菜单
Auto-generate matching hero and inline images for blog posts. The agent reads the content, derives visual prompts, and produces a ready-to-use image set.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/dvcrn/openclaw-skills-marketplace --skill blog-image-claw-skill命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
监控 OpenClaw GitHub 版本更新，获取最新版本发布说明，翻译成中文， 并推送到 Telegram 和 Feishu。用于：(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
基于 SOC 职业分类
正在显示 SKILL.md
| name | blog-image-claw-skill |
| description | Auto-generate matching hero and inline images for blog posts. The agent reads the content, derives visual prompts, and produces a ready-to-use image set. |
The agent reads blog content (text, file, or URL), derives visual prompts for the hero and each key section, then calls blogimg.js to generate images.
node blogimg.js gen "<visual_prompt>" --size header|inline
# → {"status":"SUCCESS","url":"https://...","width":1024,"height":576}
The agent handles all content analysis. The script only calls the image generation API.
NETA_TOKEN=your_token_here
in ~/.openclaw/workspace/.env