Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tody-agent/affiliate-productnpx agentmods add skills/tody-agent/affiliate-product/shopee-productWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tody-agent/affiliate-product/shopee-product)<a href="https://agentmods.dev/skills/tody-agent/affiliate-product/shopee-product"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/shopee-product/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tody-agent/affiliate-product/shopee-product"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/shopee-product.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01711 |
| Opus 5.5 | $0.00018 | $0.00684 |
| Sonnet 5.5 | $0.00009 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
shopee-product scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛍️ Shopee Product Intelligence Skill (shopee-product)
Thuộc Plugin: shopee-research
Overview
shopee-product là skill chuyên biệt thuộc bộ plugin shopee-research, phụ trách toàn bộ chu trình thu thập, phân tích và chuẩn hóa dữ liệu sản phẩm từ Shopee (Shopee Mall, Shopee Thường):
- Trích xuất thông số & biến thể: Bóc tách tự động tên, giá gốc, giá sale, % giảm giá, toàn bộ SKU phân loại (màu sắc, tính năng, loại pin, loại kết nối), thông số kỹ thuật và thông tin gian hàng (follower, tổng review, tỷ lệ phản hồi).
- Chọn lọc 10+ Reviews hạt giống (Cò mồi Social Proof): Lọc sạch review rác, gắn nhãn nỗi đau (Pain Point), sự nghi ngại (Objection), trích xuất thông tin media (video/ảnh review) và chấm điểm hữu ích AI (
ai_usefulness_score). - Đánh giá Tiềm Năng Sản Phẩm Win (AI Winning Product Potential): Công thức 5 tiêu chí chấm điểm từ 1 đến 10 để quyết định xem sản phẩm có tiềm năng bùng nổ doanh số khi chạy ads / affiliate hay không.
- Lưu trữ Cấu Trúc SQLite Local: Ghi dữ liệu vào database SQLite chuẩn (
products.db) với indexing phục vụ truy vấn SQL tức thì cho các AI Agent hoặc công cụ render video (affvideo,gflowVeo 3.1).
🎯 Khi Nào Sử Dụng (Triggers)
Kích hoạt skill này khi người dùng:
- Gửi URL sản phẩm Shopee (ví dụ:
https://shopee.vn/...-i.1020310358.44426785177) - Yêu cầu: "Đọc sản phẩm Shopee này", "Lấy dữ liệu giá và biến thể", "Lọc review làm cò mồi", "Đánh giá sản phẩm win", "Lưu vào SQLite"
- Cần nguyên liệu đầu vào có review thực tế để sinh kịch bản video AI TikTok / Shorts / Reels.
🏗️ Quy Trình Thực Thi 4 Bước
flowchart TD
A[URL Shopee / Chrome Tab] --> B[1. Anti-Bot Safe Extraction\nAppleScript UI Stream]
B --> C[2. Data Normalization\nSpecs + 5 SKU Variants + Shop Info]
C --> D[3. Review Curation\nFilter spam -> 10+ High-value Reviews]
D --> E[4. AI Analysis & SQLite Persistence\nWinning Score + products.db + Media Catalog]
E --> F[AI Video Ready\nPayload for affvideo / gflow Veo 3.1]
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 158 lines · 46 tokens per session scan A 6666ad36ef5a
shopee-product is a skill published in the GitHub repository tody-agent/affiliate-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,711 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
shopee-product compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shopee-producttody-agent/affiliate-product | Skill | 2 | 2mo ago | MIT | A | 46 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | yesterday | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | 2d ago | MIT | A | 111 | Claude Code |