skills/daily-gzh-content/SKILL.md
# daily-gzh-content — 公众号每日内容生产 > Cron: `daily-gzh-content` | 每日 21:30 | 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** 微信公众号高质量深度文章。 ## 执行流程 ### Step 1: 选题 1. brave-search 搜索 AI 深度热点: ```bash cd ~/.openclaw/skills/brave-search && ./search.js "AI技术深度分析 2026" -n 5 --content ./search.js "A
npx skillsauth add aaaaqwq/agi-super-team skills/daily-gzh-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-gzh-content| 每日 21:30 | 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 微信公众号高质量深度文章。
cd ~/.openclaw/skills/brave-search && ./search.js "AI技术深度分析 2026" -n 5 --content
./search.js "AI行业趋势 2026" -n 5 --content
核心原则:封面必须在 3 秒内传达文章核心观点,吸引点击。
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+金色/白色几何装饰" 这种通用提示词 ✅ 要求:提示词必须包含文章主题的具体物体、场景和隐喻
参数:-a "16:9" -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 "16:9" -r "1k"
📌 标题:
📝 摘要:
📝 正文:
🖼️ 封面提示词:[写出生成的实际提示词]
🖼️ 封面:
⏰ 建议发布:21:00-22:00
保存到 ~/clawd/docs/daily-content/{YYYY-MM-DD}/gzh/
mkdir -p ~/clawd/docs/daily-content/$(date +%Y-%m-%d)/gzh
| Skill | 用途 | |-------|------| | brave-search | 搜索 AI 深度热点 | | humanizer | 去 AI 痕迹 | | relay-image-gen | 生成封面图(16:9) | | content-typography | 中文排版规范 | | content-illustration-strategy | 配图策略 | | content-ops-toolkit | 选题分析、标题优化 |
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.