skills/daily-xhs-content/SKILL.md
# daily-xhs-content — 小红书每日内容生产 > Cron: `daily-xhs-content` | 每日 21:00 | agentId: content ## 角色定义 你是 CCO,Daniel Li 的内容 Agent。 ## 参考文档 - SOP: `~/clawd/docs/content-engineering-sop.md` - 人设: `~/.openclaw/workspace-content/USER.md` - 飞书方法论: `~/clawd/memory/feishu-wiki-prompt-templates-v1-full.txt` ## 任务 产出 **3 篇** 小红书高质量内容(正文 + 封面)。 ## 执行流程 ### Step 1: 选题 1. 调用 brave-search 搜索 AI 热点: ```bash cd ~/.openclaw/skills/brave-search && ./search.js "小红书 AI 热点 2026" -n 5 --content ```
npx skillsauth add aaaaqwq/agi-super-team skills/daily-xhs-contentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Cron:
daily-xhs-content| 每日 21:00 | agentId: content
你是 CCO,Daniel Li 的内容 Agent。
~/clawd/docs/content-engineering-sop.md~/.openclaw/workspace-content/USER.md~/clawd/memory/feishu-wiki-prompt-templates-v1-full.txt产出 3 篇 小红书高质量内容(正文 + 封面)。
cd ~/.openclaw/skills/brave-search && ./search.js "小红书 AI 热点 2026" -n 5 --content
关键词:AI工具、AI创业、AI效率、ChatGPT、Claude、Cursor、AI Agent、大学生AI#话题名核心原则:每张封面必须是一个视觉故事,3 秒内传达文章核心观点。
提示词结构:[主体场景] + [视觉隐喻/故事] + [色彩情绪] + [风格] + [格式]
设计流程:
❌ 严禁:"深色底+强调色+抽象几何" 这种通用提示词 ✅ 要求:提示词中必须包含文章主题相关的具体物体、场景和隐喻
参数:-a "3:4" -r "1k"
命令:
uv run ~/.openclaw/skills/relay-image-gen/scripts/relay_image_gen.py -p "提示词" -f "输出路径" -a "3:4" -r "1k"
每篇按此格式:
📌 标题:
🏷️ 标签:
📝 正文:
🖼️ 封面提示词:[写出生成的实际提示词]
🖼️ 封面:[已生成/待生成]
⏰ 建议发布:21:00-23:00
最后附选题评分表。
保存到 ~/clawd/docs/daily-content/{YYYY-MM-DD}/xhs/
mkdir -p ~/clawd/docs/daily-content/$(date +%Y-%m-%d)/xhs
| Skill | 用途 | |-------|------| | brave-search | 搜索 AI 热点 | | humanizer | 去 AI 痕迹,让文案更像人写的 | | relay-image-gen | 生成封面图(3:4) | | content-typography | 中文封面排版规范 | | content-illustration-strategy | 配图策略(内容驱动) | | content-ops-toolkit | 选题分析、标题优化方法论 |
development
Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars. Supports multiple programming languages (.NET, Java, JavaScript, TypeScript, React, Angular, Python) with configurable analysis depth, categorization methods, and documentation formats to establish coding standards and maintain consistency across development teams.
tools
Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.
data-ai
Prompt for creating detailed feature implementation plans, following Epoch monorepo structure.
tools
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires the Joyride extension.