No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by NimaChu · Codex Skill · ★ 113
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is xiaohongshu-content-creator safe to install? View the security audit →
小红书图文创作 English 是一个跨 Agent 的小红书图文创作技能，不绑定特定编码助手或运行时。Claude Code、OpenCode、OpenClaw、Hermes、Codex，以及其他能够读取 并调用本地脚本或生图工具的 Agent 都可以使用。 技能负责： 调研与事实核验 小红书标题、正文和标签 用“认知锚点”筛选真正值得成页的内容 原创视觉隐喻、文案和分镜 3:4 封面与 9:16 内页 可选择的 IP 与视觉风格档案 让所选 IP 承担每页核心动作 无生图工具时的本地 SVG → PNG 降级 带明确修复动作的发布前 QA 自动选择执行路径 有生图工具 默认使用生图工具。每个项目先选择一个 ，每次生图只传入该档案的一张 ，不会同时传多个角色参考。先生成封面和一张代表性内页，确认角色、隐喻和风格后再生成整套。 分页不按原文段落平均分配，而是选择会改变读者理解的“认知锚点”。每页用三步法从抽象概念找到物理动作和日常物件，再让角色执行这个动作，形成当前主题独有的视觉隐喻。 内置两套视觉档案： 角色资产分别放在 。新增 IP 时只需增加资产与 中的档案配置，现有工作流无需重写。 没有生图工具 自动使用原 本地渲染能力，生成中文稳定、可复现的知识卡式 PNG。它是完整的本地降级方案，但不会伪装成模型生成的漫画插画。 用户明确反馈文字错误 先尝试局部图片编辑或重绘。问题仍未解决时，才使用 SVG 文字覆盖工具修复指定区域。主流程不会为了预防错字而提前拆分文字和插画。 小红书默认规格 默认生成 1 张封面和 5–8 张内页，一页只讲一个核心观点。 核心创作机制 认知锚点选页：只保留核心判断、认知转折、关键对比、断点、边界、常见误区和状态变化；删掉不影响理解的页。 角色承担动作：如果去掉所选角色后隐喻仍完全成立，就重写分镜，让角色真正造成、阻断、修复、转换或揭示结果。 原创视觉隐喻三步法：抽象概念 → 物理动作 → 日常低科技物件；每页一个主结构，不复刻旧构图。 修复闭环 QA：每个问题都记录“缺陷 → 修复动作 → 复检结果”，而不只输出检查清单。 在不同 Agent 中使用 克隆仓库： bash git clone https://github.com
| Stars | 113 |
| Forks | 3 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65.7684342053375/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-26 |
| Created | 2026-03-29 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with xiaohongshu-content-creator for enhanced workflows:
Looking for a xiaohongshu-content-creator alternative? If you're comparing xiaohongshu-content-creator with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autono
Bringing Human Capabilities to AI Agents
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Explore other popular codex skill tools:
xiaohongshu-content-creator is Skill for Xiaohongshu image-and-text creation. It is categorized as a Codex Skill with 113 GitHub stars.
xiaohongshu-content-creator is primarily written in Python. It covers topics such as agent-workflow, article-to-image, infographic-generator.
You can find installation instructions and usage details in the xiaohongshu-content-creator GitHub repository at github.com/NimaChu/xiaohongshu-content-creator. The project has 113 stars and 3 forks, indicating an active community.
xiaohongshu-content-creator is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to xiaohongshu-content-creator on Agent Skills Hub include n8n-claw, browser-operator-core, kindly-web-search-mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: