plugins/shopify-cli-admin/skills/shopify-admin-api/SKILL.md
This skill should be used when the user asks to "run a GraphQL query on my store", "query the Shopify Admin API", "export products to CSV", "export orders", "export customers", "list products", "get orders", "check inventory", "adjust inventory", "create a product", "delete a product", "set up my dev store", "initialize dev store", "test my Shopify function", "create a test cart", "shopify app execute", "shopify app bulk execute", "bulk operation", "bulk export", or needs to run any Shopify Admin API GraphQL operation via the CLI.
npx skillsauth add alecramos-sudo/storefront-cli-plugin shopify-admin-apiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides procedural knowledge for executing Shopify Admin API operations
using the Shopify CLI. It covers single queries/mutations via shopify app execute
and large-scale data operations via shopify app bulk execute.
Before running any commands, verify the Shopify CLI is available and the user has an app context configured:
shopify version to confirm CLI is installedshopify.app.toml or ask the user for their --client-id and --storeshopify app executeExecute a single GraphQL operation against the Admin API.
Syntax:
# Inline query
shopify app execute --query '{ shop { name id } }' --store STORE_HANDLE
# Query from file
shopify app execute --query-file query.graphql --store STORE_HANDLE
# With variables
shopify app execute --query-file mutation.graphql \
--variables '{"input": {"title": "New Product"}}' \
--store STORE_HANDLE
# Save output to file
shopify app execute --query '{ shop { id } }' \
--store STORE_HANDLE --output-file result.json
Key flags:
| Flag | Purpose |
|------|---------|
| --query / -q | Inline GraphQL string |
| --query-file | Path to .graphql file |
| --variables / -v | Inline JSON variables |
| --variable-file | Path to JSON variables file |
| --store / -s | Target store handle |
| --client-id | App client ID |
| --version | API version (default: latest stable) |
| --output-file | Write result to file |
shopify app bulk executeExecute bulk queries for large datasets (>250 items). Avoids pagination and rate limits.
Syntax:
shopify app bulk execute --query '{ products { edges { node { id title } } } }' \
--store STORE_HANDLE
Bulk operations return JSONL (one JSON object per line). Pipe through jq for
transformation. See references/bulk-operations.md for complete workflow.
--store and --client-id flags, never embed tokensWhen the user describes what they need in natural language:
references/graphql-patterns.md)shopify app execute after user confirmationTriggered when the user says "generate a script", "make this reusable", "save as script", or "create a shell script":
chmod +xConstruct and run single queries. Start simple, refine based on results.
See references/graphql-patterns.md for common patterns.
Export large datasets to CSV. Use shopify app bulk execute, transform with jq.
Use the helper script at ${CLAUDE_PLUGIN_ROOT}/scripts/bulk-to-csv.sh.
See references/bulk-operations.md for the full workflow.
Create products, set inventory, upload images via scripted mutations.
Generate a setup script that can be re-run for new dev stores.
See the /shopify-dev-store-init command for a guided workflow.
Activate Shopify Functions, create test discounts, generate cart permalinks.
Clean up test data after validation.
See the /shopify-function-test command for a guided workflow.
Query products, build cart permalinks with specific variants for testing.
See the /shopify-cart-test command for a guided workflow.
For detailed patterns and techniques, consult:
references/graphql-patterns.md — Common Admin API queries and mutations with variablesreferences/bulk-operations.md — Bulk operation workflow, jq transforms, CSV export${CLAUDE_PLUGIN_ROOT}/scripts/bulk-to-csv.sh — Reusable JSONL-to-CSV transformtools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.