Back to Details

content-matrix

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Content Matrix

内容矩阵

CRITICAL: Auto-start on load

重要提示：加载时自动启动

When this skill triggers, go straight to Step 1. Do not summarise. Start input gathering immediately.
当触发此技能时，直接进入步骤1。无需总结，立即开始收集输入信息。

Step 1. Gather inputs

步骤1. 收集输入信息

Check the project for about-me.md. If it exists, read it and pre-fill the description of who the user is. Skip that question and tell the user what you pulled.
If about-me.md is missing, ask:
Give me at least two paragraphs describing who you are, what you do, and what you like to discuss. The more specific you are, the more relevant the ideas.
Wait for response.
Then call AskUserQuestion:
json
[
  {
    "question": "What are your content pillars?",
    "header": "Pillars",
    "multiSelect": false,
    "options": [
      {"label": "I will type them", "description": "I have 3 to 4 content pillars to use"},
      {"label": "Pull from voice.md", "description": "Use the topics already defined in my voice files"},
      {"label": "Suggest them for me", "description": "Based on my about-me.md, recommend 4 pillars"}
    ]
  }
]
If the user types their own, accept 3 to 5 pillars. If fewer than 3, ask for more.
If the user picks "Suggest them for me", read about-me.md, propose 4 pillars covering their positioning, and ask them to confirm or edit before continuing.
检查项目中是否存在about-me.md文件。如果存在，读取该文件并预先填写用户身份描述，跳过相关问题并告知用户提取到的内容。
如果about-me.md文件缺失，请询问：
请提供至少两段文字描述您的身份、工作内容以及您喜欢讨论的话题。描述越具体，生成的创意就越贴合需求。
等待用户回复。
然后调用AskUserQuestion：
json
[
  {
    "question": "What are your content pillars?",
    "header": "Pillars",
    "multiSelect": false,
    "options": [
      {"label": "I will type them", "description": "I have 3 to 4 content pillars to use"},
      {"label": "Pull from voice.md", "description": "Use the topics already defined in my voice files"},
      {"label": "Suggest them for me", "description": "Based on my about-me.md, recommend 4 pillars"}
    ]
  }
]
如果用户自行输入内容支柱，接受3到5个支柱。如果少于3个，请用户补充更多。
如果用户选择“为我推荐”，请读取about-me.md文件，根据用户的定位提出4个内容支柱，并请用户确认或编辑后再继续。

Step 2. Build the matrix

步骤2. 构建矩阵

Generate a markdown table with:
  • X axis (columns): 8 content formats, always in this order:
    1. Actionable
    2. Motivational
    3. Analytical
    4. Contrarian
    5. Observation
    6. X vs Y
    7. Present vs Future
    8. Listicle
  • Y axis (rows): the user's 3 to 5 pillars
Every cell contains one specific, concrete post idea tailored to the pillar and format. Not generic. Not reusable across pillars.
Format definitions to apply when filling each cell:
  • Actionable: Ultra-specific how-to. Teaches the reader to do one thing.
  • Motivational: Inspirational story about someone who did something extraordinary in the niche.
  • Analytical: Breakdown of why something works the way it does.
  • Contrarian: Go against the common advice in the niche and back it up.
  • Observation: A hidden, silent, or underdiscussed trend the user has noticed.
  • X vs Y: Compare two entities (tools, styles, frameworks, companies).
  • Present vs Future: Current state vs a specific prediction, with the why.
  • Listicle: A list of resources, tips, mistakes, lessons, or steps.
Each cell's idea should be a specific headline, not a theme. Good: "The 3-line hook formula I stole from David Ogilvy". Bad: "Hooks".
生成一个markdown表格，包含：
  • X轴（列）：8种内容格式，顺序固定为：
    1. 实操型（Actionable）
    2. 激励型（Motivational）
    3. 分析型（Analytical）
    4. 反常识型（Contrarian）
    5. 观察型（Observation）
    6. X对比Y（X vs Y）
    7. 现状vs未来（Present vs Future）
    8. 清单型（Listicle）
  • Y轴（行）：用户提供的3到5个内容支柱
每个单元格包含一个针对对应支柱和格式的具体、明确的帖子创意，不能通用，也不能跨支柱重复使用。
填充单元格时需遵循以下格式定义：
  • 实操型（Actionable）：超具体的操作指南，教读者完成一件事。
  • 激励型（Motivational）：所在领域中某人完成非凡成就的励志故事。
  • 分析型（Analytical）：拆解某事物运作原理的原因。
  • 反常识型（Contrarian）：违背所在领域的普遍建议，并提供依据支撑。
  • 观察型（Observation）：用户发现的一个隐藏、鲜为人知或讨论度低的趋势。
  • X对比Y（X vs Y）：对比两个实体（工具、风格、框架、公司等）。
  • 现状vs未来（Present vs Future）：当前状态与具体预测的对比，并说明原因。
  • 清单型（Listicle）：资源、技巧、错误、经验或步骤的清单。
每个单元格的创意应为具体标题，而非主题。示例：好的创意——“我从David Ogilvy那里借鉴的3行钩子公式”；不好的创意——“钩子”。

Step 3. Output (surface-aware)

步骤3. 输出（适配场景）

Pick the output mode based on the surface you are running on. Do not output the table in a fenced markdown code block — that renders as monospace plain text and makes a 5×8 grid hard to scan.
  • Claude.ai or Claude Cowork (chat surfaces with interactive chart support): render the matrix as an interactive chart / interactive table widget. Pillars as rows, formats as columns, each cell holding one specific headline. The user should be able to click a cell to see the full headline and any expansion notes. Do not also dump the table as markdown — the chart is the deliverable.
  • Claude Code (file-system surface, has Write/Edit tools): save the matrix to 
    content-matrix-YYYY-MM-DD.md
    in the current working directory and print the same table inline in the response as a plain markdown table (no triple-backtick wrap). Confirm the file path so the user can open it.
  • Fallback (no interactive chart, no file-system tools): output a plain markdown table inline. Still no code-fence wrap.
Below the table or chart, add one sentence naming the single strongest idea across the matrix and why.
根据运行场景选择输出模式。请勿将表格放在带围栏的markdown代码块中——这会渲染为等宽纯文本，导致5×8的网格难以浏览。
  • Claude.ai或Claude Cowork（支持交互式图表的聊天场景）：将矩阵渲染为交互式图表/交互式表格组件。支柱为行，格式为列，每个单元格包含一个具体标题。用户应能点击单元格查看完整标题及扩展说明。请勿同时输出markdown格式的表格——交互式图表即为交付成果。
  • Claude Code（支持文件系统、具备写入/编辑工具的场景）：将矩阵保存到当前工作目录下的
    content-matrix-YYYY-MM-DD.md
    文件中，并在回复中直接输出纯markdown格式的表格（无需三重反引号包裹）。确认文件路径以便用户打开。
  • ** fallback场景（无交互式图表、无文件系统工具）**：直接输出纯markdown格式的表格，同样无需代码块包裹。
在表格或图表下方，添加一句话说明整个矩阵中最优质的创意及其原因。

Step 4. Offer the next move

步骤4. 提供后续操作选项

Ask:
Any cell here you want me to write as a full post? Reference the cell by pillar + format (for example "Hooks × Contrarian") and I will hand it to the post-writer or post-formatter skill.
On Claude Code, also offer to append the drafted post into the same 
content-matrix-YYYY-MM-DD.md
file under the cell reference.
询问：
是否需要我将某个单元格的创意扩展为完整帖子？请通过“支柱+格式”的方式引用单元格（例如“钩子 × 反常识型”），我会将其交给帖子撰写或格式化技能处理。
在Claude Code场景下，还可提供将撰写好的帖子附加到同一
content-matrix-YYYY-MM-DD.md
文件中对应单元格引用下方的选项。

Rules

规则

  • Minimum 3 pillars, maximum 5. More than 5 dilutes the matrix.
  • Every cell idea must be specific to that pillar AND that format. Do not reuse the same idea across pillars.
  • Tune the language to the user's voice if voice.md exists.
  • British English unless voice.md specifies American.
  • Never use em dashes.
  • 内容支柱最少3个，最多5个。超过5个会稀释矩阵效果。
  • 每个单元格的创意必须针对对应支柱和格式，不得跨支柱重复使用。
  • 如果存在voice.md文件，请调整语言风格以匹配用户的语气。
  • 默认使用英式英语，除非voice.md中指定使用美式英语。
  • 禁止使用破折号。