← 返回 Skills 市场
Visnote Image Creator
作者
katherine0325
· GitHub ↗
· v0.1.0
· MIT-0
100
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install visnote-image-creator
功能描述
This skill should be used when generating XiaoHongShu (小红书) style images. The AI analyzes user requirements, reads template registry to select appropriate te...
安全使用建议
This skill appears to do what it says, but check these before installing:
- Provide the API key only if you trust https://vis-note.netlify.app. The script expects a config.json in the project root (not an environment variable) — the package metadata did not declare this, so you must create the file yourself.
- The script includes your API key in the editor URL query string when it opens the site; query parameters can appear in logs or referer headers, so treat the key as sensitive and rotate it if exposed.
- The skill will read any local image paths you pass (and will write the output image). Only provide files you intend to upload and avoid pointing it at sensitive files.
- It requires Playwright and a Chromium browser (npm install playwright; npx playwright install chromium). Running headless browsers can download browser binaries — review and approve those steps.
- Verify the VisNote API endpoints and the project's GitHub/homepage (URLs in the README and claw.config) independently to confirm authenticity before providing your API key.
- If you need stricter controls, consider running the generate script locally rather than granting an autonomous agent broad filesystem/network access.
功能分析
Type: OpenClaw Skill
Name: visnote-image-creator
Version: 0.1.0
The visnote-image-creator skill is a legitimate automation tool designed to generate social media images via the VisNote web service. It uses Playwright in `scripts/generate-image.mjs` to automate a headless browser, rendering templates with user-provided data and capturing the result. The skill instructions in `SKILL.md` guide the AI to verify local configuration (`config.json`), fetch template metadata from `https://vis-note.netlify.app`, and execute the generation script. While the skill possesses high-privilege capabilities such as shell execution and local file access (for image uploads), these behaviors are transparently documented and strictly aligned with the stated purpose of image creation.
能力标签
能力评估
Purpose & Capability
The skill's name/description align with what it actually does: it selects templates from a remote VisNote registry and drives a headless browser to generate images. One minor inconsistency: the registry metadata lists no required config paths or env vars, but both SKILL.md and scripts/generate-image.mjs require a local config.json containing an apikey. This is expected for the described functionality but the manifest did not declare it.
Instruction Scope
SKILL.md directs the agent to read config.json for an apikey, fetch templates from the VisNote API, and use Playwright-driven automation to upload local images and save an output PNG. The instructions do not ask for unrelated system files or credentials. They do instruct the agent to read local image files (if provided) and config.json, which is coherent with the skill's purpose.
Install Mechanism
There is no install spec (instruction-only skill) but package.json and claw.config list playwright as a dependency. The code requires installing Playwright and a Chromium browser via standard npm/npx commands; no downloads from suspicious URLs or obfuscated installers are present.
Credentials
The skill legitimately needs an API key for the VisNote service, provided via a local config.json. However, the skill metadata did not declare required config paths or environment variables; the agent will look for config.json in the project root. The script also constructs a URL that includes the API key as a query parameter when opening the editor (this is functional but has security implications—see guidance). No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request persistent/always-on inclusion (always:false) and does not modify other skills or system-wide settings. It runs on demand and uses local filesystem access to read config.json and optional image files and to write the output image.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install visnote-image-creator - 安装完成后，直接呼叫该 Skill 的名称或使用
/visnote-image-creator触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
Initial release of visnote-image-creator skill: automate XiaoHongShu-style image generation.
- Analyzes user input, extracts relevant information, and selects suitable templates from a live registry.
- Merges user-provided content with template defaults to generate highly contextual images.
- Fetches and caches template lists using API, with smart cache reuse or refresh based on user request flow.
- Prerequisite check for API Key in config.json before processing any generation requests, with clear user messaging if missing.
- Supports advanced template selection logic based on content type, tags, and user intent.
- Facilitates seamless, automated production of social media cover images and content visuals.
元数据
常见问题
Visnote Image Creator 是什么？
This skill should be used when generating XiaoHongShu (小红书) style images. The AI analyzes user requirements, reads template registry to select appropriate te... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 100 次。
如何安装 Visnote Image Creator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install visnote-image-creator」即可一键安装，无需额外配置。
Visnote Image Creator 是免费的吗？
是的，Visnote Image Creator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Visnote Image Creator 支持哪些平台？
Visnote Image Creator 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Visnote Image Creator？
由 katherine0325（@katherine0325）开发并维护，当前版本 v0.1.0。
推荐 Skills