolete) → Retire. 301 redirect to the closest relevant page or parent category.

Decision 2: Is there another page on the site targeting the same topic?

  • Yes → Consolidate. Merge the best content from both pages into one. 301 redirect the weaker page.
  • No → proceed to Decision 3

Decision 3: Has the search intent shifted?

Check what currently ranks for the target keyword. Has the SERP changed from:

  • Listicles → long-form guides?
  • Blog posts → product pages?
  • Text → video?
  • General → specific?
  • Yes, intent shifted → Rewrite. Rebuild the page to match current intent. Keep the URL.
  • No → proceed to Decision 4

Decision 4: Is the content simply outdated?

Check for: stale statistics, outdated screenshots, deprecated tools/methods, old dates in the title, broken external links.

  • Yes, outdated → Refresh. Update facts, screenshots, examples, and dates. Add new sections covering recent developments.
  • No → Investigate deeper. The issue may be technical (lost backlinks, slower page speed, mobile issues) or competitive (stronger pages now outrank).

Refresh Playbooks by Content Type

Different content types require different refresh approaches. Use the matching playbook:

Blog Post / Article (3-4 hours)

  1. Update title with current year or fresh hook (10 min)
  2. Rewrite introduction with a new angle (20 min)
  3. Update all statistics with current sources (30-60 min)
  4. Add 1-2 new sections covering gaps competitors address (60-90 min)
  5. Update screenshots and images (30 min)
  6. Add or refresh FAQ section with current PAA questions (20 min)
  7. Refresh internal links to recent related content (15 min)
  8. Update meta description (5 min)
  9. Add or update schema markup — dateModified at minimum (10 min)
  10. Republish with updated date and re-submit to Search Console (5 min)

Statistics / Data Roundup (4-5 hours)

  1. Verify every statistic — remove any without a current source
  2. Replace outdated stats with current data (within 2 years)
  3. Add new statistics from recent studies
  4. Update all source links — replace broken citations
  5. Update year references in title and body
  6. Add a data visualization if none exists
  7. Update meta description and title

How-To Guide (3-3.5 hours)

  1. Verify all steps still work as written
  2. Update screenshots for any changed interfaces
  3. Add new alternative methods if any have emerged
  4. Update tool recommendations (remove deprecated, add current)
  5. Add a troubleshooting section for common failure points
  6. Update FAQ with recent questions
  7. Test all external links

Refresh Checklist (General)

For any content type, always complete:

  • Update all statistics and data points to current year
  • Replace outdated examples and screenshots
  • Add new sections covering developments since last update
  • Remove or update broken external links
  • Improve the title and meta description (check competitor titles for CTR ideas)
  • Add internal links from recent, related content
  • Expand thin sections that competitors cover better
  • Add original insights, data, or expert quotes (E-E-A-T signals)
  • Update the published/modified date
  • Re-submit to Google Search Console for re-indexing

Consolidation Checklist

When merging two pages:

  • Identify the stronger URL (more backlinks, better position, older)
  • Move the best content from the weaker page into the stronger one
  • Set up a 301 redirect from the weaker URL to the stronger one
  • Update all internal links that pointed to the weaker URL
  • Check for backlinks to the weaker URL — the redirect will pass authority

Prioritization

Score each page for refresh priority:

FactorWeight
Current traffic value25%
Decay severity (composite score)20%
Competitive opportunity20%
Refresh difficulty (inverse — easier = higher)15%
Strategic importance (conversions, brand)10%
Backlink equity at risk10%

Then rank pages:

PageDecay ScoreTraffic LostPriority ScoreActionEffort
...72 (significant)1,200/mo85Refresh3-4 hrs
...45 (active)300/mo60Consolidate2 hrs

Focus on pages that (a) had the most traffic, (b) drive conversions, and (c) are easiest to fix. A quick refresh on a high-traffic page beats a full rewrite on a low-traffic one.

Content Retirement Options

When a page can't be saved, choose the right exit:

OptionWhen to Use
301 redirectContent has backlinks or residual traffic — send equity to closest relevant page
ConsolidateMultiple weak pages on same topic — merge best content into one URL
NoindexInternal utility page that shouldn't rank but serves users
Delete (410)No value, no links, no traffic — clean removal

Output Format

Content Recovery Plan: [domain]

Decay Summary

  • Pages analyzed: [count]
  • Pages needing action: [count]
  • Estimated traffic recoverable: [sum of lost traffic]

Triage Results

PageTraffic LostDiagnosisActionEffort
......intent shift / outdated / cannibalization / irrelevantrefresh / consolidate / redirect / retirelow / medium / high

Priority Actions

For each high-priority page:

  • What specifically needs to change
  • Which sections to update, expand, or remove
  • Estimated impact if recovered

Pro Tip: Use the free Keyword Density Analyzer to check whether a declining page is still optimized for its target keyword. SEOJuice MCP users can run /seojuice:content-strategy to see active content decay alerts with severity ratings — the list_content_decay tool pulls pages losing traffic automatically.

平台分布

Codex

36.28%
按下载量换算4,712

Claude

30.83%
按下载量换算4,005

Cursor

16.31%
按下载量换算2,119

Gemini CLI

9.67%
按下载量换算1,256

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/calm-north/seojuice-skills --skill recover-content 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。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