Cn Content Matrix

What it does

When your agent uses it

• Tasks that involve Messaging and chat bots
• Tasks that involve Regulatory compliance

Example prompts

• “/cn-content-matrix”

Requirements

• A Bash shell
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent

Workflow steps

12 steps, taken from the step headings in SKILL.md.

1. 1主题调研
2. 2加载平台规范
3. 3内容生成
4. 4输出前自查
5. 5输出
6. 6生成内容核心 (Content Core)
7. 7主题调研
8. 8按平台生成内容
9. 9差异化检查
10. 10生成内容一览表
11. 11读取待审查内容
12. 12加载平台规范

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit
  • Grep
  • Glob
  • WebSearch
  • WebFetch
  • Agent

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Shell), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cn Content Matrix loads about 2.4k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 388 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~89

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~15k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 388 words, ~2,440 tokens.

name

cn-content-matrix

description

Chinese multi-platform content matrix generator — given a topic, auto-generate content adapted for Xiaohongshu, WeChat Official Account, Douyin, and Bilibili with true style transfer (not just reformatting). Supports single-platform generation, full-matrix generation, and compliance review. (中文) 中文多平台内容矩阵：小红书、微信公众号、抖音、B站，真正的风格迁移而非简单格式转换。

allowed-tools

Bash, Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent

user_invocable

true

argument-hint

<command> <args> — 命令: content-gen [主题] [平台] | content-matrix [主题] | content-review [平台] [文件路径]

license

MIT

metadata.version

1.0.0

metadata.author

fullstackcrew

metadata.category

content-creation

metadata.tags

chinese-content, social-media, content-matrix, xiaohongshu, wechat, douyin, bilibili, copywriting

<content-gen>

# 使用当前年份动态构造搜索词，确保结果时效性
CURRENT_YEAR=$(date +%Y)
WebSearch "{主题} 最新趋势 ${CURRENT_YEAR}"
WebSearch "{主题} {平台名} 爆款内容"

Read references/{平台规范文件}.md
Read references/sensitive-words.md

# 将主题转为 URL 友好的 slug（中文保留拼音首字母或原文，英文转小写连字符）
TOPIC_SLUG=$(echo "{主题}" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd '[:alnum:]-_\p{Han}')
OUTPUT_DIR="$HOME/content-output/$(date +%Y-%m-%d)/${TOPIC_SLUG}"
# 如果目录已存在（同主题重复生成），加时间戳后缀避免覆盖
if [[ -d "$OUTPUT_DIR" ]]; then
    OUTPUT_DIR="${OUTPUT_DIR}-$(date +%H%M%S)"
fi
mkdir -p "$OUTPUT_DIR"

---
platform: {平台名}
topic: {主题}
word_count: {字数}
generated_at: {ISO 8601 时间戳}
self_check: PASS / WARNING
---

{正文内容}

</content-gen>

<content-matrix>

Read references/content-core-template.md

# 内容核心 — {主题}

## 1. 核心论点
- 主论点：{一句话总结}
- 支撑论点 1：{论点 + 关键证据}
- 支撑论点 2：{论点 + 关键证据}
- 支撑论点 3：{论点 + 关键证据}

## 2. 关键数据
| 数据点 | 来源 | 用途 |
|--------|------|------|
| {数据1} | {来源} | {在哪个平台/段落使用} |
| {数据2} | {来源} | {用途} |

## 3. 目标受众画像
- **小红书受众**: {年龄、性别、兴趣、痛点、期望}
- **公众号受众**: {年龄、职业、阅读场景、期望深度}
- **抖音受众**: {年龄、使用场景、注意力窗口、互动偏好}
- **B站受众**: {年龄、技术水平、社区文化认同、内容消费习惯}

## 4. 情绪基调
- 核心情绪：{如：惊喜发现 / 深度洞察 / 实用干货 / 趣味科普}
- 小红书情绪变体：{如：闺蜜安利的惊喜感}
- 公众号情绪变体：{如：专业人士的深度解读}
- 抖音情绪变体：{如：打破认知的震撼感}
- B站情绪变体：{如：懂行朋友的技术分享}

## 5. 关键词集
- 通用关键词：{5-10个}
- 小红书关键词：{含种草词、品类词}
- 公众号关键词：{含行业词、趋势词}
- 抖音关键词：{含热搜词、话题词}
- B站关键词：{含技术词、社区词}

# 使用当前年份动态构造搜索词
CURRENT_YEAR=$(date +%Y)
WebSearch "{主题} 最新信息 ${CURRENT_YEAR}"
WebSearch "{主题} 用户评价 体验"
WebSearch "{主题} 行业分析 趋势"

读取所有已生成的平台内容文件

TOPIC_SLUG=$(echo "{主题}" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd '[:alnum:]-_\p{Han}')
OUTPUT_DIR="$HOME/content-output/$(date +%Y-%m-%d)/${TOPIC_SLUG}/matrix"
if [[ -d "$OUTPUT_DIR" ]]; then
    OUTPUT_DIR="$HOME/content-output/$(date +%Y-%m-%d)/${TOPIC_SLUG}-$(date +%H%M%S)/matrix"
fi
mkdir -p "$OUTPUT_DIR"

{主题slug}/matrix/
├── content-core.md          # 内容核心
├── xhs.md                   # 小红书版本
├── wechat.md                # 微信公众号版本
├── douyin.md                # 抖音脚本版本
├── bilibili.md              # B站专栏版本
└── overview.md              # 内容一览表

# 内容矩阵一览 — {主题}

> 生成时间: {ISO 8601}

## 各平台版本对比

| 维度 | 小红书 | 微信公众号 | 抖音 | B站 |
|------|--------|-----------|------|-----|
| 字数 | {N}字 | {N}字 | {N}字(口播) | {N}字 |
| 语气 | {描述} | {描述} | {描述} | {描述} |
| 切入角度 | {描述} | {描述} | {描述} | {描述} |
| 核心卖点 | {描述} | {描述} | {描述} | {描述} |
| CTA | {描述} | {描述} | {描述} | {描述} |
| 特色元素 | {如: 10个hashtag} | {如: 3个数据图表} | {如: 5个画面切换} | {如: 代码块示例} |

## 内容核心摘要

{从 content-core.md 提取的 3 句话摘要}

## 发布建议

| 平台 | 建议发布时间 | 预期效果 | 注意事项 |
|------|------------|---------|---------|
| 小红书 | {时间段} | {预期} | {注意} |
| 微信公众号 | {时间段} | {预期} | {注意} |
| 抖音 | {时间段} | {预期} | {注意} |
| B站 | {时间段} | {预期} | {注意} |

</content-matrix>

<content-review>

Read {用户指定的文件路径}

Read references/{对应平台规范文件}.md
Read references/sensitive-words.md

# 内容审查报告

> **平台**: {平台名}
> **文件**: {文件路径}
> **审查时间**: {ISO 8601}

## 总评: {PASS ✅ / WARNING ⚠️ / FAIL ❌}

综合得分: {N}/60（满分60分，及格36分）

## 逐项评分

| 维度 | 得分 | 状态 | 说明 |
|------|------|------|------|
| 字数 | {N}/10 | {✅⚠️❌} | {说明} |
| 格式结构 | {N}/10 | {✅⚠️❌} | {说明} |
| 语气匹配 | {N}/10 | {✅⚠️❌} | {说明} |
| 敏感词 | {N}/10 | {✅⚠️❌} | {说明} |
| SEO友好度 | {N}/10 | {✅⚠️❌} | {说明} |
| 可发布性 | {N}/10 | {✅⚠️❌} | {说明} |

## 问题详情

### 🔴 必须修改（{N}项）

1. **[{维度}] {问题描述}**
   - 位置：第{N}段 / 第{N}行
   - 当前：`{当前内容}`
   - 建议：`{修改建议}`

### 🟡 建议修改（{N}项）

1. **[{维度}] {问题描述}**
   - 说明：{为什么建议修改}
   - 建议：{修改建议}

### 🟢 可选优化（{N}项）

1. **[{维度}] {优化建议}**
   - 说明：{为什么这样更好}

## 修改后预估

如按以上建议修改，预估综合得分: {N}/60

</content-review>

---
platform: {平台名}
topic: {主题}
word_count: {字数}
generated_at: {ISO 8601}
self_check: PASS / WARNING
warnings: [{如有警告，列出}]
---

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (scripts, references) in skills/cn-content-matrix of LeoYeAI/openclaw-master-skills.

• SKILL.md
• README.md
• _meta.json
• references/bilibili.md
• references/content-core-template.md
• references/douyin.md
• references/sensitive-words.md
• references/wechat-mp.md
• references/xiaohongshu.md
• scripts/content-check.sh

Open the folder on GitHubat commit e5199b5