菜单
Assign every product a Shopify Standard Product Taxonomy category so AI agents can map a shopper's intent to the right category and surface the store's products.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-product-taxonomy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。
Master skill collection for Shopify store operators. Provides access to all merchandising, marketing, support, and operations capabilities.
Edit the theme's robots.txt.liquid to explicitly allow AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot, Amazonbot) so AI assistants are permitted to read the catalog.
Rewrite thin product descriptions into structured, fact-rich copy (materials, fit, use-cases, the words shoppers actually type) so AI agents have something concrete to quote and match.
基于 SOC 职业分类
正在显示 SKILL.md
| name | shopify-admin-agentic-product-taxonomy |
| role | agentic |
| description | Assign every product a Shopify Standard Product Taxonomy category so AI agents can map a shopper's intent to the right category and surface the store's products. |
| toolkit | shopify-admin, shopify-admin-execution |
| api_version | 2025-01 |
| graphql_operations | ["products:query","taxonomy:query","productUpdate:mutation"] |
| status | stable |
| compatibility | Claude Code, Cursor, Codex, Gemini CLI |
| audit_signals | ["category-taxonomy-api","catalog-intent-alignment"] |
AI shopping agents resolve a query ("running shoes", "office chair", "sustainable sneakers") to a taxonomy node, then retrieve products in that node. Products with no Standard Product Taxonomy category are invisible to that mapping — they only surface on exact keyword luck. This skill finds uncategorized (or mis-categorized) products and assigns the correct Shopify standard taxonomy category, inferred from title/type/tags and confirmed against the live taxonomy tree. Fixes category-taxonomy-api and lifts catalog-intent-alignment.
shopify auth login --store <domain>)read_products, write_productsAll skills accept these universal parameters:
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| store | string | yes | — | Store domain (e.g., mystore.myshopify.com) |
| format | string | no | human | Output format: human (default) or json |
| dry_run | bool | no | false | Preview mutations without executing |
Skill-specific parameters:
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| collection_id | string | no | — | Limit to a collection GID |
| tag | string | no | — | Limit to a product tag |
| only_missing | bool | no | true | If true, only assign products with no category; if false, also review mismatches |
| confidence_floor | float | no | 0.7 | Skip products whose best taxonomy match scores below this |
⚠️ Step 4 (
productUpdate) sets thecategoryon live products, which affects storefront facets, marketplaces, and tax. A wrong category mis-files a product everywhere. Run , review the proposed mapping, and only auto-assign matches above ; queue the rest for human review.
dry_run: trueproduct → categoryconfidence_floorOPERATION: products — query
Inputs: first: 250, optional filter; fields title, productType, tags, category{ id fullName }; paginate.
Expected output: Products with their current category (or null).
OPERATION: taxonomy — query
Inputs: search the standard taxonomy tree by candidate terms derived from each product's type/title.
Expected output: Candidate taxonomy category nodes (id + fullName) to match against.
COMPUTE (no API): score each product against candidate nodes; pick the best ≥ confidence_floor. Emit the proposed mapping.
OPERATION: productUpdate — mutation
Inputs: { id, category: <taxonomyCategoryId> } per confident match.
Expected output: Updated product category; collect userErrors.
# products:query — validated against api_version 2025-01
query TaxonomyProducts($first: Int!, $after: String, $query: String) {
products(first: $first, after: $after, query: $query) {
edges {
node {
id
title
productType
tags
category { id fullName }
}
}
pageInfo { hasNextPage endCursor }
}
}
# taxonomy:query — validated against api_version 2025-01
query TaxonomySearch($search: String) {
taxonomy {
categories(first: 20, search: $search) {
edges { node { id fullName isLeaf level } }
}
}
}
# productUpdate:mutation — validated against api_version 2025-01
mutation TaxonomyAssign($input: ProductInput!) {
productUpdate(input: $input) {
product { id category { id fullName } }
userErrors { field message }
}
}
Claude MUST emit the following output at each stage. This is mandatory.
On start, emit:
╔══════════════════════════════════════════════╗
║ SKILL: <skill name> ║
║ Store: <store domain> ║
║ Started: <YYYY-MM-DD HH:MM UTC> ║
╚══════════════════════════════════════════════╝
After each step, emit:
[N/TOTAL] <QUERY|MUTATION> <OperationName>
→ Params: <brief summary of key inputs>
→ Result: <count or outcome>
If dry_run: true, prefix every mutation step with [DRY RUN] and do not execute it.
On completion, emit:
For format: human (default):
══════════════════════════════════════════════
OUTCOME SUMMARY
<Metric label>: <value>
Errors: 0
Output: <filename or "none">
══════════════════════════════════════════════
For format: json, emit:
{
"skill": "<skill-slug>",
"store": "<domain>",
"started_at": "<ISO8601>",
"completed_at": "<ISO8601>",
"dry_run": false,
"steps": [
{
"step": 1,
"operation": "<OperationName>",
"type": "query",
"params_summary": "<string>",
"result_summary": "<string>",
"skipped": false
}
],
"outcome": {
"metric_key": 0,
"errors": 0,
"output_file": null
}
}
human: count categorized + a CSV (product, old_category, new_category, confidence) and a "needs review" list below the floor. json: { categorized, needs_review, errors, output_file }.
| Error | Cause | Recovery |
|---|---|---|
THROTTLED | API rate limit | Wait 2s, retry up to 3 times |
| No taxonomy match | Niche/ambiguous product | Add to needs-review list, do not guess |
userErrors on update | Invalid category id | Log, skip, continue |
only_missing: true for the first pass; re-categorizing existing assignments is higher-risk and best reviewed.shopify-admin-agentic-readiness-audit to confirm the Matchable pillar improved.