Token导航 LogoToken导航

Agent Skill · 研究检索

content-atomizer(内容 atomizer)

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。

content-atomizer 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 67,168。

总安装 250周安装 10GitHub Stars 30下载 81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:content-atomizer(内容 atomizer)
来源仓库:https://github.com/salesably/salesably-marketplace
仓库路径:skills/content-atomizer
安装命令:
npx skills add https://github.com/salesably/salesably-marketplace --skill content-atomizer
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/salesably/salesably-marketplace --skill content-atomizer

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。

content-atomizer 用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写,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。适用于内容原子化相关的文档整理、README 优化和内容稿件改写等文本处理任务。

通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 核验具体用法。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。

可结合来源仓库路径 skills/content-atomizer 继续核验功能细节和使用边界。

来源仓库内路径:skills/content-atomizer

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/salesably/salesably-marketplace --skill conten…;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

content-atomizer 怎么安装?

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

content-atomizer 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。

content-atomizer 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。

content-atomizer 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。

content-atomizer 用的人多吗?

公开数据是累计安装 250 次,近一周安装 10 次,下载 81 次,GitHub 30 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。

content-atomizer 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
content-atomizer

内容 atomizer · 本页

25030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

Content Atomizer

This skill extracts maximum value from every piece of content by strategically repurposing it across formats and platforms - without losing quality or sounding repetitive.

Objective

Transform one substantial piece of content into many derivative pieces, each optimized for its destination platform while maintaining consistent brand voice and messaging.

Intake Questions

Before atomizing content, gather context:

  1. Source content: What is the original piece? (Blog post, video, podcast, webinar, report)
  2. Target platforms: Where should the atomized content go? (LinkedIn, Twitter/X, Instagram, YouTube, email, etc.)
  3. Audience overlap: Are the same people on multiple platforms or different segments?
  4. Brand voice: What's the established voice? (Reference brand-voice skill)
  5. Goals per platform: What action do you want on each? (Awareness, clicks, engagement, follows)
  6. Content calendar: What's the publishing cadence per platform?
  7. Evergreen vs. timely: Does this content have a shelf life?

The Atomization Matrix

Transform source content into these derivative formats:

From a Blog Post / Article

Derivative FormatWhat to ExtractPlatform
Twitter/X threadMain points as numbered listTwitter/X
LinkedIn postKey insight + personal takeLinkedIn
Instagram carouselTips/steps as slidesInstagram
Email newsletter sectionSummary + linkEmail
Quote graphicsQuotable linesAll social
YouTube Short / ReelOne tip explainedYouTube, IG, TikTok
Podcast talking pointsDiscussion outlinePodcast
InfographicData/process visualizationPinterest, LinkedIn
Slide deckKey points as slidesSlideShare, LinkedIn
FAQ contentQuestions answered in postWebsite, help docs

From a Video / Webinar

Derivative FormatWhat to ExtractPlatform
Blog postFull transcript, editedWebsite
Short clips (60-90s)Key momentsYouTube Shorts, Reels, TikTok
AudiogramAudio + waveform visualSocial media
Quote graphicsBest soundbitesAll social
Twitter/X threadMain points summarizedTwitter/X
Email recapHighlights + replay linkEmail
LinkedIn articleExpanded written versionLinkedIn
Slide deckPresentation slides reusedSlideShare
GIF momentsReactions, demonstrationsSocial, website
Transcript PDFLead magnet or resourceWebsite

From a Podcast Episode

Derivative FormatWhat to ExtractPlatform
Show notes postSummary + timestampsWebsite
Full transcriptSearchable text versionWebsite
Blog postKey insights expandedWebsite
Audiogram clipsBest 60-second momentsSocial media
Quote graphicsGuest quotes, key insightsSocial media
Twitter/X threadEpisode highlightsTwitter/X
NewsletterEpisode summary + linkEmail
YouTube videoVideo version if recordedYouTube
Pull quotesFor promotional useAll channels
Guest spotlightFeature the guestLinkedIn, Twitter/X

From a Report / Research

Derivative FormatWhat to ExtractPlatform
Blog posts (series)One post per findingWebsite
InfographicsData visualizationsPinterest, LinkedIn
Twitter/X threadsKey stats and insightsTwitter/X
LinkedIn postsIndividual findingsLinkedIn
Press releaseNewsworthy findingsMedia
Slide deckPresentation versionConferences, webinars
WebinarWalk through findingsLive presentation
Email seriesOne finding per emailEmail
Stat graphicsIndividual data pointsAll social
Executive summaryShort PDF versionLead magnet

Platform-Specific Adaptation

Each platform has different requirements:

Twitter/X

  • Length: 280 characters or threads
  • Tone: Conversational, punchy
  • Format: Text, images, threads, polls
  • Best for: Ideas, insights, engagement
  • Hook: First line must stop the scroll

LinkedIn

  • Length: Up to 3,000 characters
  • Tone: Professional but human, relatable, and opinionated
  • Format: Text posts, carousels, articles, video
  • Best for: B2B, thought leadership, career content, personal branding
  • Hook: First 2 lines are critical before "...see more"
  • Timing: Tuesday-Thursday, 8-11 AM (audience's time zone)
  • Links: Place external links in the first comment, not the post body, to avoid algorithm penalties

Instagram

  • Length: 2,200 characters (but shorter better)
  • Tone: Visual-first, casual, authentic
  • Format: Feed posts, carousels, Reels, Stories
  • Best for: Visual content, personal brands, how-tos
  • Hook: Strong first slide/frame

YouTube

  • Length: Varies (Shorts: 60s, Long-form: 10-20min optimal)
  • Tone: Energetic, valuable, entertaining
  • Format: Long-form, Shorts, Community posts
  • Best for: Tutorials, entertainment, deep dives
  • Hook: First 30 seconds critical

TikTok

  • Length: Up to 10 minutes (but 15-60s performs best)
  • Tone: Authentic, entertaining, trend-aware
  • Format: Short videos, duets, stitches
  • Best for: Younger audiences, entertainment, trends
  • Hook: First 1-3 seconds critical

Email

  • Length: 200-500 words typically
  • Tone: Personal, direct, valuable
  • Format: Newsletter sections, standalone emails
  • Best for: Deeper engagement, conversions
  • Hook: Subject line + first line

Viral LinkedIn Post Framework (2025)

When repurposing content for LinkedIn, follow this proven structure for maximum reach:

1. The Scroll-Stopping Hook

The first 2 lines must earn the click on "...see more".

  • Stat/Data: Start with a surprising number.
  • Bold Opinion: Challenge common wisdom in your niche.
  • Personal Moment: Share a vulnerable or relatable struggle.
  • Unexpected Twist: Start with a premise and flip it immediately.
  • Avoid: "Just wanted to share some thoughts..." or "I've been thinking about..."

2. The Single Message Body

Don't cram multiple ideas into one post.

  • One Post, One Intent: Stick to one story, one lesson, or one tip.
  • Scannable Formatting: Use 1-3 lines per paragraph max.
  • Mobile-Friendly: Use whitespace to make it easy to read on phones.
  • Specifics: Name tools, give real numbers, and use concrete examples.

3. The Discussion-Starting CTA

End with a prompt that invites conversation.

  • Real Questions: "Have you felt this same pressure?" or "What's one tool I missed?"
  • Low Friction: Make it easy for people to share their own experience.
  • Avoid Engagement Bait: Never use "Like if you agree" or "Comment 'YES' below".
  • Optional CTA: If the post is a heartfelt story, it's okay to skip the CTA entirely.

4. Early Engagement Strategy

LinkedIn's algorithm prioritizes posts that get traction in the first 60-90 minutes.

  • Reply Immediately: Engage with every comment in the first hour.
  • Seed the Link: If you have a link to share, post it as the first comment after publishing.

Content Hierarchy

Structure your content ecosystem:

                 ┌─────────────────────────────┐
                 │      PILLAR CONTENT         │
                 │  (Blog post, Video, Report) │
                 └─────────────┬───────────────┘
                               │
           ┌───────────────────┼───────────────────┐
           │                   │                   │
           ▼                   ▼                   ▼
    ┌─────────────┐     ┌─────────────┐     ┌─────────────┐
    │ SUPPORTING  │     │ SUPPORTING  │     │ SUPPORTING  │
    │  Blog posts │     │   Videos    │     │   Emails    │
    └──────┬──────┘     └──────┬──────┘     └──────┬──────┘
           │                   │                   │
           ▼                   ▼                   ▼
    ┌─────────────────────────────────────────────────────┐
    │               MICRO CONTENT                         │
    │  Social posts, Clips, Graphics, Quotes, Stories     │
    └─────────────────────────────────────────────────────┘

Rules:

  • Pillar content: Comprehensive, original, high-effort
  • Supporting content: Derived, expanded on subtopics
  • Micro content: Snackable, platform-native, high-volume

Efficiency Workflow

Batch production process for maximum efficiency:

Step 1: Create Pillar Content

  • Invest heavily in one comprehensive piece
  • Make it your best work on the topic
  • Include multiple angles and subtopics

Step 2: Extract Core Elements

Pull from pillar content:

  • Key insights (3-5)
  • Quotable lines (5-10)
  • Data points (all stats)
  • Steps/processes (full lists)
  • Stories/examples (all narratives)

Step 3: Map to Platforms

Assign elements to platforms based on the AMA Framework:

  • Audience: Who are we talking to on this specific platform? (Speak to one real person).
  • Message: What is the one key insight they need from this piece?
  • Action: What specific action should they take?

Assign elements to platforms based on:

  • Platform format requirements
  • Audience on each platform
  • Goals per platform

Step 4: Batch Create

Create all derivatives in batches:

  • All graphics in one session
  • All written posts in one session
  • All video clips in one session

Step 5: Schedule Distribution

Stagger publication:

  • Don't post everywhere same day
  • Space derivatives over weeks
  • Maintain consistent presence per platform

Voice Consistency Checklist

When atomizing, maintain brand voice:

  • Same vocabulary and terminology
  • Consistent perspective (first person, third person)
  • Matching energy level (enthusiastic, measured)
  • Aligned values and opinions
  • Recognizable style markers
  • No Em-Dashes: Ensure no em-dashes (-) or en-dashes (-) are used in any platform derivatives.

Adaptation allowed:

  • Tone can flex slightly for platform (more casual on TikTok, more professional on LinkedIn)
  • Length adjusts for platform
  • Format changes for platform requirements

Not allowed:

  • Contradicting messaging across platforms
  • Different personalities on different channels
  • Conflicting information or opinions

Output Format

When atomizing content, deliver:

  1. Source Analysis: Summary of pillar content and extractable elements
  2. Atomization Plan: What derivatives to create, for which platforms
  3. Derivative Content: Full copy/scripts for each piece
  4. Visual Specifications: Requirements for graphics/video (if applicable)
  5. Distribution Schedule: When to publish each piece
  6. Cross-Linking Strategy: How pieces connect back to pillar content

Cross-References

  • Apply brand-voice to ensure consistency across all derivatives
  • Source content may come from seo-content pillar articles
  • Turn derivatives into newsletter sections
  • Support lead-magnet promotion across channels
  • keyword-research topics inform pillar content selection
  • orchestrator routes here for content distribution projects

平台分布

Codex

37.73%
按下载量换算31

Claude

29.22%
按下载量换算24

Cursor

18.32%
按下载量换算15

Gemini CLI

9.68%
按下载量换算8

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