← Back to Skills Marketplace
301
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install aiznt-xhs
Description
小红书图文排版生成，JSON 入参。Use when: 用户要生成小红书风格多页图文、排版。
README (SKILL.md)
小红书图文 (aiznt-xhs)
服务端将 JSON 转为 form-urlencoded 调上游。
node scripts/xhs.js --body '{"user_text":"标题与正文","page_count":3}'
node scripts/xhs.js
URL 键：xhs_generate。配置见 TsClaw「同步天树凭证」。
Usage Guidance
This skill will send any JSON you provide to whichever endpoint you place in AIZNT_PROXY_URLS.xhs_generate using the TS_TOKEN for Authorization. Before installing: 1) Ensure AIZNT_PROXY_URLS points to a trusted service (the skill will forward whatever data you give it). 2) Treat TS_TOKEN as sensitive — only supply a token with the minimal necessary scope and rotate it if you suspect misuse. 3) Note the minor doc/code mismatch: SKILL.md mentions form-urlencoded but the script sends application/json; confirm the upstream expects JSON. 4) Avoid sending unrelated secrets in the body argument. If you need higher assurance, verify the actual endpoint implementation or run the scripts in a controlled environment first.
Capability Analysis
Type: OpenClaw Skill
Name: aiznt-xhs
Version: 1.0.0
The skill is a straightforward API wrapper for generating Xiaohongshu-style layouts. It reads configuration and authentication tokens from environment variables (TS_TOKEN, AIZNT_PROXY_URLS) and performs a standard POST request to a user-defined endpoint. No evidence of data exfiltration, malicious execution, or prompt injection was found in scripts/xhs.js or SKILL.md.
Capability Assessment
Purpose & Capability
Name/description (XHS layout) match the actual behavior: the skill reads JSON input and POSTs it to a configured xhs_generate endpoint. Requested items (TS_TOKEN and AIZNT_PROXY_URLS) are appropriate for calling an upstream API proxy.
Instruction Scope
Runtime instructions and scripts only read the declared env vars and an optional --body-file. One small inconsistency: SKILL.md says the server converts JSON to form-urlencoded, but the script sends application/json. Otherwise the script stays within the declared purpose and does not access unrelated files or env vars.
Install Mechanism
No install spec; this is an instruction-only skill with small helper scripts. Nothing is downloaded or written during install.
Credentials
Only two env items are required: AIZNT_PROXY_URLS (URL map for proxies) and TS_TOKEN (auth token). Both are relevant and proportional to the skill's operation.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges. It does not modify other skills or system-wide configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install aiznt-xhs - After installation, invoke the skill by name or use
/aiznt-xhs - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Publish from ts-claw bundled-skills
Metadata
Frequently Asked Questions
What is XHS Layout?
小红书图文排版生成，JSON 入参。Use when: 用户要生成小红书风格多页图文、排版。 It is an AI Agent Skill for Claude Code / OpenClaw, with 301 downloads so far.
How do I install XHS Layout?
Run "/install aiznt-xhs" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is XHS Layout free?
Yes, XHS Layout is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does XHS Layout support?
XHS Layout is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created XHS Layout?
It is built and maintained by tianshu (@wangshengli0421); the current version is v1.0.0.
More Skills