Clawhub auto publisher

v1.0.0

Automatically package and publish local skills to ClawHub marketplace with pricing optimization.

0· 290·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The skill's stated purpose is to package and publish skills to ClawHub (including automated pricing). The code scans a local skills directory and suggests prices, which fits the description, but the actual upload implementation is a stub (TODO). Registry metadata lists no required credentials, yet the README and code reference CLAWHUB_API_KEY — this mismatch is unexplained.
!
Instruction Scope
SKILL.md tells users to export CLAWHUB_API_KEY and to run commands with flags like --auto-price and --publish. The shipped publisher.py only honors --dry-run (and an optional skill name via direct filtering) and does not implement --auto-price or --publish. The instructions therefore give users capabilities the code doesn't implement. The script scans ~/.openclaw/workspace/skills and will read SKILL.md and code files in each skill directory — the scope of file access is broad but consistent with a publisher; still, SKILL.md and code disagree about required env vars and flags.
Install Mechanism
There is no install spec and no downloads; the skill is instruction+single Python script. This has lower install risk because nothing external is fetched or written by an installer.
Credentials
SKILL.md instructs setting CLAWHUB_API_KEY and the code reads os.getenv('CLAWHUB_API_KEY'), which is proportionate for a publisher. However, the skill registry metadata did not declare any required env vars or a primary credential — that inconsistency should be resolved before trusting the skill with secrets. The code reads the API key but never uses it (upload is unimplemented).
Persistence & Privilege
The skill does not request always:true and has no install-time persistence. It reads files from a user-local path (~/.openclaw/workspace/skills) which is appropriate for a publisher, but this directory scan is significant — the skill will read all SKILL.md and code files under that path when run.
What to consider before installing
This skill is inconsistent in several ways: SKILL.md instructs you to set CLAWHUB_API_KEY and to run flags (--auto-price, --publish) that the provided publisher.py does not implement; the actual upload function is a TODO (no network calls are present). Before installing or running: (1) verify whether a real upload implementation exists (the publisher currently will only scan and print suggestions), (2) avoid exporting sensitive API keys until you confirm where and how they are used, (3) inspect or run the script in a safe environment (dry-run first) because it will read all SKILL.md and .py files under ~/.openclaw/workspace/skills, and (4) ask the publisher's author or upstream repo for an updated release that documents required env vars in the registry metadata and implements/documents the upload behavior. If you need to test, run it on a sandboxed account or with a dummy API key and ensure no unexpected network activity occurs.

Like a lobster shell, security has layers — review code before you run it.

latestvk9767svmyp79w9wsaasvqackan81yhrb

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📦 Clawdis

SKILL.md

ClawHub Auto Publisher

一键将本地开发的 skills 打包并上架到 ClawHub,自动定价和优化描述。

Features

  • 批量上架: 扫描本地 skills 目录,批量提交
  • 智能定价: 根据复杂度、功能数量自动建议价格
  • SEO 优化: 自动生成关键词和描述
  • 版本管理: 自动递增版本号,记录 changelog

Quick Start

# 配置 ClawHub API
export CLAWHUB_API_KEY=your_key_here

# 扫描并上架所有 skills
python3 publisher.py --auto-price --publish

# 只预览不上架
python3 publisher.py --dry-run

Pricing Strategy

Skill 类型基础价格溢价因素
工具类200-500+API 集成
自动化300-600+多平台支持
赚钱类400-800+收益证明
系统类300-500+监控告警

Requirements

  • Python 3.8+
  • ClawHub API access
  • Git (for version tracking)

Files

2 total
Select a file
Select a file to preview.

Comments

Loading comments…