shopify-storefront-graphql

Use for custom storefronts requiring direct GraphQL queries/mutations for data fetching and cart operations. Choose this when you need full control over data fetching and rendering your own UI. NOT for Web Components - if the prompt mentions HTML tags like <shopify-store>, <shopify-cart>, use storefront-web-components instead.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a tight, actionable validation-driven workflow with clear sequencing and real one-level script references. Its main weakness is repetition of the validate.mjs flags and search command, which costs it the top conciseness score.

Suggestions

Deduplicate the validate.mjs flag list and the artifact-id/revision explanation — state them once and refer back, removing the repeated copy in the 'MANDATORY Validate' section.

Collapse the 'MANDATORY Search Before Writing Code' section into the numbered workflow to avoid restating the search_docs.mjs command a second time.

Reference or document the bundled assets/storefront-graphql_2026-04.json.gz in the body so every bundle file has a clear entry point.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the validate.mjs flags and the artifact-id/revision explanation are stated twice and the 'MANDATORY Search' section re-issues the search command already given in the numbered list. It is not level 3 because the redundancy could be tightened; it is not level 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands — `scripts/search_docs.mjs "<query>"` and `scripts/validate.mjs --code '...'` with every flag specified — plus a concrete predictiveSearch example. It is not level 2 because the guidance is complete and concrete rather than pseudocode or missing key details.	3 / 3
Workflow Clarity	Sequences search → write → validate → (on failure) search the error, fix, re-validate up to 3 retries → return only after validation passes, with explicit validation checkpoints and a feedback loop. It is not level 2 because validation checkpoints are explicit rather than implicit or missing.	3 / 3
Progressive Disclosure	Instructions stay inline and point one level deep to real bundle scripts (`scripts/search_docs.mjs`, `scripts/validate.mjs`, both present), with well-organized sections and easy navigation. It is not level 2 because references are clearly signaled and flat rather than nested or poorly organized; the unreferenced assets file is a minor gap that does not lower the score.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete with explicit 'when' guidance, plus strong disambiguation against the storefront-web-components skill. It is a strong example of the rubric's score-3 anchors across all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'direct GraphQL queries/mutations for data fetching and cart operations' and 'rendering your own UI' — matching the anchor for several specific concrete actions. It is not level 2 because it goes beyond naming only a domain and a couple of actions.	3 / 3
Completeness	Explicitly answers both what (GraphQL queries/mutations for data fetching and cart operations) and when ('Use for custom storefronts requiring...', 'Choose this when you need full control...'). It is not level 2 because the 'when' trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	Uses natural developer terms — 'GraphQL queries/mutations', 'data fetching', 'cart operations', 'custom storefronts' — that a user would plausibly say when needing this skill. It is not level 2 because the keyword coverage is broad rather than missing common variations.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche and explicit negative guidance — 'NOT for Web Components ... use storefront-web-components instead' — making misrouting unlikely. It is not level 2 because the boundary against the nearest competing skill is stated, not merely implied.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/shopify/skills/shopify-storefront-graphql/SKILL.md
Commit: 11c74d6

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.