Token导航 LogoToken导航

Agent Skill · 研究检索

content-repurposer(内容再利用者)

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-repurposer 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,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 52,216。

总安装 563周安装 23GitHub Stars 35下载 182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-repurposer(内容再利用者)
来源仓库:https://github.com/superamped/ai-marketing-skills
仓库路径:skills/content-repurposer
安装命令:
npx skills add https://github.com/superamped/ai-marketing-skills --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/superamped/ai-marketing-skills --skill content-repurposer

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-repurposer 辅助文档与内容整理,支持 Markdown、README 等格式优化。适用于提炼结构、统一术语或重组零散材料,提升可读性与一致性。使用时需保留项目已有事实,避免将未确认信息写成确定结论。涉及对外文案时应控制语气,防止过度营销或夸大能力描述。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/content-repurposer

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/superamped/ai-marketing-skills --skill content…;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

    它需要需要联网,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

content-repurposer 怎么安装?

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

content-repurposer 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-repurposer 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

content-repurposer 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-repurposer 用的人多吗?

公开数据是累计安装 563 次,近一周安装 23 次,下载 182 次,GitHub 35 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-repurposer 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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

  • 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-repurposer

内容再利用者 · 本页

56335需要联网未明确有提醒

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 Repurposer

Usage

Use when you've just published a newsletter or blog post and need social content to promote and extend it, repurposing a podcast episode or YouTube video transcript, or getting a full week of social posts from one piece of long-form content.

Process

Step 1: Gather Inputs

Ask the user for:

  1. Long-form content — the hub piece. Can be:

- A newsletter issue (pasted or file path) - A blog post (pasted, file path, or URL to fetch) - A podcast/video transcript - A research doc or set of notes

  1. Target platform (optional) — LinkedIn, Twitter/X, or both (default: both)
  2. Voice/tone — what the brand voice sounds like (casual, professional, witty, etc.)
  3. Target audience — who follows them on social
  4. Newsletter/content link (optional) — URL to link back to in CTA posts
  5. Subscriber/reader count (optional) — for social proof in CTA posts
  6. Number of spokes (optional) — default: 5 (one per template)
  7. Constraints (optional) — things to avoid, compliance requirements

Step 2: Extract the Core from the Hub

Read the long-form content and extract:

  • Main thesis — the one big idea in one sentence
  • Key takeaways — 3-7 specific, actionable points
  • Supporting stories — personal anecdotes, examples, or case studies
  • Data/proof points — any numbers, stats, or results mentioned
  • Contrarian or surprising elements — anything that challenges conventional thinking
  • Tools/resources mentioned — any recommendations, links, or references

Present this extraction to the user as a summary before generating spokes. This ensures nothing important is missed.

Step 3: Generate Spoke Posts

Create one post for each of the spoke templates:


Template 1: Story

Tell a narrative that leads to the hub's key insight.

Structure:

  1. Pain/Attention — Open with a personal story or relatable problem
  2. Agitate — Show how things got worse
  3. Intrigue — Introduce a turning point
  4. Positive Future — Show the benefits
  5. Solution — Bring clarity with a specific action or resource

Rules:

  • First person. This is a story, not a lecture.
  • Short sentences. One idea per line.
  • The opening line must hook.

Template 2: Observation

Share a pattern or insight related to the hub topic.

Structure:

  1. Observation statement — One clear, specific thing you noticed
  2. Evidence — 2-4 specifics that support the observation
  3. Closer — A short, punchy takeaway line

Template 3: Contrarian Take

Challenge a commonly held belief from the hub content.

Structure:

  1. Hot take — State the contrarian position clearly
  2. Supporting points — 3-5 reasons this take is valid
  3. Reframe — End with a new way to think about it

Template 4: Listicle

Curate tools, resources, tips, or takeaways from the hub content.

Structure:

  1. Framing line — "X [things] every [audience] should know about:"
  2. Numbered list — Each item with a name + short description
  3. Optional closer — A recommendation or CTA

Template 5: Meme

Turn the hub's key insight into a meme-format post.

Structure:

  1. Choose a meme format — Match the hub's core tension to a template
  2. Write the caption — The meme does the heavy lifting. Caption adds context.

Rules:

  • Standalone. Understandable without reading the hub content.
  • Use the audience's in-group language.
  • Don't force it. If no natural meme angle, skip and double up on another template.

Template 6: Past vs. Present

Show how the hub topic has evolved — then vs. now.

Structure:

  1. Then — What things looked like before. 3-5 bullet points.
  2. Now — What things look like after. 3-5 bullet points (matching structure).
  3. Lesson — One line that captures the shift.

Step 4: Generate CTA Posts

Create 2 CTA posts to drive traffic back to the hub content:

Pre-Hub CTA (publish the day before or morning of)
{Attention-grabbing opener related to the topic}
{1-2 sentences of context — why this matters}

Here's what I'll cover:
1. {Takeaway 1}
2. {Takeaway 2}
3. {Takeaway 3}

Tomorrow, I'll share this with [XX,XXX] subscribers.

If you want in: {link}
Post-Hub CTA (publish the day after)
{Problem question or pain point}
{1-2 sentences on why most people get this wrong}

Yesterday, [XX,XXX] people got my breakdown on [topic].

Miss it? Grab it here ↓
{link}

CTA rules:

  • If the user provides a subscriber count, use it for social proof.
  • If no count is available, skip that line — don't make one up.
  • The link should be the last element.

Step 5: Tag Content Psychology

Tag each post with its primary emotional trigger:

TriggerWhat it doesPost types that map
EntertainsGenerates awarenessStory, Past vs. Present
TeachesBuilds trustListicle, Observation
EmpathizesDeepens emotional connectionStory (pain-focused), Contrarian
Makes me thinkChallenges preconceptionsContrarian Take, Observation

Flag if the batch is unbalanced. A good week has at least 2 different triggers represented.

Step 6: Platform Adaptation

LinkedIn:

  • First line is everything — shows above the "see more" fold
  • Line breaks generously
  • 1,300 characters is the sweet spot
  • End with a question or conversation starter

Twitter/X:

  • 280 characters for single tweets — ruthlessly edit
  • Threads: first tweet stands alone
  • Listicles and observations compress well into single tweets
  • Stories and contrarian takes work better as threads

Step 7: Build Publishing Schedule

DayPost TypeTrigger
Day 1 (pre-hub)Pre-Hub CTA—
Day 2 (hub day)Hub publishes—
Day 3 (post-hub)Post-Hub CTA—
Day 4StoryEntertains / Empathizes
Day 5ObservationTeaches
Day 6Contrarian TakeMakes me think
Day 7Listicle or Past vs. PresentTeaches / Entertains

Output Format

# Content Repurposed: [Hub Title]

**Date:** [current date]
**Hub:** [title or description of the long-form piece]
**Platform(s):** [LinkedIn / Twitter / Both]
**Posts Generated:** [count]

---

## Hub Summary

**Main thesis:** [one sentence]

**Key takeaways:**
1. [takeaway]
2. [takeaway]
3. [takeaway]

**Stories/examples found:** [brief list]
**Data points found:** [brief list]
**Contrarian angles found:** [brief list]

---

## Spoke Posts

### 1. Story
**Trigger:** [Entertains / Empathizes]

[Full post text]

---

### 2. Observation
**Trigger:** [Teaches / Makes me think]

[Full post text]

---

### 3. Contrarian Take
**Trigger:** [Makes me think]

[Full post text]

---

### 4. Listicle
**Trigger:** [Teaches]

[Full post text]

---

### 5. Past vs. Present
**Trigger:** [Entertains]

[Full post text]

---

## CTA Posts

### Pre-Hub CTA
[Full post text]

### Post-Hub CTA
[Full post text]

---

## Publishing Schedule

| Day | Post | Platform | Trigger |
|-----|------|----------|---------|
| [day] | [post type] | [platform] | [trigger] |

---

## Trigger Balance

| Trigger | Count |
|---------|-------|
| Entertains | X |
| Teaches | X |
| Empathizes | X |
| Makes me think | X |

**Balance:** [Balanced / Leans toward X — consider adding Y]

Rules

  • The hub piece does the heavy thinking. Spokes repackage, they don't rehash. Each spoke should feel like a standalone post, not a summary.
  • Never copy-paste a section of the hub and post it as a spoke. Rewrite for the platform and format.
  • The Story template is the hardest but typically gets the highest engagement. It needs a real narrative arc.
  • Contrarian takes only work if the original content actually has a contrarian angle. Don't manufacture one.
  • CTA posts work best when they give a taste of value before asking for the click.
  • If the hub is thin on material (under 500 words or only 1-2 takeaways), generate 3 spokes instead of 5 and flag that the hub could be expanded.

平台分布

Codex

38.05%
按下载量换算69

Claude

29.41%
按下载量换算54

Cursor

19.21%
按下载量换算35

Gemini CLI

10.07%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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