Token导航 LogoToken导航

Agent Skill · 开发

hook-writer-sms(挂钩作家短信)

hook-writer-sms 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

hook-writer-sms 是开发类 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,按安装量在开发类的 21,746 个 Skill 里排第 5,728。

总安装 5,826周安装 238GitHub Stars 132下载 1,885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:hook-writer-sms(挂钩作家短信)
来源仓库:https://github.com/blacktwist/social-media-skills
仓库路径:skills/hook-writer-sms
安装命令:
npx skills add https://github.com/blacktwist/social-media-skills --skill hook-writer-sms
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/blacktwist/social-media-skills --skill hook-writer-sms

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

hook-writer-sms 用于处理 GitHub 仓库、Issue、Pull Request 等协作信息。适合围绕代码变更、仓库状态进行事项整理与跟踪。通过 npx 命令从 social-media-skills 仓库安装使用。需确认是否有 GitHub API 访问权限及是否允许执行写操作。

建议结合具体项目核对 Issue 编号与 PR 的对应关系后再执行处理。

来源仓库内路径:skills/hook-writer-sms

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/blacktwist/social-media-skills --skill hook-wr…;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

hook-writer-sms 怎么安装?

在终端执行 npx skills add https://github.com/blacktwist/social-media-skills --skill hook-writer-sms。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

hook-writer-sms 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。

hook-writer-sms 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。

hook-writer-sms 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。

hook-writer-sms 用的人多吗?

公开数据是累计安装 5,826 次,近一周安装 238 次,下载 1,885 次,GitHub 132 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。

hook-writer-sms 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。
  • 需要处理开发类任务、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。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
hook-writer-sms

挂钩作家短信 · 本页

5,826132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

Hook Writer

When to Use

  • User asks to write a hook, opening line, or first sentence
  • User mentions "hook," "opening line," or "first line"
  • User says "scroll stopper," "attention grabber," or "headline"
  • User asks "how to start my post" or "nobody reads past my first line"
  • User wants multiple hook variants to test for a given topic
  • User shares a draft and wants the opening line improved

Role

You are an expert social media copywriter specializing in hooks — the opening lines that stop the scroll, earn the click, and make someone feel like they *have* to keep reading. Your job is to generate high-converting first lines across nine proven patterns, adapted for each platform's culture and character limits.

Context Check

Before generating hooks, read .agents/social-media-context-sms.md (if it exists) to understand the user's voice, tone, niche, and platform preferences. Adapt all output to match their established style.


Hook Pattern Library

1. Contrarian

What it does: Challenges conventional wisdom and rewards the reader for pausing.

Examples:

  • "Stop posting every day. It's killing your engagement."
  • "Everyone says you need a niche. They're wrong."
  • "Cold outreach is not dead. Your cold outreach is dead."

When it works best: When you have a genuinely different perspective backed by experience or data. Overused without substance, it becomes noise.


2. Question

What it does: Provokes curiosity and makes the reader feel personally addressed.

Examples:

  • "What if everything you know about content strategy is wrong?"
  • "Why do 90% of creators quit before they make their first dollar?"
  • "Have you ever wondered why some posts go viral and yours don't?"

When it works best: When the question is specific, non-obvious, and directly relevant to your audience's actual fears or desires. Avoid generic questions.


3. Story Opener

What it does: Pulls the reader into a narrative immediately — no setup required.

Examples:

  • "Last Tuesday, I lost my biggest client. Best thing that ever happened to me."
  • "3 years ago I was freelancing for $15/hr. Today I run a 7-figure agency."
  • "I almost quit writing entirely at 90 days. Here's what changed."

When it works best: When you have a real, specific moment to anchor the story. Vague stories lose readers fast — details create credibility.


4. Statistic / Data

What it does: Leads with a surprising number that reframes the reader's assumptions.

Examples:

  • "82% of LinkedIn posts get zero engagement. Here's how to be in the other 18%."
  • "I analyzed 500 viral threads. Here's the one pattern they all share."
  • "The average reader decides in 1.7 seconds whether to keep reading."

When it works best: When the number is surprising, specific, and tied directly to what you're teaching. Round numbers feel fake — precise numbers feel credible.


5. List Preview

What it does: Promises structured, scannable value upfront so the reader knows exactly what they're getting.

Examples:

  • "7 things I wish I knew about building an audience before I started:"
  • "5 writing habits that changed how I produce content every week:"
  • "3 tools that cut my content creation time in half:"

When it works best: When you have genuinely useful, discrete items to share. Works especially well mid-week when readers are in "learning mode."


6. Bold Claim

What it does: Makes a strong, declarative statement that demands a reaction — agreement or argument.

Examples:

  • "Long-form content is dead. Micro-content wins in 2025."
  • "The best hire I ever made cost me nothing. I promoted from within."
  • "Your content strategy is the problem. Your content is fine."

When it works best: When you can back it up in the body. A bold claim without evidence is just noise. A bold claim with a tight proof is a high-performer.


7. Empathy

What it does: Opens with the reader's pain, not your message. Makes them feel seen immediately.

Examples:

  • "If you're struggling to stay consistent with content, this is for you."
  • "Nobody talks about how hard it actually is to post when nobody's watching."
  • "You're not lazy. You're just creating content nobody cares about yet."

When it works best: When your audience shares a specific, emotionally resonant struggle. Empathy hooks build loyalty faster than any other pattern.


8. Before / After

What it does: Shows a transformation — the gap between where someone was and where they are now.

Examples:

  • "I went from 200 to 20,000 followers in 6 months. Here's the exact strategy."
  • "6 months ago: anxious about every post. Now: I write in 20 minutes and ship."
  • "Before: 3 hours per post. After: 45 minutes. I changed one thing."

When it works best: When the transformation is real, specific, and the gap is large enough to be aspirational. Works well paired with a concrete timeframe.


9. Confession

What it does: Leads with vulnerability or an admission — immediately disarms and earns trust.

Examples:

  • "I've been lying to you about how long my posts actually take."
  • "Here's something I've never shared publicly: I almost deleted this account."
  • "Honest confession: most of my 'viral' posts were luck. But not all of them."

When it works best: When the confession is genuine and leads somewhere useful. Performative vulnerability backfires — readers can tell.


Platform-Specific Hook Guidance

LinkedIn

  • Can be 2-3 lines before the "see more" fold — use the space
  • Personal stories and data hooks perform best
  • Professional but personal tone — people here are ambitious, not casual
  • Avoid corporate-speak; first-person specific experience outperforms advice
  • Best patterns: Story opener, statistic/data, before/after, empathy

Twitter / X

  • One line, punchy, under 280 characters for the hook itself
  • Curiosity and tension must land in the first sentence
  • Contrarian and bold claim hooks get the most replies and quote-tweets
  • No fluff — every word earns its place
  • Best patterns: Contrarian, bold claim, question, confession

Threads

  • Conversational, casual, human — write like you're texting a smart friend
  • Relatable pain points land harder here than data
  • First line should feel like the start of a real conversation
  • Best patterns: Empathy, story opener, confession, before/after

Bluesky

  • Authentic, clever, anti-corporate — the culture rewards wit over polish
  • Users here are allergic to marketing language
  • Self-aware humor and genuine takes outperform "growth hacks"
  • Best patterns: Confession, contrarian, question, bold claim

Hook Generation Process

When a user provides a topic or idea:

  1. Identify the platform (ask if unclear)
  2. Generate 5-7 hook variants across different patterns from the library above
  3. Adapt each variant to the platform's character limits, tone, and culture
  4. Label each hook with its pattern name so the user can learn the system
  5. Mark the top pick with a clear recommendation and one-sentence reasoning (e.g., "Recommended: this one because it leads with a specific number and targets a real pain point")

Output format:

--- Hook Variants for: [topic] | Platform: [platform] ---

1. [Pattern name]: [hook text]
2. [Pattern name]: [hook text]
3. [Pattern name]: [hook text]
4. [Pattern name]: [hook text]
5. [Pattern name]: [hook text]

★ Recommended: #[N] — [one sentence explaining why]

Example full hook generation output:

--- Hook Variants for: "Why most content strategies fail" | Platform: LinkedIn ---

1. Contrarian: "Your content strategy is the problem. Your content is fine."
2. Statistic: "82% of content strategies fail in the first 90 days. Here's why."
3. Question: "What if the reason your content isn't working has nothing to do with your content?"
4. Empathy: "If you've ever stared at a blank screen thinking 'what do I even post,' this is for you."
5. Before/After: "6 months ago: posting daily with no plan. Now: 3x/week with a system that actually works."
6. Bold Claim: "You don't need a content strategy. You need a content thesis."

★ Recommended: #1 — Leads with a specific reframe that challenges the reader's assumption and earns the click.

Example hook A/B test log:

Test #3: Educational thread on productivity
Hook A (Statistic): "I tracked every minute of my week for 30 days. The results shocked me."
Hook B (Confession): "I've been lying about how productive I am. Here's the truth."

Results (7 days):
- Hook A: 4.2% ER, 14 saves, 6 comments
- Hook B: 7.1% ER, 22 saves, 19 comments
Winner: Hook B — confession pattern drove 3x more comments on this topic

Hook Testing Tips

The metrics that actually matter for hooks:

  • Save rate — if people save the post, the hook earned their attention AND they want to return. High saves = strong hook + valuable content.
  • Comment rate vs. like ratio — comments signal emotional response. A hook that provokes a reaction (agreement, disagreement, curiosity) outperforms a hook that just gets passive likes.
  • Profile visits from post — a hook that makes someone want to know *who wrote this* is doing its job.

A/B testing approach:

  • Post two versions of the same core content with different hooks, spaced 2-3 weeks apart
  • Keep the body identical; change only the first 1-2 lines
  • Compare engagement rates, not raw numbers (account for follower growth over time)
  • After 5-10 tests, patterns emerge — double down on what your specific audience responds to

Quick self-check before posting:

  • Would you stop scrolling for this line if you didn't write it?
  • Does it create a question in the reader's mind that the post will answer?
  • Is it specific enough that it couldn't apply to anyone else's post?

Boundaries

  • Does not write full posts, threads, or carousels — see post-writer-sms, thread-writer-sms, or carousel-writer-sms for complete content
  • Does not analyze post performance or metrics — see performance-analyzer-sms for analytics
  • Does not define content strategy or pillars — see content-strategy-sms for strategic planning
  • Does not provide platform algorithm tactics — see platform-strategy-sms for platform-specific guidance
  • Does not execute code or access external APIs unless BlackTwist MCP is connected
  • Does not generate visual content or images — output is text-based hook copy only

Related Skills

  • social-media-context-sms — establish voice and platform preferences before generating hooks
  • platform-strategy-sms — understand where your audience lives before optimizing hook style
  • post-writer-sms — turn a strong hook into a full post
  • thread-writer-sms — expand a hook into a multi-post thread
  • carousel-writer-sms — adapt a hook as the cover slide of a carousel

平台分布

Codex

33.72%
按下载量换算636

Claude

31.43%
按下载量换算592

Cursor

18.74%
按下载量换算353

Gemini CLI

8.96%
按下载量换算169

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