admin-graphql
Skill2 starsChanged 38 days agoMITView on GitHub
Implement or debug Shopify Admin GraphQL operations, pagination, throttling, and mutations.
In this repository35 other files it gives its agents.
- admin-restSkill
- app-accessibilitySkill
- app-authSkill
- app-billingSkill
- app-bridgeSkill
- app-frameworkSkill
- app-listing-optimizationSkill
- app-market-researchSkill
- app-namingSkill
- app-niche-finderSkill
- app-performanceSkill
- app-pricing-strategySkill
- app-release-readinessSkill
- app-validationSkill
- b2b-marketsSkill
- built-for-shopify-standardsSkill
- dev-troubleshootingSkill
- hydrogen-storefrontSkill
- liquid-themesSkill
- merchant-pain-preventionSkill
- metafields-metaobjectsSkill
- polaris-uiSkill
- shopify-app-store-adsSkill
- shopify-cliSkill
- shopify-connectionsSkill
- shopify-functionsSkill
- shopify-project-copilotSkill
- storefront-apiSkill
- top-app-ux-patternsSkill
- using-shopify-app-builderSkill
- ux-empty-error-statesSkill
- ux-modern-app-feelSkill
- ux-onboardingSkill
- ux-polaris-antipatternsSkill
- webhooksSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Ask only for missing information that changes this task.
- Distinctive: line 18
Use variables and server-side authenticated clients.
- Distinctive: line 24
Test empty pages, multiple pages, access denial, throttling and partial mutation failure.
- Distinctive: line 29
If a field fails, check that exact stable-version schema before expanding scopes.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Read and update store data safely
Start here
GraphQL asks Shopify for specific data; a mutation changes it.
First useful outcome: List products with pagination before adding any write operation. Ask only for missing information that changes this task. Inspect the existing project and use synthetic data before touching a merchant store. Explain the next action and its expected result in plain language; offer a recommended default with its tradeoff.
Guided workflow
- Inspect the app's API version and required scopes; start with a read-only query and synthetic fixtures.
- Use variables and server-side authenticated clients; handle transport errors, GraphQL errors and mutation userErrors separately.
- Paginate with cursors, budget query cost, retry throttling with bounded backoff and preserve per-shop isolation.
- For writes, preview affected records, obtain scope/operation approval, and design idempotency plus recovery.
Check it worked
Test empty pages, multiple pages, access denial, throttling and partial mutation failure; HTTP 200 alone is not success. Report what was changed, what was tested, and what still needs account access or live verification. Do not claim production readiness or approval from generated code alone.
If you get stuck
If a field fails, check that exact stable-version schema before expanding scopes. Give one safe next step and a redacted error example, not a list of speculative fixes.
Safety and optional depth
Use only the user's selected project/accounts. Never read credential caches or request secrets in chat; the operator configures the application's approved secret store. Ask before live deployment, store mutations, billing, publication or paid runs unless that exact action is already authorized. No MCP service is required by this plugin.
For concrete examples in an existing project, read only the relevant section of technical-guide.md. These retained v1.x examples are version-sensitive, not the default template. Verify SDKs, schema fields, CLI flags and platform rules with official documentation before using them.
Example request: "Use admin-graphql to help me with this task. Explain each change and verify it before moving on."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

