💡 Summary
ByHeaven Skills offers a monorepo of Claude Code plugins, including an auto publisher for Xiaohongshu.
🎯 Target Audience
🤖 AI Roast: “This repo is like a buffet; a bit of everything but not enough of anything.”
The project may involve network access for plugin installation and could expose sensitive data if not properly secured. Ensure to validate and sanitize inputs to mitigate risks.
ByHeaven Skills
A monorepo of Claude Code skills/plugins by ByHeaven
English | 中文 README
Plugins
- xhs-publisher (
plugins/xhs-publisher) — Xiaohongshu (RED) auto publisher (browser automation)
Installation
This repo supports multiple installation workflows (similar to JimLiu/baoyu-skills).
1) Quick Install (skills CLI)
npx skills add byheaven/byheaven-skills
Or install by cloning this repo and copying a specific skill into your Claude plugins directory:
git clone https://github.com/byheaven/byheaven-skills.git cd byheaven-skills mkdir -p ~/.claude/plugins rsync -a plugins/xhs-publisher/ ~/.claude/plugins/xhs-publisher/
2) Add as Claude Code Plugin Marketplace
In Claude Code, run:
/plugin marketplace add byheaven/byheaven-skills
3) Install a skill/plugin
After adding the marketplace:
- Browse UI: open
/pluginand install from the marketplace - Direct install:
/plugin install xhs-publisher@byheaven-skills
- Or ask the agent:
- “Please install Skills from github.com/byheaven/byheaven-skills”
4) Update
/plugin marketplace update byheaven-skills
Repo structure
Each plugin lives under plugins/<name>/ and is intended to be self-contained (it includes its own .claude-plugin/plugin.json, commands/, skills/, etc.).
License
MIT License
Pros
- Supports multiple installation methods
- Self-contained plugins for easy management
- Focus on automation for Xiaohongshu
Cons
- Limited to specific plugins
- Documentation could be more detailed
- Niche focus may not appeal to all users
Related Skills
some_claude_skills
A“Powerful, but the setup might scare off the impatient.”
ordinary-claude-skills
B“Powerful, but the setup might scare off the impatient.”
pytorch
S“It's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.”
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author byheaven.
