用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/oyi77/1ai-skills --skill agent-reach-channels命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | agent-reach-channels |
| version | 1.0.0 |
| category | automation |
| domain | automation |
| author | oyi77 |
| license | Apache-2.0 |
| subdomain | workflow-automation |
| description | Use when multi-platform e-commerce and messaging channel extraction (Shopee, TikTok Shop, WeChat) |
| keywords | ["shopee","tiktok-shop","wechat","scraping","commerce","messaging","southeast-asia","indonesia"] |
| tags | ["ecommerce","scraping","agent-reach","shopee","tiktok","wechat"] |
| source | Panniantong/Agent-Reach |
Unified channel extraction framework for Southeast Asian e-commerce (Shopee, TikTok Shop) and Chinese messaging (WeChat).
# Refer to the skill's usage section for specific commands
# Adapt these to your workflow
| Rationalization | Reality |
|---|---|
| "I'll figure it out as I go" | A structured approach saves time and reduces errors. Follow the workflow in this skill rather than improvising. |
| "I already know this topic" | Familiarity breeds shortcuts. Use the checklist to verify you haven't missed critical steps. |
| "This doesn't apply to my situation" | The patterns here generalize across contexts. Adapt, don't skip — the underlying principles hold. |
| "One more tool will fix it" | Adding complexity rarely solves process gaps. Master the core workflow first. |
Backends: shopee-cli (primary), Selenium web scraping (fallback) Auth: Cookie-based (browser login or shopee-cli) Extraction: Product data, reviews, seller info, pricing Regions: .co.id (Indonesia), .com.my (Malaysia), .com.ph (Philippines), .com.sg (Singapore), .com.th (Thailand), .vn (Vietnam)
from agent_reach.channels.shopee import ShopeeChannel
channel = ShopeeChannel()
# Check backend availability
status, msg = channel.check()
# Extract product data
data = channel.extract("https://shopee.co.id/product/123456789")
Backends: tiktok-shop-cli (primary), Playwright web scraping (fallback) Auth: TikTok account login (cookies) Extraction: Products, live streams, seller metrics, engagement data Patterns: /shop/, /live/, seller profiles
from agent_reach.channels.tiktok_shop import TikTokShopChannel
channel = TikTokShopChannel()
# Check backend
status, msg = channel.check()
# Extract shop data
data = channel.extract("https://www.tiktok.com/shop/product/789")
Backends: wechat-cli (primary), Selenium web scraping (fallback) Auth: QR code login or existing session Extraction: Official Account articles, mini-programs, Moments, user profiles Patterns: mp.weixin.qq.com, wechat.com, WeChat IDs
from agent_reach.channels.wechat import WeChatChannel
channel = WeChatChannel()
# Check backend
status, msg = channel.check()
# Extract WeChat data
data = channel.extract("https://mp.weixin.qq.com/s/article123")
Use in:
26/26 tests passing (100%):
pytest tests/test_new_channels.py -v # 26 passed
See the parent skill for authoritative workflow documentation.