← Back to Skills Marketplace
直播返利助手
by
fangshan101-coder
· GitHub ↗
· v0.1.0
· MIT-0
96
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install live-rebate
Description
直播间购物返利优化工具，追踪各平台热门直播间的商品返利信息，帮助用户在直播购物中获得额外返利。
README (SKILL.md)
直播返利助手
直播间购物场景的返利优化工具。追踪淘宝直播、抖音直播、快手直播等平台热门直播间的商品信息，查询直播专属价叠加返利后的真实到手价，避免冲动消费的同时最大化省钱效果。
触发词
直播返利、直播间省钱、直播购物返利、淘宝直播返利、抖音直播返利、快手直播返利、live rebate、直播带货返利、主播返利
计划实现能力
核心功能
- 直播商品返利查询：输入直播间链接或商品链接，查询该商品是否有返利
- 直播价 vs 日常价对比：对比直播专属价与日常价，判断是否真优惠
- 多平台直播追踪：追踪淘宝直播、抖音、快手等平台的高返利直播间
- 冲动消费防护：购买前展示商品历史价格，避免伪低价陷阱
支持的直播平台
| 平台 | 返利方式 | 特点 |
|---|---|---|
| 淘宝直播 | 淘宝联盟佣金 | 返利比例稳定，品类齐全 |
| 抖音直播 | 精选联盟佣金 | 爆款多，限时秒杀 |
| 快手直播 | 好省等渠道 | 下沉市场，性价比高 |
| 京东直播 | 京东联盟佣金 | 3C数码返利较高 |
| 视频号直播 | 微信生态返利 | 新兴渠道，红利期 |
直播购物决策流程
发现直播间商品
↓
查询返利比例
↓
对比日常价格（是否真低价？）
↓
查看历史价格走势
↓
计算直播价+返利的真实到手价
↓
值得买 → 生成返利链接下单
不值得 → 提示日常购买更划算
使用场景
- 直播间蹲守：主播上链接时快速查询返利，决定是否下单
- 直播预告查询：提前查看即将开播的高返利直播间
- 防坑指南：对比直播价和历史价，识别虚假低价
- 复盘购物：直播结束后核算已下单商品的返利到账情况
输出格式
📺 直播返利查询
直播间：[主播名] - [平台]
商品：[商品名称]
价格对比：
直播价：¥[价格]
日常价：¥[价格]
历史最低：¥[价格]
返利信息：
返利比例：[X]%
返利金额：¥[金额]
真实到手价：¥[最终价格]
📊 购买建议：[值得买/观望/不推荐]
理由：[分析说明]
Usage Guidance
This skill's README promises cross‑platform rebate tracking and automatic rebate link generation but provides no technical details (no API endpoints, no affiliate credentials, no install). Before installing or using it, ask the developer to clarify: (1) exactly which APIs or affiliate programs it integrates with, (2) what credentials/tokens are required and whether they will be stored, (3) how rebate links are generated, (4) what data is collected, transmitted, or stored and where, and (5) whether the skill will ask you to paste session cookies or account tokens. Do not paste account credentials, cookies, or API keys into the chat unless you fully trust the developer and understand how they are used and stored. If the developer cannot provide clear answers, treat the skill as unsafe for sensitive accounts; prefer official affiliate tools or documented APIs instead.
Capability Analysis
Type: OpenClaw Skill
Name: live-rebate
Version: 0.1.0
The skill bundle contains only metadata and descriptive documentation for a live-stream shopping rebate assistant. There is no executable code, network activity, or malicious prompt injection instructions present in the provided files (_meta.json and SKILL.md).
Capability Assessment
Purpose & Capability
The description promises cross‑platform rebate tracking and '生成返利链接下单' (generate rebate links for ordering). Those capabilities normally require platform‑specific affiliate credentials (Taobao/Alibaba, Douyin, Kuaishou, JD, 微信视频号) or an integration mechanism; the skill declares no required env vars, credentials, APIs, or install steps. That is internally inconsistent: either the skill cannot actually perform the claimed actions, or it expects to obtain sensitive credentials at runtime without declaring them.
Instruction Scope
SKILL.md is high level and does not specify how to obtain rebate data, which endpoints/APIs to call, or how links are generated. Phrases like '查询返利比例' and '生成返利链接下单' are vague and grant broad discretion to the agent (e.g., scraping pages, asking for cookies/credentials, or contacting external services). There are no explicit instructions limiting what data to read, store, or transmit.
Install Mechanism
No install spec and no code files — lowest install risk (nothing written to disk by an installer). The skill is instruction‑only, so there is no packaged binary or third‑party download to evaluate.
Credentials
The skill requests no environment variables or credentials, yet its stated features (affiliate link generation, multi‑platform tracking) typically require affiliate IDs, API keys, or access to user session cookies. The absence of declared credentials is disproportionate to the claimed functionality and could mean the agent will request sensitive info at runtime or attempt scraping.
Persistence & Privilege
always:false and no install means the skill does not request permanent presence or elevated platform privileges. It does not declare any modifications to other skills or agent-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install live-rebate - After installation, invoke the skill by name or use
/live-rebate - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
初始发布
Metadata
Frequently Asked Questions
What is 直播返利助手?
直播间购物返利优化工具，追踪各平台热门直播间的商品返利信息，帮助用户在直播购物中获得额外返利。 It is an AI Agent Skill for Claude Code / OpenClaw, with 96 downloads so far.
How do I install 直播返利助手?
Run "/install live-rebate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 直播返利助手 free?
Yes, 直播返利助手 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 直播返利助手 support?
直播返利助手 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 直播返利助手?
It is built and maintained by fangshan101-coder (@fangshan101-coder); the current version is v0.1.0.
More Skills