Filtmall Shopping Skill
Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.
Install
npx skills add filtalgo/Filtmall-Shopping-Skill --skill filtmall-shopping -gclaude mcp add filtmall-shopping-skill -- npx skills add filtalgo/Filtmall-Shopping-Skill --skill filtmall-shopping -g{
"mcpServers": {
"filtmall-shopping-skill": {
"command": "npx",
"args": [
"skills",
"add",
"filtalgo/Filtmall-Shopping-Skill",
"--skill",
"filtmall-shopping",
"-g"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Filtmall Shopping
Agent-native shopping, built for extreme value.
Filtmall Shopping is the official shopping skill from 筛电 (Filtmall/Filtalgo). It gives AI agents live products, same-product and same-specification price evidence, checkout, orders, delivery, and after-sales in one shopping flow. A user can start with one sentence; the agent can find a better-fit product, show where the price advantage comes from, and continue through the transaction when asked.
The current catalog focuses on beauty and personal care. Account authorization, order confirmation, and payment stay with the buyer.
Price advantages with clear boundaries
Filtmall products are often the lowest-priced option online. For some verified products, Filtmall prices can be as low as about one-third of a public price for the same product and specification on a major marketplace. Actual prices vary with account, region, membership, and promotions. The skill shows a price advantage only when the live result includes the matching specification, source platform, and recorded time.
Install
npx skills add filtalgo/Filtmall-Shopping-Skill --skill filtmall-shopping -g
Node.js 18 or later is required. The skill ships with its CLI runtime, so installation needs no separate npm install.
Clients that support folder or ZIP imports can import the repository root directly.
Try it
- “I need a moisturizing facial mask under ¥100 that does not feel sticky.”
- “Compare the first and third products and explain which one fits sensitive skin better.”
- “Did my payment go through?”
- “Where is my latest order?”
The first two prompts exercise product discovery and decision support. The last two continue the shopping journey through order and logistics queries.
What it helps with
| Stage | User outcome |
|---|---|
| Discover | Turn a natural-language request into live product candidates from Filtmall |
| Decide | Compare price, specification, stock, product details, and fit for the stated need |
| Buy | Continue through a persistent cart or an isolated single-SKU BUY_NOW flow |
| Pay | Generate a buyer-facing checkout link for desktop web or mobile H5 |
| Follow up | Query orders and logistics, manage addresses, cancel eligible orders, and enter after-sales workflows |
Why Filtmall is agent-native
- Products that agents can reason over. Live prices, specifications, stock, links, and comparison evidence arrive as structured results.
- One conversation, one shopping journey. Product discovery, purchase, delivery, and after-sales share the same context.
- Extreme value with visible proof. Recommendations can show the external same-specification price, source platform, recorded time, and saving percentage.
- Buyer-controlled account and payment steps. The agent handles repeatable operations; the buyer opens authorization and payment pages and confirms consequential actions.
How it works
flowchart LR
U["Natural-language request"] --> A["AI agent"]
A --> S["Filtmall Shopping Skill"]
S --> F["Filtmall catalog and transaction services"]
F --> A
A --> H["Product, authorization, payment, and order pages"]
The agent uses one command interface:
node scripts/filtalgo.js <command> --json
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…