Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

content-repurposing内容再利用

Agent Skill

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。

总安装

6,230

周安装

257

GitHub Stars

380

下载量

2,035
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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-repurposing(内容再利用)
来源仓库:https://github.com/inference-sh/skills
仓库路径:skills/content-repurposing
安装命令:
npx skills add https://github.com/inference-sh/skills --skill content-repurposing
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/inference-sh/skills --skill content-repurposing

简介

content-repurposing 用于文档与 Markdown 内容的整理与改写,提升可读性。

  • 适合提炼结构、补齐章节、统一术语或检查链接有效性。
  • 应保留项目已有事实与路径,不将未确认信息写成确定结论。
  • 对外文案需注意语气控制,避免过度营销或夸大能力描述。
  • 建议结合原始资料核验关键数据与引用来源准确性。

SKILL.md

Content Repurposing

Turn one piece of content into many formats via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions
belt login

# Generate a quote card from a blog pull-quote
belt app run falai/flux-dev-lora --input '{
  "prompt": "minimal quote card design, dark navy background, large white quotation marks, clean sans-serif typography space, modern professional design, social media post format",
  "width": 1024,
  "height": 1024
}'

The Content Pyramid

One source piece can generate 10+ derivative assets:

            ┌──────────┐
            │ LONG-FORM │  Blog post, podcast, video, whitepaper
            │  SOURCE   │
            └─────┬─────┘
                  │
        ┌─────────┼─────────┐
        ▼         ▼         ▼
   ┌─────────┐ ┌──────┐ ┌──────────┐
   │ MEDIUM  │ │MEDIUM│ │  MEDIUM  │  Newsletter, LinkedIn, email
   │ FORMAT  │ │FORMAT│ │  FORMAT  │
   └────┬────┘ └──┬───┘ └────┬─────┘
        │         │          │
   ┌────┼────┐    │     ┌────┼────┐
   ▼    ▼    ▼    ▼     ▼    ▼    ▼
 ┌───┐┌───┐┌───┐┌───┐┌───┐┌───┐┌───┐  Tweets, quotes, audiograms,
 │   ││   ││   ││   ││   ││   ││   │  short clips, infographic tiles
 └───┘└───┘└───┘└───┘└───┘└───┘└───┘

Conversion Recipes

Blog Post -> Twitter/X Thread

Extract 5-8 key insights. One per tweet. Add hook.

ElementRule
Hook tweetListicle, contrarian, or promise format
Body tweetsOne insight per tweet, 280 chars max
Visual breaksAdd image every 3-4 tweets
Final tweetCTA + "RT the first tweet if useful"

Adaptation:

  • Remove nuance and caveats (threads are punchy)
  • Add numbers and specifics (threads need skimmability)
  • Cut academic language (threads are conversational)
# Generate a visual for the thread
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean infographic tile, single statistic 60% highlighted in large bold text, minimal dark background, data visualization style, professional",
  "width": 1024,
  "height": 1024
}'

# Post the thread
belt app run x/post-create --input '{
  "text": "I analyzed 500 landing pages.\n\nHere are 7 patterns the top converters all share:\n\n🧵 Thread:"
}'

Blog Post -> LinkedIn Carousel

1 slide per section. 8-12 slides total.

SlideContent
1 (Hook)Bold claim or question from headline
2-9 (Content)One key point per slide, large text, supporting visual
10 (Summary)Recap the key takeaways
11 (CTA)"Follow for more" / "Save this" / "Comment your thoughts"

Specs: 1080x1080 (square) or 1080x1350 (4:5 for more space)

# Generate carousel slides
for i in {1..10}; do
  belt app run falai/flux-dev-lora --input "{
    \"prompt\": \"clean minimal presentation slide, dark gradient background, large text area, professional business design, slide $i of 10, consistent style\",
    \"width\": 1024,
    \"height\": 1024
  }" --no-wait
done

Blog Post -> Newsletter Section

3-line summary + "why it matters" + link.

## This Week's Feature: [Title]

[1-2 sentence summary of the key insight]

**Why it matters:** [1 sentence connecting to reader's work/life]

→ [Read the full post](link)

Blog Post -> Short-Form Video Script

Problem + key insight + CTA. Under 60 seconds.

SectionDurationContent
Hook3s"Most people get [topic] wrong."
Problem10sState the common mistake
Insight25sYour key finding/advice
Proof10sOne stat or example
CTA5s"Follow for more" / "Link in bio"
# Generate voiceover
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Most landing pages make this mistake. They put the features above the fold instead of the outcome. Top converting pages show what life looks like AFTER using the product. Try it and watch your conversion rate climb."
}'

# Generate video
belt app run google/veo-3-1-fast --input '{
  "prompt": "Screen recording style, scrolling through a well-designed landing page, clean modern UI, smooth scroll, professional website"
}'

Blog Post -> Audiogram

Pull best quote. Generate audio. Add waveform visual.

# Generate audio of the key quote
belt app run falai/dia-tts --input '{
  "prompt": "[S1] The number one mistake I see on landing pages... is putting features above the fold. The best pages show the outcome. Not what your product does, but what life looks like after."
}'

Podcast Episode -> Blog Post

# 1. Transcribe the episode
belt app run <stt-app> --input '{
  "audio": "episode-42.mp3"
}'

# 2. Edit transcript into blog format:
# - Remove filler words (um, uh, like, you know)
# - Add headers at topic changes
# - Break into paragraphs
# - Add intro and conclusion
# - Add links mentioned in the episode

Podcast Episode -> Quote Cards

3-5 best quotes with speaker attribution.

# Generate quote card backgrounds
belt app run falai/flux-dev-lora --input '{
  "prompt": "minimal quote card background, subtle gradient from dark blue to black, large quotation mark watermark, clean modern design, social media square format",
  "width": 1080,
  "height": 1080
}'

Video -> GIF

Key moment, 3-5 seconds, under 5MB.

Best moments for GIFs:

  • Reaction shots
  • Before/after reveals
  • Key demonstration steps
  • Funny or surprising moments

Long Video -> Short Clips

# Extract the best 15-60 second segments for Reels/TikTok/Shorts
# Focus on self-contained moments that make sense without context:
# - A single tip or insight
# - A surprising stat reveal
# - A demonstration of one feature
# - A strong opinion or hot take

The Golden Rule

Never copy-paste across formats. Each platform has different:

PlatformAttention SpanToneFormat
Blog5-10 minThorough, detailedLong paragraphs OK
Twitter/X5-30 sec per tweetPunchy, declarative280 chars, fragmented
LinkedIn1-3 minProfessional, insightfulShort paragraphs, line breaks
Newsletter5-7 minCurated, personalSections with headers
TikTok/Reels15-60 secEnergetic, directHook in 1 second
Podcast20-60 minConversational, deepStories and tangents OK

Content Repurposing Checklist

For each piece of long-form content, create:

  • Twitter/X thread (5-8 tweets)
  • LinkedIn post or carousel
  • Newsletter section (3-line summary)
  • 2-3 quote cards for social
  • Short-form video script (30-60s)
  • Email snippet for nurture sequence
  • Slide for internal presentation

Common Mistakes

MistakeProblemFix
Copy-pasting between platformsFeels lazy, wrong formatRewrite for each platform's style
Repurposing weak contentAmplifies mediocrityOnly repurpose your best pieces
Same day posting everywhereAudience overlap sees duplicatesStagger across days/weeks
Losing the core messageDerivative misses the pointIdentify the ONE key insight first
No visual adaptationText-only on visual platformsCreate platform-specific graphics
Forgetting attributionPlagiarizes yourselfLink back to the original

Related Skills

npx skills add inference-sh/skills@ai-social-media-content
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@text-to-speech
npx skills add inference-sh/skills@twitter-automation

Browse all apps: belt app list

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.06%
按下载量换算673

Claude

32.89%
按下载量换算669

Cursor

17.1%
按下载量换算348

Gemini CLI

9.86%
按下载量换算201

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills