小红书图片生成

Generates Xiaohongshu (Little Red Book) infographic series with 11 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for X...

This skill largely matches its description (image/style/layout guides) but the runtime instructions will create files on disk (project `.baoyu-skills/baoyu-xhs-images/EXTEND.md` or `~/.baoyu-skills/baoyu-xhs-images/EXTEND.md`) and require completing a 'first-time setup' before doing anything else. Before installing or enabling it: 1) Expect it to write files to your project folder or home directory — review exactly what will be written and where. 2) If you want to limit risk, run the skill in a sandboxed environment or a disposable project repository. 3) Ask the skill author or inspect the upstream repo to confirm the exact file contents and any further file-write behaviors (analysis.md, generated image files). 4) If you do install, consider choosing project-scoped save (not user/global) and check/delete EXTEND.md after first run if you don't want persistent preferences. 5) If you need a safer posture, refuse automatic file writes and require the agent to show the generated YAML/analysis output to you for manual approval before saving.

Type: OpenClaw Skill Name: xhs-images-generator Version: 1.0.0 The baoyu-xhs-images skill bundle is a highly structured tool designed for generating Xiaohongshu (Little Red Book) infographics. It implements a multi-step workflow including content analysis, preference management, and sequential image generation using a reference image chain for visual consistency. The skill uses standard shell commands (e.g., 'test -f') to check for local configuration files (EXTEND.md) and performs file operations within project-specific directories. There is no evidence of data exfiltration, malicious execution, or unauthorized persistence. The instructions in SKILL.md and the reference documents are entirely focused on the stated functional purpose and do not contain malicious prompt injections or hidden payloads.