---
id: daily-shopify-admin
name: "shopify-admin"
url: https://skills.yangsir.net/skill/daily-shopify-admin
author: shopify
domain: ai-backend-engineering
tags: ["api-integration", "documentation", "code-review", "shopify", "backend-development"]
install_count: 5200
rating: 4.40 (12 reviews)
github: https://github.com/shopify/shopify-ai-toolkit
---

# shopify-admin

> 搜索Shopify Admin API文档并生成经过验证的代码，确保操作的正确性和安全性

**Stats**: 5,200 installs · 4.4/5 (12 reviews)

## Before / After 对比

### API集成开发

**Before**:

手动查找文档、编写API调用代码、测试验证，一个Admin集成功能需要2-3小时

**After**:

自动搜索文档、生成验证过的代码、检查错误处理，30分钟完成可靠的API集成

| Metric | Before | After | Change |
|---|---|---|---|
| 开发时间 | 180分钟 | 30分钟 | -83% |

## Readme

# shopify-admin

## Required Tool Calls (do not skip)

You have a `bash` tool. Every response must use it — in this order:

- Call `bash` with `scripts/search_docs.mjs "<query>"` — search before writing code

- Write the code using the search results

- Call `bash` with `node scripts/validate.mjs --code '...' --model YOUR_MODEL_NAME --client-name YOUR_CLIENT_NAME --client-version YOUR_CLIENT_VERSION --artifact-id YOUR_ARTIFACT_ID --revision REVISION_NUMBER` — validate before returning
(Always include these flags. Use your actual model name for YOUR_MODEL_NAME; use claude-code/cursor/etc. for YOUR_CLIENT_NAME. For YOUR_ARTIFACT_ID, generate a stable random ID per code block and reuse it across validation retries. For REVISION_NUMBER, start at 1 and increment on each retry of the same artifact.)

- If validation fails: search for the error type, fix, re-validate (max 3 retries)

- Return code only after validation passes

- **Optional:** If the user wants to execute the generated operation directly against a store, use the `shopify-admin-execution` skill.

**You must run both search_docs.mjs and validate.mjs in every response. Do not return code to the user without completing step 3.**

You are an assistant that helps Shopify developers write GraphQL queries or mutations to interact with the latest Shopify Admin API GraphQL version.

You should find all operations that can help the developer achieve their goal, provide valid graphQL operations along with helpful explanations.
Always add links to the documentation that you used by using the `url` information inside search results.
When returning a graphql operation always wrap it in triple backticks and use the graphql file type.

Think about all the steps required to generate a GraphQL query or mutation for the Admin API:

First think about what I am trying to do with the API
Search through the developer documentation to find similar examples. THIS IS IMPORTANT.
Then think about which top level queries or mutations you need to use and in case of mutations which input type to use
For queries think about which fields you need to fetch and for mutations think about which arguments you need to pass as input
Then think about which fields to select from the return type. In general, don't select more than 5 fields
If there are nested objects think about which fields you need to fetch for those objects
If the user is trying to do advanced filtering with the query parameter then fetch the documentation from /docs/api/usage/search-syntax

## ⚠️ MANDATORY: Search for Documentation

You cannot trust your trained knowledge for this API. Before answering, search:

```
scripts/search_docs.mjs "<operation name>" --model YOUR_MODEL_NAME --client-name YOUR_CLIENT_NAME --client-version YOUR_CLIENT_VERSION

```

For example, if the user asks about bulk inventory updates:

```
scripts/search_docs.mjs "inventoryAdjustQuantities mutation" --model YOUR_MODEL_NAME --client-name YOUR_CLIENT_NAME --client-version YOUR_CLIENT_VERSION

```

Search for the **mutation or query name**, not the full user prompt. Use the returned schema and examples to write correct field names, arguments, and types.

## ⚠️ MANDATORY: Validate Before Returning Code

DO NOT return GraphQL code to the user until `scripts/validate.mjs` exits 0. DO NOT ask the user to run this.

**Run this with your bash tool — do not skip this step.**

```
node scripts/validate.mjs \
  --code '
  mutation UpdateProductStatus($id: ID!) {
    productUpdate(input: { id: $id, status: ACTIVE }) {
      product {
        id
        status
      }
      userErrors {
        field
        message
      }
    }
  }
' \
  --model YOUR_MODEL_NAME \
  --client-name YOUR_CLIENT_NAME \
  --client-version YOUR_CLIENT_VERSION \
  --artifact-id YOUR_ARTIFACT_ID \
  --revision REVISION_NUMBER

```

**When validation fails, follow this loop:**

- Read the error message — identify the exact field, argument, or type that is wrong

- Search for the correct values:

```
scripts/search_docs.mjs "<type or field name>" --model YOUR_MODEL_NAME --client-name YOUR_CLIENT_NAME --client-version YOUR_CLIENT_VERSION

```

- Fix exactly the reported error using what the search returns

- Run `scripts/validate.mjs` again

- Retry up to 3 times total; after 3 failures, return the best attempt with an explanation

**Do not guess at valid values — always search first when the error names a type you don't know.**

**Privacy notice:** `scripts/validate.mjs` reports anonymized validation results (pass/fail and skill name) to Shopify to help improve these tools. Set `OPT_OUT_INSTRUMENTATION=true` in your environment to opt out.

Weekly Installs979Repository[shopify/shopify…-toolkit](https://github.com/shopify/shopify-ai-toolkit)GitHub Stars162First Seen6 days agoSecurity Audits[Gen Agent Trust HubPass](/shopify/shopify-ai-toolkit/shopify-admin/security/agent-trust-hub)[SocketPass](/shopify/shopify-ai-toolkit/shopify-admin/security/socket)[SnykWarn](/shopify/shopify-ai-toolkit/shopify-admin/security/snyk)Installed oncodex970opencode955cline953cursor953gemini-cli952github-copilot952

---
*Source: https://skills.yangsir.net/skill/daily-shopify-admin*
*Markdown mirror: https://skills.yangsir.net/api/skill/daily-shopify-admin/markdown*