Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计通过

content-writer-mcbai内容作家麦克拜

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

3,340

周安装

142

GitHub Stars

公开资料未说明

下载量

1,170
OpenClaw

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

MIT-0

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-writer-mcbai(内容作家麦克拜)
来源仓库:https://github.com/mcbaivn/content-writer-mcbai
安装命令:
openclaw skills install content-writer-mcbai
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install content-writer-mcbai

简介

基于研究材料生成多平台社交媒体文案。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

  • 支持 LinkedIn、Twitter/X、TikTok 等平台适配。
  • 输入源数据即可产出符合调性的内容草稿。
  • 建议人工润色后再发布,确保品牌一致性。
  • content-writer-mcbai 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
content-writer
description
Generate high-quality social media posts from research articles and source data. Supports multiple platforms (LinkedIn, Facebook, Twitter/X, TikTok caption, Threads), 6 content formats (Toplist, POV, Case Study, How-to, Story, Hook-List-CTA), multiple tones (default, bold, educational, storytelling, analytical, viral, empathetic, custom), 3 lengths (short/medium/long), and 2 languages (English/Vietnamese). Use this skill whenever the user wants to write a post, create social media content, draft content from research data, generate content in any format, or asks to "write a post", "viết bài", "tạo nội dung", "draft a post", "generate a post from this article", or any content writing from source material.

Content Writer Skill

Installation

npx clawhub@latest install content-writer-mcbai

Generate professional social media posts from research articles. Supports LinkedIn, Facebook, Twitter/X, TikTok caption, Threads — taking source material and producing polished, platform-optimized posts.

When to Use

  • User has articles/data and wants to create social media posts
  • User wants to write a post in a specific format
  • User needs content for any platform: LinkedIn, Facebook, Twitter/X, TikTok, Threads
  • User asks to "write a post", "viết bài", "tạo content" from any source material
  • Works best after using the content-research skill to gather sources

Core Workflow

Step 1: Gather Inputs

Collect from the user (ask if not provided):

  1. Source material (required) — article, URL, summary, or raw data
  2. Platform (default: LinkedIn) — LinkedIn / Facebook / Twitter/X / TikTok / Threads
  3. Content format (default: toplist) — see 6 formats below
  4. Tone (default: default) — see Tone Presets
  5. Length (default: medium) — short/medium/long
  6. Language (default: Vietnamese) — English or Vietnamese
  7. Number of posts (default: 1)

Step 2: Select Format

Read the appropriate format reference file:

FormatFileBest For
📋 Toplistreferences/format-toplist.mdNumbered lists with data
💡 POVreferences/format-pov.mdBold opinions backed by data
🏢 Case Studyreferences/format-case-study.mdDeep-dive one story
🛠️ How-toreferences/format-how-to.mdStep-by-step guides
📖 Storyreferences/format-story.mdNarrative, emotional journey
🎯 Hook-List-CTAreferences/format-hook-list-cta.mdFacebook viral format

Step 3: Apply Platform Rules

Read references/platform-rules.md for platform-specific constraints. Quick reference:

PlatformMax lengthStyleHashtag
LinkedIn3,000 charsProfessional, data-driven3-5 tags
Facebook63,206 charsConversational, emotional, story0-3 tags
Twitter/X280 charsPunchy, hook-heavy1-2 tags
TikTok2,200 chars (caption)Casual, trendy, FOMO5-10 tags
Threads500 charsConversational, casual0-2 tags

Step 4: Build the Prompt

Combine:

  1. Brand context — read references/brand-context.md
  2. Format instructions — from selected format file
  3. Platform rules — from references/platform-rules.md
  4. Source material — articles/data provided
  5. Tone + Language + Length instructions

Step 5: Generate Content

Output rules (non-negotiable):

  • Plain text only — no markdown rendering on social platforms
  • ZERO asterisks — no *, no **
  • No em dashes (—) — use - or comma
  • No source URLs in post body
  • No markdown (#, [], ())
  • Short paragraphs — 1-2 sentences max
  • Data-driven — every claim backed by numbers
  • For emphasis: use CAPS on 1-2 key words
  • Lists: use numbers (1. 2. 3.) or arrows ()
  • Emoji: use naturally per platform style (Facebook/TikTok: more; LinkedIn: 2-3 max)

Step 6: Present and Refine

Offer after generating:

  • Regenerate with different format/tone/length/platform
  • Create variants for A/B testing
  • Generate versions for multiple platforms simultaneously

Format Structures

Toplist

HOOK: Bold claim + specific number
CONTEXT: Why this matters now
LIST: Numbered items with data points
TAKEAWAY: Pattern that emerges
CTA: Engagement question

POV

HOOK: Contrarian bold opening
DATA: Evidence with numbers
ANALYSIS: What this means
PREDICTION: Clear position
CTA: Provocative question

Case Study

HOOK: Most impressive metric
CONTEXT: Problem that existed
WHAT THEY DID: Strategy + numbers
RESULTS: Concrete outcomes
LESSON: Non-obvious takeaway
CTA: Engagement or MCB AI mention

How-to

HOOK: Promise clear outcome
WHY: What people get wrong
STEPS: 3-7 numbered, action verbs
PRO TIP: Non-obvious shortcut
RESULT: What they'll achieve
CTA: "Try step 1 today"

Story (Facebook-optimized)

OPENING SCENE: Specific moment, pulls reader in
TENSION: Problem/conflict builds
TURNING POINT: Insight or decision
RESOLUTION: Outcome + lesson
CTA: Relatable question or tag prompt

Hook-List-CTA (Facebook viral)

HOOK (1 line): Stop-the-scroll — question, shock, or bold claim
BLANK LINE
LIST: 5-10 short punchy items (emoji optional)
BLANK LINE
CTA: "Tag ai cũng cần biết điều này" hoặc câu hỏi

Tone Presets

Read references/tone-presets.md for full details:

ToneStyle
DefaultData-driven, confident, accessible
BoldProvocative, contrarian, strong positions
EducationalTeacher mode, analogies, "here's why"
StorytellingNarrative arc, scenes, emotional
AnalyticalResearch analyst, patterns, comparisons
ViralFOMO-driven, emotional trigger, share-bait
EmpatheticWarm, understanding, community-focused
CustomUser provides own tone description

Length Guidelines

LengthWordsCharsBest for
Short50-100~300-600Twitter/X, Threads, TikTok caption
Medium150-300~800-1800LinkedIn, Facebook standard
Long400-700~2500-4500LinkedIn deep dive, Facebook story

Reference Files

  • references/brand-context.md — MCB AI brand identity + writing rules
  • references/format-toplist.md — Toplist format instructions
  • references/format-pov.md — POV format instructions
  • references/format-case-study.md — Case Study instructions
  • references/format-how-to.md — How-to format instructions
  • references/format-story.md — Story format instructions (Facebook-optimized)
  • references/format-hook-list-cta.md — Hook-List-CTA viral format
  • references/tone-presets.md — All tone details + Viral + Empathetic presets
  • references/platform-rules.md — Platform-specific constraints
  • references/formatting-rules.md — Critical formatting rules (MUST read)

Critical Rules (Non-Negotiable)

  1. ABSOLUTELY NO asterisks (*) anywhere
  2. ABSOLUTELY NO markdown formatting
  3. ABSOLUTELY NO em dashes (—)
  4. ABSOLUTELY NO source URLs in post
  5. Output MUST be plain text only
  6. Emphasis = CAPS on 1-2 words max
  7. Lists = numbers or → arrows only
  8. Emoji = natural, platform-appropriate (not excessive on LinkedIn)

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

补充不同宿主或平台的使用分布数据

能力 5

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

OpenClaw

70.68%
按下载量换算827

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

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。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