Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问许可证需确认审计通过

newsletter-to-social社交通讯

Agent Skill

newsletter-to-social 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。

总安装

490

周安装

20

GitHub Stars

4

下载量

158
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:newsletter-to-social(社交通讯)
来源仓库:https://github.com/cdeistopened/opened-vault
仓库路径:skills/newsletter-to-social
安装命令:
npx skills add https://github.com/cdeistopened/opened-vault --skill newsletter-to-social
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 newsletter-to-social

简介

newsletter-to-social 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。

  • 适用于新闻聚合、信息检索、内容筛选等研究检索类任务场景。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和联网需求。
  • 安装前建议核实维护状态、是否会触发命令执行或文件读写操作。
  • 可结合原始 README 文档进一步核验具体功能和使用方法。

SKILL.md

Newsletter/Blog to Social Router

Transform a newsletter or blog post into multiple social suggestions using framework fitting.

Invocation

User says:

  • "social from newsletter" or "social from today's newsletter"
  • "social from [blog post title]"
  • "generate social for [URL]"
  • "/newsletter-to-social"

When to Use

  • After publishing a daily or weekly newsletter
  • After publishing a blog post to Webflow
  • When repurposing any hub content for social
  • For batch social content generation

Output

Posts suggestions to #content-inbox (C0ABV2VQQKS) for triage, not direct scheduling.

The Process

NEWSLETTER
    │
    ├─→ THOUGHT segment → Extract hot take
    │       ├─→ LinkedIn (Contrarian template)
    │       ├─→ X (Paradox Hook)
    │       └─→ Instagram (Quote card)
    │
    ├─→ TREND segment → Extract stat + interpretation
    │       ├─→ LinkedIn (Authority template)
    │       └─→ X (Commentary)
    │
    └─→ TOOL segment → Extract recommendation
            ├─→ LinkedIn (List/How-to)
            └─→ X (Thread: tool + benefits)

Phase 1: Snippet Extraction

Read the newsletter and extract standalone snippets from each segment.

From THOUGHT segment (contrarian take):

  • Core opinion (1-2 sentences)
  • Why it matters
  • Snippet type: hot_take

From TREND segment (data/research):

  • Key stat or finding
  • OpenEd interpretation
  • Snippet type: stat

From TOOL segment (practical advice):

  • Recommendation
  • Why it helps
  • Snippet type: how_to

Output format:

## Extracted Snippets

### Snippet 1 (from THOUGHT)
**Type:** hot_take
**Content:** [1-2 sentence opinion]
**Context:** [why this matters]

### Snippet 2 (from TREND)
**Type:** stat
**Content:** [stat + interpretation]
**Source:** [if external]

### Snippet 3 (from TOOL)
**Type:** how_to
**Content:** [recommendation]
**Benefit:** [what it enables]

Phase 2: Parallel Sub-Agents

For each snippet, spawn parallel platform sub-agents.

Load for all sub-agents:

  1. TEMPLATE_INDEX.md (lightweight index)
  2. opened-identity (brand voice)
  3. ai-tells (hard blocks)

Sub-agent prompt pattern:

You are a [PLATFORM] content specialist for OpenEd.

SNIPPET: [extracted snippet]
TYPE: [hot_take|stat|how_to]

Match to 2-3 best templates from TEMPLATE_INDEX.md.
Generate draft options.
Apply voice constraints.
Return for selection.

Platform-specific routing:

Snippet TypeLinkedInXInstagramFacebook
hot_takeContrarian, StoryParadox Hook, BinaryQuote cardAgree/Disagree
statAuthority, CommentaryCommentary, ThreadCarouselQuestion post
how_toList, TipsThreadCarouselFill-blank

Phase 3: Quality Gate

Apply Lite Quality Loop (3-judge):

  1. AI-Tell Judge (BLOCKING)
  2. Voice Judge (BLOCKING)
  3. Platform Judge (ADVISORY)

Phase 4: Nearbound Check

Before finalizing, check if any people are mentioned:

  1. Search Studio/Nearbound Pipeline/people/ for name
  2. If found, add platform-appropriate @handle to post:

- LinkedIn: Full name or @handle if connected - X: @handle - Instagram: @handle in caption

  1. If not found, note for future profile creation

Phase 5: Post to Content Inbox

Post each suggestion to #content-inbox (C0ABV2VQQKS) using the standard format.

Message format for each suggestion:

*[Hook/Title from post]*
_Newsletter | [Newsletter Title] | [Platform]_

[The draft post content]

OpenEd angle: [Why this works for this platform]
@handles: [Tagged people if any]

Source: [Newsletter URL or title]

Example:

*Your kid's Minecraft addiction might be genius*
_Newsletter | OpenEd Daily 2026-01-28 | LinkedIn_

Every parent worries about screen time.

But here's what the research actually shows: kids who play Minecraft develop stronger spatial reasoning than kids who don't.

The key isn't less screens. It's intentional screens.

OpenEd angle: Contrarian take that validates flexible approaches
@handles: none

Source: OpenEd Daily - Jan 28

Expected output per newsletter:

  • 2-3 LinkedIn suggestions
  • 2-3 X suggestions
  • 1-2 Instagram suggestions (with visual direction)
  • 1-2 Facebook suggestions

Total: 6-9 suggestions posted to #content-inbox for triage

Users react with ✍️ to develop further or ✅ to approve as-is.


Quick Reference

Snippet Type → Template Mapping

TypeBest Templates
hot_takeContrarian, Paradox Hook, Binary Framing, Call BS
statAuthority, Commentary, Data Story
how_toList, Thread, Tips, Do's/Don'ts
quoteQuote + Hot Take, Commentary
storyTransformation, Day-in-Life

Voice Constraints (Always Apply)

  • NO correlatives
  • NO AI-isms
  • Hyphens with spaces
  • Brand account voice

Related Skills

  • text-content - Full template library
  • quality-loop - Quality gates
  • opened-daily-newsletter-writer - Newsletter source
  • x-posting - X/Twitter scheduling

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

36.01%
按下载量换算57

Claude

29.53%
按下载量换算47

Cursor

20.2%
按下载量换算32

Gemini CLI

11.11%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/cdeistopened/opened-vault --skill newsletter-to-social 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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