Token导航 LogoToken导航

Agent Skill · 研究检索

social-media-marketing(社交媒体营销)

social-media-marketing 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。

social-media-marketing 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,权限为只读;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 4,934。

总安装 28,862周安装 1,174GitHub Stars 4下载 9,675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:social-media-marketing(社交媒体营销)
来源仓库:https://github.com/dengineproblem/agents-monorepo
仓库路径:skills/social-media-marketing
安装命令:
npx skills add https://github.com/dengineproblem/agents-monorepo --skill social-media-marketing
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/dengineproblem/agents-monorepo --skill social-media-marketing

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。

社交媒体策略专家,涵盖 Instagram、TikTok、LinkedIn、Facebook 和 Twitter,并具有特定于平台的策略。

五个主要平台的详细策略,包括每个平台的最佳发布频率、最佳时间、内容格式和算法因素 综合社区管理框架,包含评论、问题、投诉和危机情况的响应协议 每周内容日历结构,包含 40/20/20/10/10 内容组合(教育、娱乐、促销、参与、策划) 付费社交指导,涵盖活动目标、受众定位、相似策略和 A/B 测试方法 跨所有平台的认知度、参与度和转化率的参与基准和指标跟踪

来源仓库内路径:skills/social-media-marketing

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/dengineproblem/agents-monorepo --skill social-…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

social-media-marketing 怎么安装?

在终端执行 npx skills add https://github.com/dengineproblem/agents-monorepo --skill social-media-mark…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

social-media-marketing 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。

social-media-marketing 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

social-media-marketing 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。

social-media-marketing 用的人多吗?

公开数据是累计安装 28,862 次,近一周安装 1,174 次,下载 9,675 次,GitHub 4 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。

social-media-marketing 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
social-media-marketing

社交媒体营销 · 本页

28,8624只读未明确通过

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

Social Media Marketing Expert

Comprehensive knowledge of social media strategy, content creation, community management, and platform optimization.

Core Competencies

platform_strategy:
  - "Platform selection and focus"
  - "Content pillars development"
  - "Posting schedule optimization"
  - "Hashtag strategy"
  - "Algorithm understanding"

content_creation:
  - "Native platform formats"
  - "Visual content best practices"
  - "Video strategy"
  - "Ephemeral content (Stories)"
  - "User-generated content"

community_management:
  - "Engagement tactics"
  - "Response frameworks"
  - "Audience building"
  - "Crisis management"
  - "Influencer relationships"

Platform Strategies

Instagram

instagram:
  audience: "18-44, visual-first, lifestyle focus"
  content_types:
    feed_posts:
      formats: ["Carousels", "Single image", "Video"]
      frequency: "4-7 posts/week"
      best_times: "11am-1pm, 7pm-9pm"

    reels:
      length: "15-90 seconds"
      style: "Entertaining, trending audio"
      frequency: "5-7 per week"
      best_practices:
        - "Hook in first 3 seconds"
        - "Use trending sounds"
        - "Add captions"
        - "Native editing preferred"

    stories:
      frequency: "3-5 per day"
      content:
        - "Behind the scenes"
        - "Polls and questions"
        - "Quick updates"
        - "Link sharing"
      engagement: "Use interactive stickers"

    lives:
      frequency: "1-2 per week"
      duration: "30-60 minutes"
      content:
        - "Q&A sessions"
        - "Product launches"
        - "Collaborations"

  algorithm_factors:
    - "Engagement rate"
    - "Relationship signals"
    - "Timeliness"
    - "Content type diversity"
    - "Time spent on post"

  hashtag_strategy:
    quantity: "3-5 per post (quality over quantity)"
    mix:
      - "1-2 branded"
      - "2-3 niche specific"
      - "1-2 community"
    placement: "In caption or first comment"

TikTok

tiktok:
  audience: "16-34, entertainment-first"
  content_types:
    regular_videos:
      length: "15-60 seconds optimal"
      frequency: "1-3 per day"
      style: "Raw, authentic, entertaining"

    trending:
      action: "Jump on trends within 24-48 hours"
      adaptation: "Make it relevant to your niche"

  best_practices:
    hooks:
      - "Start with movement"
      - "Ask a question"
      - "Make a bold statement"
      - "Use pattern interrupt"

    retention:
      - "Keep cuts fast"
      - "Add on-screen text"
      - "Loop-worthy endings"
      - "Storytelling arc"

  algorithm_factors:
    - "Watch time / completion rate"
    - "Rewatches"
    - "Shares"
    - "Comments"
    - "Profile visits after viewing"

  trending_sounds:
    strategy: "Use trending sounds early"
    discovery: "Creative Center, For You page"

LinkedIn

linkedin:
  audience: "B2B professionals, decision makers"
  content_types:
    text_posts:
      length: "1200-1500 characters optimal"
      format:
        - "Hook first line"
        - "Short paragraphs"
        - "White space"
        - "Strong CTA"
      frequency: "3-5 per week"

    carousels:
      slides: "8-12 optimal"
      design: "Clean, branded, mobile-first"
      content: "Educational, actionable"

    articles:
      length: "1500-2000 words"
      frequency: "1-2 per month"
      content: "Thought leadership, deep dives"

    video:
      length: "Under 2 minutes"
      type: "Native upload preferred"
      content: "Tips, insights, behind scenes"

  best_practices:
    posting_times: "Tue-Thu, 8-10am, 12pm, 5-6pm"
    engagement:
      - "Respond to all comments"
      - "Comment on others' posts first"
      - "Tag relevant people"
      - "Ask questions"

  algorithm_factors:
    - "Dwell time"
    - "Comments (especially long ones)"
    - "Shares"
    - "Profile clicks"
    - "Connection relevance"

Facebook

facebook:
  audience: "25-54, community focus"
  content_types:
    posts:
      formats: ["Video", "Links", "Images", "Carousels"]
      frequency: "1-2 per day"
      best_times: "1-4pm"

    reels:
      length: "15-90 seconds"
      style: "Similar to Instagram Reels"

    groups:
      purpose: "Community building"
      engagement: "Daily interaction"
      content: "Exclusive, discussion-driven"

    lives:
      boost: "Higher organic reach"
      content: "Events, Q&A, launches"

  best_practices:
    native_video: "Upload directly, no YouTube links"
    engagement: "Respond within 1 hour"
    groups: "Build owned community"

  algorithm_factors:
    - "Meaningful interactions"
    - "Comments > Reactions > Shares"
    - "Native content preferred"
    - "Video watch time"

Twitter/X

twitter_x:
  audience: "News, real-time, conversations"
  content_types:
    tweets:
      length: "100-200 characters optimal"
      frequency: "3-10 per day"
      formats: ["Text", "Images", "Polls", "Threads"]

    threads:
      length: "5-15 tweets"
      structure:
        - "Hook tweet"
        - "Value content"
        - "Summary/CTA"
      numbering: "1/, 2/, etc."

    spaces:
      purpose: "Audio conversations"
      frequency: "Weekly"
      duration: "30-60 minutes"

  best_practices:
    engagement:
      - "Reply to others"
      - "Quote tweet with insight"
      - "Join conversations"
    timing: "Morning, lunch, evening peaks"
    hashtags: "1-2 max"

  algorithm_factors:
    - "Recency"
    - "Engagement velocity"
    - "Relationship signals"
    - "Content type variety"

Content Calendar

content_calendar:
  weekly_structure:
    monday:
      theme: "Educational"
      content: "Tips, how-tos, tutorials"

    tuesday:
      theme: "Industry trends"
      content: "News, insights, opinions"

    wednesday:
      theme: "Behind the scenes"
      content: "Team, process, culture"

    thursday:
      theme: "Customer spotlight"
      content: "Testimonials, case studies, UGC"

    friday:
      theme: "Engagement"
      content: "Questions, polls, fun content"

    saturday:
      theme: "Curated"
      content: "Third-party content, shares"

    sunday:
      theme: "Cultural/Inspirational"
      content: "Quotes, stories, values"

  content_mix:
    educational: "40%"
    entertaining: "20%"
    promotional: "20%"
    engagement: "10%"
    curated: "10%"

  planning_template:
    fields:
      - "Date/Time"
      - "Platform"
      - "Content type"
      - "Topic/Theme"
      - "Copy"
      - "Visual assets"
      - "Hashtags"
      - "CTA"
      - "Links"
      - "Status"

Community Management

engagement_strategy:
  response_framework:
    positive_comments:
      response_time: "Within 2 hours"
      approach: "Thank, add value, engage"

    questions:
      response_time: "Within 1 hour"
      approach: "Answer thoroughly, offer more help"

    complaints:
      response_time: "Within 30 minutes"
      approach: "Acknowledge, empathize, resolve"
      escalation: "Take to DM if sensitive"

    negative_comments:
      assessment: "Legitimate concern vs troll"
      legitimate: "Address publicly, show resolution"
      troll: "Don't engage, hide if needed"

  proactive_engagement:
    daily_tasks:
      - "Like relevant posts (30-50)"
      - "Comment meaningfully (20-30)"
      - "Share valuable content (5-10)"
      - "Respond to all mentions"
      - "Check brand hashtags"

  crisis_management:
    assessment:
      level_1: "Minor complaint (individual)"
      level_2: "Growing concern (spreading)"
      level_3: "Full crisis (viral, media)"

    response_protocol:
      - "Acknowledge immediately"
      - "Gather facts before responding"
      - "Prepare holding statement"
      - "Provide updates regularly"
      - "Document everything"

Metrics & Analytics

key_metrics:
  awareness:
    - "Reach"
    - "Impressions"
    - "Follower growth"
    - "Share of voice"

  engagement:
    - "Engagement rate"
    - "Comments"
    - "Shares/Saves"
    - "Click-through rate"

  conversion:
    - "Link clicks"
    - "Website traffic from social"
    - "Lead generation"
    - "Sales attribution"

engagement_rate_benchmarks:
  instagram:
    good: ">3%"
    average: "1-3%"
    low: "<1%"

  tiktok:
    good: ">5%"
    average: "3-5%"
    low: "<3%"

  linkedin:
    good: ">2%"
    average: "1-2%"
    low: "<1%"

  twitter:
    good: ">1%"
    average: "0.5-1%"
    low: "<0.5%"

reporting:
  weekly:
    - "Top performing posts"
    - "Engagement trends"
    - "Follower changes"
    - "Notable interactions"

  monthly:
    - "Full metrics dashboard"
    - "Content performance analysis"
    - "Audience insights"
    - "Competitor comparison"
    - "Recommendations"

Paid Social

paid_social_strategy:
  campaign_objectives:
    awareness:
      - "Reach"
      - "Brand awareness"
      - "Video views"

    consideration:
      - "Traffic"
      - "Engagement"
      - "App installs"
      - "Lead generation"

    conversion:
      - "Conversions"
      - "Catalog sales"
      - "Store traffic"

  targeting:
    core_audiences:
      - "Demographics"
      - "Interests"
      - "Behaviors"
      - "Location"

    custom_audiences:
      - "Website visitors"
      - "Email list"
      - "App users"
      - "Engagement audiences"

    lookalike_audiences:
      source: "Best customers"
      percentage: "1-3% for quality, 5-10% for reach"

  budget_allocation:
    testing: "20%"
    proven_campaigns: "70%"
    experimental: "10%"

  optimization:
    a_b_testing:
      - "Creative variations"
      - "Audiences"
      - "Placements"
      - "Copy"
    frequency_cap: "3-5 per week per user"

Tools Stack

smm_tools:
  scheduling:
    - "Buffer"
    - "Hootsuite"
    - "Later"
    - "Sprout Social"

  analytics:
    - "Native platform analytics"
    - "Sprout Social"
    - "Brandwatch"
    - "Mention"

  design:
    - "Canva"
    - "Adobe Creative Suite"
    - "Figma"
    - "CapCut (video)"

  listening:
    - "Brandwatch"
    - "Mention"
    - "Sprinklr"
    - "Talkwalker"

  influencer:
    - "AspireIQ"
    - "Grin"
    - "Upfluence"

Лучшие практики

  1. Platform native — адаптируй контент под каждую платформу
  2. Consistency — регулярный постинг важнее идеального
  3. Engage authentically — общайся как человек, не бренд
  4. Test and iterate — анализируй что работает
  5. Community first — строй отношения, не только followers
  6. Video priority — все платформы продвигают видео

平台分布

Codex

38.9%
按下载量换算3,764

Claude

28.61%
按下载量换算2,768

Cursor

20.04%
按下载量换算1,939

Gemini CLI

10.32%
按下载量换算998

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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