← Back to Skills Marketplace
zhuchenggong19851114-design

Multi Platform Publish

by zhuchenggong19851114-design · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
71
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install multi-platform-publish
Description
根据不同平台要求,生成符合尺寸和风格的封面图、详情长图及文案,支持微信公众号、小红书、抖音和B站发布内容。
Usage Guidance
This skill appears to do what it says (generate platform-specific images and copy), but the instructions assume a local rendering service (http://localhost:3710) and specific template files under skills/auto-contents/references/ that are not bundled. Before installing or using it, verify: (1) Do you actually run a trusted renderer on localhost:3710? If not, the agent may fail or attempt unexpected local network access. (2) The referenced template files are missing from the package — ask the publisher for the template assets or update the instructions to use external, explicit resources. (3) Treat the skill as untrusted until you confirm the source and that any local service it calls is safe; prefer running it only when you explicitly control the local rendering service and templates. If you cannot confirm those, avoid giving this skill runtime access that could let it contact localhost services or read local files.
Capability Analysis
Type: OpenClaw Skill Name: multi-platform-publish Version: 1.0.0 The skill bundle is designed for generating social media content and images tailored for platforms like WeChat, Xiaohongshu, and Bilibili. It utilizes a local API endpoint (localhost:3710) and HTML templates for image rendering as described in SKILL.md. No indicators of data exfiltration, malicious execution, or prompt injection were found.
Capability Assessment
Purpose & Capability
The name/description (multi-platform content + images/copy) aligns with the instructions for generating platform-specific images and text. However, the instructions reference a 'MakeContents render-text' API and local template file paths (skills/auto-contents/references/...) that are not included in the skill bundle, which is inconsistent with an instruction-only skill that claims no local artifacts.
Instruction Scope
SKILL.md directs the agent to POST to a localhost service (http://localhost:3710/api/content/render and a render-text interface) and to use template files under skills/auto-contents/references/*. Those endpoints and file paths are outside the bundled skill and would cause the agent to probe or read local services/files at runtime — behavior not obvious from the skill metadata and potentially unexpected.
Install Mechanism
No install spec (instruction-only) — lowest install risk. Nothing is downloaded or written to disk by an installer.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate for a content-generation helper. The main concern is that it assumes availability of a local rendering service and local template files despite not declaring them.
Persistence & Privilege
always is false and the skill is user-invocable with normal autonomous invocation enabled. No requests to persist or modify other skills or system-wide settings are present.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install multi-platform-publish
  3. After installation, invoke the skill by name or use /multi-platform-publish
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of multi-platform-publish skill. - Supports generating platform-optimized images and copy for WeChat Official Accounts, Xiaohongshu, Douyin/Video Accounts, and Bilibili. - Details per-platform image size, aspect ratio, and copywriting style requirements. - Introduces HTML template rendering for flexible multi-platform cover images. - Provides step-by-step guide for workflow from requirement collection to output. - Includes checklists and templates for common use cases and pre-publish review.
Metadata
Slug multi-platform-publish
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Multi Platform Publish?

根据不同平台要求,生成符合尺寸和风格的封面图、详情长图及文案,支持微信公众号、小红书、抖音和B站发布内容。 It is an AI Agent Skill for Claude Code / OpenClaw, with 71 downloads so far.

How do I install Multi Platform Publish?

Run "/install multi-platform-publish" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Multi Platform Publish free?

Yes, Multi Platform Publish is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Multi Platform Publish support?

Multi Platform Publish is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Multi Platform Publish?

It is built and maintained by zhuchenggong19851114-design (@zhuchenggong19851114-design); the current version is v1.0.0.

💬 Comments