← Back to Skills Marketplace
多平台数据聚合
by
yayale-Deng
· GitHub ↗
· v1.0.0
· MIT-0
36
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install crossdata
Description
整合多个电商及社交平台公开数据，提供标准化竞品价格、销量和市场分析，支持多市场多平台的实时查询。
README (SKILL.md)
CrossData
CrossData - 多平台数据聚合技能
功能描述
整合多个电商及社交媒体平台的数据，提供标准化的竞品分析数据，解决单一平台数据孤岛问题。
输入参数
keywords: 搜索关键词（数组），如["USB-C fast charger", "Type-C 快充"]targetMarkets: 目标市场列表，如["Russia", "Brazil", "MiddleEast", "SoutheastAsia", "Europe"]priceRange: 价格区间（美元），如{"min": 5, "max": 50}sourcePlatforms: 数据来源平台，支持["aliexpress", "1688", "tiktok", "amazon"]limit: 每平台最大返回数量，默认 20
输出格式
{
"productData": [
{
"platform": "aliexpress",
"productName": "65W USB-C Fast Charger",
"price": 24.99,
"sales": 2847,
"rating": 4.8,
"shipping": "无忧集运"
}
],
"summary": {
"totalProducts": 50,
"avgPrice": 25.17,
"priceDistribution": {"low": 0.2, "mid": 0.5, "high": 0.3},
"topMarkets": ["Russia", "Brazil"]
}
}
使用示例
{
"keywords": ["USB-C fast charger", "65W Type-C"],
"targetMarkets": ["Russia", "Brazil"],
"priceRange": {"min": 5, "max": 50},
"sourcePlatforms": ["aliexpress", "1688"],
"limit": 30
}
权限说明
- 需要 ClawHub token：
clh_dfYBmWi76_VPBJhUkwRoK8BWpQ4m1IV47bAHieANjVA - 访问多个平台的公开数据权限
- 数据聚合与清洗权限
备注
- 当前版本需 ClawHub token 激活
- 数据刷新频率为实时
- 输出格式支持 JSON/CSV
Usage Guidance
Do not install or use this skill until the author clarifies the following: (1) what 'ClawHub' is and why a single token is sufficient for multiple platforms; (2) whether the token embedded in SKILL.md is a real/active secret (if real, treat it as leaked and rotate it immediately); (3) what network endpoints the skill will call and what data will be sent or stored externally; (4) which credentials (if any) are actually required for each source platform and how they should be provided (env vars, secure storage); and (5) an explicit privacy/data usage policy. If you must proceed, insist on a version that removes hardcoded credentials, declares required env vars, documents endpoints, and limits permissions to least privilege.
Capability Analysis
Type: OpenClaw Skill
Name: crossdata
Version: 1.0.0
The skill documentation (SKILL.md) contains a hardcoded API token (clh_dfYBmWi76_VPBJhUkwRoK8BWpQ4m1IV47bAHieANjVA) within the permissions section. Hardcoding credentials in instructions intended for an AI agent is a significant security vulnerability that could lead to unauthorized access or tracking of the agent's activities, though no executable code was provided to confirm intentional malicious exploitation.
Capability Assessment
Purpose & Capability
The skill's name/description (aggregating e‑commerce and social platform public data) matches the inputs and output schema in SKILL.md. However, for real aggregation you'd normally expect declared API keys or clear scraping guidance for each source (Amazon, TikTok, 1688, AliExpress). The skill does not declare those, instead referencing a single 'ClawHub token' without explaining what ClawHub is or why one token suffices for multiple platforms.
Instruction Scope
SKILL.md does not include explicit commands or endpoints, but it explicitly states '需要 ClawHub token' and embeds a concrete token string. There is no instruction for how the token is passed (env var name), what service endpoints will be called, or what data is transmitted. Embedding a credential in the instructions is a red flag and the lack of endpoint/usage detail makes runtime behavior unclear.
Install Mechanism
Instruction-only skill with no install spec and no code files — this has lower install risk because nothing is written to disk. However, absence of code makes it impossible to verify what network calls would be made at runtime, increasing the need for clarity in the SKILL.md.
Credentials
Registry metadata lists no required env vars, but SKILL.md demands a ClawHub token and even provides a literal token. The token's presence is disproportionate and unexplained: either it's a placeholder (should not be published) or it's a leaked secret. There is no justification for other platform credentials (Amazon, TikTok) or description of least-privilege access.
Persistence & Privilege
The skill does not request always:true or system-wide changes and is user-invocable only. Autonomous invocation is allowed by default but not combined here with other elevated privileges, so no extra persistence/privilege flags are present.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install crossdata - After installation, invoke the skill by name or use
/crossdata - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: AliExpress + 1688 + TikTok data aggregation
Metadata
Frequently Asked Questions
What is 多平台数据聚合?
整合多个电商及社交平台公开数据，提供标准化竞品价格、销量和市场分析，支持多市场多平台的实时查询。 It is an AI Agent Skill for Claude Code / OpenClaw, with 36 downloads so far.
How do I install 多平台数据聚合?
Run "/install crossdata" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 多平台数据聚合 free?
Yes, 多平台数据聚合 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 多平台数据聚合 support?
多平台数据聚合 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 多平台数据聚合?
It is built and maintained by yayale-Deng (@yayale-deng); the current version is v1.0.0.
More Skills