shopify-use-shopify-cli

Choose when the user needs **Shopify CLI** to run or fix something now: validate app or extension config on disk (`shopify.app.toml`, `shopify.app.<name>.toml`, `shopify.extension.toml`); run or troubleshoot store workflows (`shopify store auth`, `shopify store execute`); inventory or product changes by handle, SKU, or location name; or CLI setup, auth, upgrade issues. Emphasize **commands and operational steps**, not only authoring GraphQL. Skip for API-only understanding or codegen with no CLI execution. Examples: validate configuration before deploy; run an existing query via CLI; list products; missing `shopify store execute`.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%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.

Highly actionable with concrete commands and flags, but the body is verbose with repeated constraints, offers a flat rather than checkpointed workflow for destructive store operations, and keeps everything inline with no reference-file disclosure. Strong on actionability, weaker on conciseness, workflow structure, and disclosure.

Suggestions

De-duplicate the store execution constraints into one canonical checklist (consolidate the repeated 'do not omit --store/--scopes/--query' rules) to tighten conciseness and reduce overlapping bullets.

Restructure the store execution flow as a numbered sequence with explicit validation checkpoints and an error-recovery loop (e.g., auth fails -> re-auth; execute errors -> inspect output -> fix query -> retry), which matters for destructive --allow-mutations operations.

Extract the larger sections (store execution contract, app configuration validation, CLI analytics attribution) into reference files under references/ and link to them from SKILL.md so the overview stays lean and content is one level deep.

Dimension	Reasoning	Score
Conciseness	Most content is domain-specific operational guidance Claude would not know, but it is padded with redundancy — the same constraints repeated ('Do not omit --store', '--scopes', '--query' restated across multiple bullets) and boundaries restated from the intro ('does not use validate_graphql_codeblocks', 'Pick this topic over shopify-admin') — so it lands at 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: 'npm install -g @shopify/cli@latest', 'shopify app config validate --json', the env-prefixed attribution template, and concrete 'shopify store auth --store ... --scopes ...' + 'shopify store execute --store ... --query ...' command shapes with flag-level detail.	3 / 3
Workflow Clarity	Sequencing exists (numbered 'Order of operations', an 'Execution flow' bullet list) and some validation is referenced, but the store execution flow is a flat ~16-bullet list with implicit checkpoints and no validate->fix->retry error-recovery loop; given destructive store mutations (--allow-mutations), the missing explicit feedback loop caps this at 2.	2 / 3
Progressive Disclosure	No bundle/reference files exist (references/, scripts/, assets/ all absent) and the ~126-line body is a single monolithic file; it is sectioned with headers but content that could be split (store execution contract, app validation, analytics attribution) is inline, matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	9 / 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.

A dense, specific description that clearly states capabilities, natural triggers, a when-to-use boundary, and a skip clause distinguishing it from API-authoring skills. It earns top marks on all four dimensions, though its length flirts with verbosity that the rubric cautions against rewarding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with specific artifacts and commands — 'validate app or extension config on disk (`shopify.app.toml`, `shopify.app.<name>.toml`, `shopify.extension.toml`)', 'run or troubleshoot store workflows (`shopify store auth`, `shopify store execute`)', 'inventory or product changes by handle, SKU, or location name' — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (run/fix Shopify CLI workflows) and when via 'Choose when the user needs Shopify CLI to run or fix something now', plus a 'Skip for API-only understanding or codegen with no CLI execution' negative boundary; the 'Use when'-equivalent trigger is present, so completeness is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural user phrases a developer would say — 'validate configuration before deploy', 'run an existing query via CLI', 'list products', 'missing shopify store execute' — alongside CLI/auth/upgrade trigger language, giving good coverage rather than jargon-only terms.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to CLI execution with an explicit contrast ('Emphasize commands and operational steps, not only authoring GraphQL'; 'Skip for API-only understanding') and named command surfaces, making conflict with adjacent skills like shopify-admin unlikely.	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-use-shopify-cli/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.