shopify-hydrogen

Hydrogen storefront implementation cookbooks. Some of the available recipes are: B2B Commerce, Bundles, Combined Listings, Custom Cart Method, Dynamic Content with Metaobjects, Express Server, Google Tag Manager Integration, Infinite Scroll, Legacy Customer Account Flow, Markets, Partytown + Google Tag Manager, Subscriptions, Third-party API Queries and Caching. MANDATORY: Use this API for ANY Hydrogen storefront question - do NOT use Storefront GraphQL when 'Hydrogen' is mentioned.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/shopify/skills/shopify-hydrogen/SKILL.md

Quality

Content

47%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 skill has an excellent mandatory search->validate workflow with a real feedback loop, but it is dominated by a ~3,350-line inline TypeScript type dump that wrecks token efficiency and should be split into a reference file. Actionability is medium: concrete script commands exist, but recipe code is deferred to dynamic search.

Suggestions

Move the inline TypeScript component type definitions (lines 60-3414) into a bundled reference file (e.g. references/hydrogen-types.d.ts) and link to it from SKILL.md; drop the unrelated type-fest utility doc comments entirely, since they bloat the context with content already available in the package itself.

Add 1-2 concrete, copy-paste-ready JSX recipe examples inline (e.g. a minimal cart fetch and render) so the skill is actionable without requiring a successful search_docs call first.

Consolidate the duplicated tool-call instructions (the top 'Required Tool Calls' block and the bottom 'MANDATORY: Search/Validate' sections) into a single workflow block to remove redundancy.

Dimension	Reasoning	Score
Conciseness	The body is ~3,350 lines of inline TypeScript type definitions (lines 60-3414), including lengthy type-fest utility doc comments (UnionToIntersection, KeysOfUnion) unrelated to Hydrogen usage — a monolithic dump of content Claude could read from the package's own .d.ts, matching the 'verbose; padded with unnecessary context' anchor.	1 / 3
Actionability	Concrete executable commands are present ("scripts/search_docs.mjs", "scripts/validate.mjs --code '...'" with specific flags), but the actual recipe/JSX code examples are deferred to dynamic search rather than shown inline, leaving key details missing per the anchor-2 'some concrete guidance but incomplete' criterion.	2 / 3
Workflow Clarity	A clearly numbered workflow (search -> write -> validate -> "If validation fails: search for the error type, fix, re-validate (max 3 retries)" -> "Return code only after validation passes") with an explicit validation checkpoint and error-recovery feedback loop, matching the anchor for a clear sequenced process.	3 / 3
Progressive Disclosure	Some structure exists (section headers, real bundle scripts, an external cookbook doc path), but ~3,350 lines of type definitions that should live in a separate reference file are dumped inline — the textbook anchor-2 anti-pattern of 'API reference that could be in a separate file'; not anchor 1 because navigation/structure is present.	2 / 3
	Total	8 / 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 strong description: specific recipe enumeration, explicit positive and negative trigger guidance, and a clear niche that distinguishes it from sibling Storefront GraphQL skills. The only blemish is framing cookbooks as an 'API', which does not undermine trigger clarity.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete recipe capabilities ("B2B Commerce, Bundles, Combined Listings, Custom Cart Method, ... Subscriptions, Third-party API Queries and Caching") beyond just naming the domain, matching the 'lists multiple specific concrete actions' anchor rather than the anchor-2 'names domain and some actions'.	3 / 3
Completeness	States what it does ("Hydrogen storefront implementation cookbooks" plus a recipe list) and when to use it ("Use this API for ANY Hydrogen storefront question"), satisfying both what and when with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes natural terms a developer would say ("Hydrogen storefront", "Hydrogen") plus an explicit trigger ("when 'Hydrogen' is mentioned"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear Hydrogen niche with an explicit anti-conflict directive ("do NOT use Storefront GraphQL when 'Hydrogen' is mentioned"), making overlap with a generic Storefront GraphQL skill unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (3458 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 4 missing, 4 deeper-than-1-level, 24 suspicious	Warning

	Total	14 / 16 Passed

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

Reviewed: 11 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.