← 返回 Skills 市场
mcbaivn

Content Writer - MCB AI

作者 MCB AI · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
114
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install content-writer-mcbai
功能描述
Generate high-quality social media posts from research articles and source data. Supports multiple platforms (LinkedIn, Facebook, Twitter/X, TikTok caption,...
使用说明 (SKILL.md)

\r \r

Content Writer Skill\r

Installation

npx clawhub@latest install content-writer-mcbai

\r 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.\r \r

When to Use\r

\r

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

Core Workflow\r

\r

Step 1: Gather Inputs\r

\r Collect from the user (ask if not provided):\r \r

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

Step 2: Select Format\r

\r Read the appropriate format reference file:\r \r | Format | File | Best For |\r |--------|------|----------|\r | 📋 Toplist | references/format-toplist.md | Numbered lists with data |\r | 💡 POV | references/format-pov.md | Bold opinions backed by data |\r | 🏢 Case Study | references/format-case-study.md | Deep-dive one story |\r | 🛠️ How-to | references/format-how-to.md | Step-by-step guides |\r | 📖 Story | references/format-story.md | Narrative, emotional journey |\r | 🎯 Hook-List-CTA | references/format-hook-list-cta.md | Facebook viral format |\r \r

Step 3: Apply Platform Rules\r

\r Read references/platform-rules.md for platform-specific constraints. Quick reference:\r \r | Platform | Max length | Style | Hashtag |\r |----------|-----------|-------|---------|\r | LinkedIn | 3,000 chars | Professional, data-driven | 3-5 tags |\r | Facebook | 63,206 chars | Conversational, emotional, story | 0-3 tags |\r | Twitter/X | 280 chars | Punchy, hook-heavy | 1-2 tags |\r | TikTok | 2,200 chars (caption) | Casual, trendy, FOMO | 5-10 tags |\r | Threads | 500 chars | Conversational, casual | 0-2 tags |\r \r

Step 4: Build the Prompt\r

\r Combine:\r

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

Step 5: Generate Content\r

\r Output rules (non-negotiable):\r

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

Step 6: Present and Refine\r

\r Offer after generating:\r

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

Format Structures\r

\r

Toplist\r

HOOK: Bold claim + specific number\r
CONTEXT: Why this matters now\r
LIST: Numbered items with data points\r
TAKEAWAY: Pattern that emerges\r
CTA: Engagement question\r
```\r
\r
### POV\r
```\r
HOOK: Contrarian bold opening\r
DATA: Evidence with numbers\r
ANALYSIS: What this means\r
PREDICTION: Clear position\r
CTA: Provocative question\r
```\r
\r
### Case Study\r
```\r
HOOK: Most impressive metric\r
CONTEXT: Problem that existed\r
WHAT THEY DID: Strategy + numbers\r
RESULTS: Concrete outcomes\r
LESSON: Non-obvious takeaway\r
CTA: Engagement or MCB AI mention\r
```\r
\r
### How-to\r
```\r
HOOK: Promise clear outcome\r
WHY: What people get wrong\r
STEPS: 3-7 numbered, action verbs\r
PRO TIP: Non-obvious shortcut\r
RESULT: What they'll achieve\r
CTA: "Try step 1 today"\r
```\r
\r
### Story (Facebook-optimized)\r
```\r
OPENING SCENE: Specific moment, pulls reader in\r
TENSION: Problem/conflict builds\r
TURNING POINT: Insight or decision\r
RESOLUTION: Outcome + lesson\r
CTA: Relatable question or tag prompt\r
```\r
\r
### Hook-List-CTA (Facebook viral)\r
```\r
HOOK (1 line): Stop-the-scroll — question, shock, or bold claim\r
BLANK LINE\r
LIST: 5-10 short punchy items (emoji optional)\r
BLANK LINE\r
CTA: "Tag ai cũng cần biết điều này" hoặc câu hỏi\r
```\r
\r
## Tone Presets\r
\r
Read `references/tone-presets.md` for full details:\r
\r
| Tone | Style |\r
|------|-------|\r
| Default | Data-driven, confident, accessible |\r
| Bold | Provocative, contrarian, strong positions |\r
| Educational | Teacher mode, analogies, "here's why" |\r
| Storytelling | Narrative arc, scenes, emotional |\r
| Analytical | Research analyst, patterns, comparisons |\r
| Viral | FOMO-driven, emotional trigger, share-bait |\r
| Empathetic | Warm, understanding, community-focused |\r
| Custom | User provides own tone description |\r
\r
## Length Guidelines\r
\r
| Length | Words | Chars | Best for |\r
|--------|-------|-------|---------|\r
| Short | 50-100 | ~300-600 | Twitter/X, Threads, TikTok caption |\r
| Medium | 150-300 | ~800-1800 | LinkedIn, Facebook standard |\r
| Long | 400-700 | ~2500-4500 | LinkedIn deep dive, Facebook story |\r
\r
## Reference Files\r
\r
- `references/brand-context.md` — MCB AI brand identity + writing rules\r
- `references/format-toplist.md` — Toplist format instructions\r
- `references/format-pov.md` — POV format instructions\r
- `references/format-case-study.md` — Case Study instructions\r
- `references/format-how-to.md` — How-to format instructions\r
- `references/format-story.md` — Story format instructions (Facebook-optimized)\r
- `references/format-hook-list-cta.md` — Hook-List-CTA viral format\r
- `references/tone-presets.md` — All tone details + Viral + Empathetic presets\r
- `references/platform-rules.md` — Platform-specific constraints\r
- `references/formatting-rules.md` — Critical formatting rules (MUST read)\r
\r
## Critical Rules (Non-Negotiable)\r
\r
1. ABSOLUTELY NO asterisks (*) anywhere\r
2. ABSOLUTELY NO markdown formatting\r
3. ABSOLUTELY NO em dashes (—)\r
4. ABSOLUTELY NO source URLs in post\r
5. Output MUST be plain text only\r
6. Emphasis = CAPS on 1-2 words max\r
7. Lists = numbers or → arrows only\r
8. Emoji = natural, platform-appropriate (not excessive on LinkedIn)\r
\r
\r
安全使用建议
This skill is instruction-only and does not ask for credentials or install external code, so its immediate technical risk is low. Before installing, consider: (1) review the reference files (brand-context and formatting rules) to ensure you accept the required brand mentions and strict no-URL/no-asterisk output rules; (2) avoid pasting sensitive private documents as 'source material'—the skill will use any provided text to generate posts; (3) the skill requires numeric data for many outputs—if you supply vague sources it may fabricate specific numbers, so verify all data-backed claims before publishing; (4) README shows an npx install example, but the registry has no install spec here—confirm the installation method you plan to use comes from a trusted source; and (5) note the small internal inconsistency about default language (English vs Vietnamese) and the mention of a separate content-research skill — this affects usability but not security.
功能分析
Type: OpenClaw Skill Name: content-writer-mcbai Version: 1.0.0 The content-writer-mcbai skill is a legitimate tool designed to transform research data into social media posts for platforms like LinkedIn and Facebook. It utilizes a structured workflow involving multiple reference files (e.g., format-toplist.md, platform-rules.md) to guide the AI agent's output. The strict formatting constraints, such as the prohibition of markdown and asterisks, are functional requirements to ensure the generated text is compatible with social media platforms that do not support markdown rendering. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
The skill's name and description (generate platform-optimized social posts from source material) match the provided instructions and reference files. Minor inconsistencies: SKILL.md's Step 1 lists default language as Vietnamese while references/brand-context.md states default English unless Vietnamese is requested. The SKILL.md also says it 'works best after using the content-research skill' even though no such dependency is declared in the registry metadata — this is a usability note, not a security mismatch.
Instruction Scope
All runtime instructions are about composing posts from user-provided source material and internal reference files. The skill asks the agent to read local reference files (packaged with the skill) and to request source material from the user. It does not instruct the agent to read system files, environment variables, or contact external endpoints. It enforces strict output formatting (no URLs, no asterisks) and requests data-backed claims, which is functional but could lead to hallucinated numeric claims if the user-provided source lacks numbers.
Install Mechanism
There is no install spec in the registry entry and no code files that would be executed; the package is instruction-only. The README contains an example 'npx clawhub@latest install content-writer-mcbai' but that is documentation only — the registry shows no automatic installer or download-from-URL behavior to review.
Credentials
The skill requires no environment variables, no credentials, and no special config paths. All required inputs are user-provided content and format/tone/platform options, which are proportionate to the stated purpose.
Persistence & Privilege
The skill is not marked 'always' and does not request any elevated persistence or cross-skill configuration changes. Autonomous invocation is allowed by default (platform behavior) but is not combined with other red flags here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install content-writer-mcbai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /content-writer-mcbai 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release by MCB AI
元数据
Slug content-writer-mcbai
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Content Writer - MCB AI 是什么?

Generate high-quality social media posts from research articles and source data. Supports multiple platforms (LinkedIn, Facebook, Twitter/X, TikTok caption,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 114 次。

如何安装 Content Writer - MCB AI?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install content-writer-mcbai」即可一键安装,无需额外配置。

Content Writer - MCB AI 是免费的吗?

是的,Content Writer - MCB AI 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Content Writer - MCB AI 支持哪些平台?

Content Writer - MCB AI 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Content Writer - MCB AI?

由 MCB AI(@mcbaivn)开发并维护,当前版本 v1.0.0。

💬 留言讨论