Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

content-repurposer内容再利用者

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

392

周安装

16

GitHub Stars

4

下载量

127
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-repurposer(内容再利用者)
来源仓库:https://github.com/cdeistopened/opened-vault
仓库路径:skills/content-repurposer
安装命令:
npx skills add https://github.com/cdeistopened/opened-vault --skill content-repurposer
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/cdeistopened/opened-vault --skill content-repurposer

简介

用于将源内容转化为平台优化的社交媒体帖子,适配不同渠道的表达形式。

  • 适合品牌内容再创作、跨平台传播和多格式文案生成场景。
  • 使用时应加载 opened-identity 上下文,保持品牌身份一致性。
  • 通过 GitHub 安装,支持主流宿主环境,需注意品牌语境和发布平台特性。
  • content-repurposer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Content Repurposer

Transform source content into platform-optimized posts using framework fitting.

Core job: Take content from any source → understand context → extract snippets → match to templates → optimize for each platform.


Context Awareness (Critical)

Brand Context

OpenEd is a company, not an individual.

AspectImplication
VoiceBrand account, not personal ("we" not "I")
Authority125,000+ families, 9 states, tuition-free resources
ToneHelpful expert, not salesy. Permission-giving, not preachy.
IdentityPro-child, not anti-school. Mix and match philosophy.

Always load: opened-identity for full brand context.

Source Context

The source determines voice and framing:

SourceVoiceFramingTagging
Podcast guestThird personMake THEM look goodTag guest on all platforms
NewsletterFirst person plural"We found..." "Our team..."Tag mentioned sources
Archive articleAuthorityFresh angle, current relevanceTag original author if external
Staff insightFirst person pluralShare the discoveryInternal attribution

Podcast guest example:

❌ "I learned so much from Ken Danford..."
✅ "Ken Danford (@northstarteens) explains why..."
✅ "@kendanford's insight on self-directed learning..."

The Framework Fitting Process

Step 1: Identify Source Type

What am I repurposing?
├─ Podcast episode → Load guest context, prepare @handles
├─ Newsletter → Extract TTT segments (Thought/Trend/Tool)
├─ Article → Extract key insights, stats, quotes
├─ Archive content → Find fresh angle, check current relevance
└─ Raw insight → Match to template directly

Step 2: Extract Snippets by Type

From any source, identify standalone pieces:

Snippet TypeWhat to ExtractBest Templates
hot_takeOpinion that stands aloneContrarian, Paradox Hook, Call BS
statData point + interpretationAuthority, Commentary, Data Story
how_toActionable adviceList, Thread, Tips, Carousel
quoteMemorable line from sourceQuote + Commentary
storyTransformation arcStory, Day-in-Life

Step 3: Check Nearbound

Before drafting, check for taggable people:

1. Identify all names mentioned
2. Search: Studio/Nearbound Pipeline/people/
3. If found → Get @handle for target platform
4. If not found → Note for future profile creation

Priority tags: Podcast guests, quoted experts, tool/curriculum founders.

Step 4: Route to Platforms

SnippetLinkedInXInstagramFacebook
hot_takeContrarianParadox HookQuote cardAgree/Disagree
statAuthorityCommentaryCarouselQuestion
how_toListThreadCarouselFill-blank
quoteQuote + Hot TakeCommentaryQuote cardValidation
storyTransformationThreadCarouselStory post

Step 5: Apply Platform Constraints

PlatformLengthHashtagsLinksTone
LinkedIn200-500 words3-5OK in bodyProfessional authority
X70-100 chars0-2In replyPunchy, scroll-stopping
Instagram30-150 chars5-10Bio onlyCasual, visual-first
Facebook10-40 words0Comments onlyConversational, questions
TikTok50-150 chars3-5Bio onlyCasual, trend-aware

Template Quick Reference

Load full templates from: .claude/skills/text-content/references/

LinkedIn (6 categories)

  • linkedin/engagement.md - Polls, Agree/Disagree (16 templates)
  • linkedin/story.md - Transformations, Values (24 templates)
  • linkedin/list.md - Tips, Frameworks (17 templates)
  • linkedin/contrarian.md - Hot takes, Rants (20 templates)
  • linkedin/authority.md - Quotes, How-to (26 templates)
  • linkedin/community.md - Shoutouts, Introductions (15 templates)

X/Twitter

  • templates/post-structures.md - 100+ formats
  • templates/one-liners.md - 12 punchy patterns

Instagram/Facebook

  • platforms/instagram-captions.md
  • platforms/facebook.md

Output Format

For each platform, produce:

## [Platform] Post

**Template:** [Template name used]
**Source:** [What this came from]

---

[The actual post content]

---

**Tags:** @handle1 @handle2
**Hashtags:** #tag1 #tag2 (platform-appropriate count)
**Visual direction:** [If needed - quote card, carousel, etc.]

Dimension Handling (Visual Assets)

When source includes a 16:9 infographic or thumbnail:

Original (16:9 - article thumbnail)
    │
    ├─→ Instagram Feed (4:5)
    │   Prompt: "Adapt this infographic to 4:5 portrait,
    │            prioritize [key element], crop or extend background"
    │
    ├─→ Instagram/Facebook Square (1:1)
    │   Prompt: "Center the key message, square crop"
    │
    └─→ Stories/Reels Cover (9:16)
        Prompt: "Vertical adaptation, text readable on mobile"

Use: nano-banana-image-generator with re-input of original image.


Voice Constraints (Always Apply)

From ai-tells - HARD BLOCKS:

❌ No correlative constructions:

  • "X isn't just Y - it's Z"
  • "It's not about X, it's about Y"

❌ No forbidden words:

  • delve, comprehensive, crucial, leverage, landscape, navigate, foster, facilitate, realm, paradigm, embark, journey, tapestry, myriad, multifaceted, seamless, cutting-edge

❌ No setup phrases:

  • "The best part?", "What if I told you", "Here's the thing", "Let's be honest"

❌ No staccato patterns:

  • "No fluff. No filler. Just results."

Dash usage: Hyphens with spaces - like this. Never em dashes.


Batch Processing Mode

When repurposing multiple pieces (e.g., full newsletter → social):

1. Read entire source
2. Extract ALL snippets (usually 3-5 per newsletter)
3. For each snippet:
   ├─ Identify type (hot_take, stat, how_to, quote, story)
   ├─ Check nearbound for tags
   └─ Generate 2-3 platform drafts
4. Output organized by platform:
   ├─ LinkedIn (2-3 posts)
   ├─ X (2-3 posts)
   ├─ Instagram (1-2 posts + visual direction)
   └─ Facebook (1-2 posts)

Expected output: 6-9 total posts per newsletter/article.


When to Use This Skill

Use content-repurposer when:

  • Newsletter is complete → need social posts
  • Podcast is published → need clip promotions
  • Article is live → need distribution posts
  • Archive content identified → need fresh framing
  • Any content needs multi-platform adaptation

Don't use for:

  • Original content creation (use specific content skills)
  • Video production (use video-caption-creation)
  • Newsletter writing (use opened-daily-newsletter-writer)

Related Skills

  • text-content - Full template library (this skill routes TO those templates)
  • newsletter-to-social - Automated newsletter → social (uses this methodology)
  • opened-identity - Brand voice (always load)
  • ai-tells - Hard blocks (always apply)
  • nano-banana-image-generator - Visual adaptations

Example: Podcast Guest Repurposing

Source: Podcast with Ken Danford about self-directed learning

Step 1: Identify source type → Podcast guest

Step 2: Extract snippets:

  • hot_take: "The best thing a school can do is get out of the way"
  • stat: "75% of North Star teens go to college - without transcripts"
  • story: Ken quit teaching to prove schools are optional

Step 3: Check nearbound → Ken Danford profile exists, @kendanford on X

Step 4: Draft posts:

LinkedIn (Authority):

Ken Danford spent 10 years as a public school teacher.

Then he quit to prove schools are optional.

His self-directed learning center, North Star, has helped hundreds of teens:
- No grades
- No transcripts
- 75% college attendance rate

The secret? "Get out of the way and let them lead."

Full conversation on the OpenEd podcast: [link]

#SelfDirectedLearning #AlternativeEducation #Homeschooling

X:

"The best thing a school can do is get out of the way."

@kendanford quit teaching to prove it. 75% of his students go to college - without transcripts.

[link to episode]

Instagram (Quote card direction):

Visual: Quote card with Ken's face + "Get out of the way and let them lead."
Caption: When a 10-year teacher quits to prove schools are optional... and it works. Link in bio.

#homeschool #selfdirectedlearning #alternativeeducation #unschooling #parentingtips

*Framework fitting is the core technique. This skill specializes in it.*

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

34.13%
按下载量换算43

Claude

33.07%
按下载量换算42

Cursor

17.04%
按下载量换算22

Gemini CLI

8.98%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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