ucp

Use when the user wants to use the UCP CLI to find, compare, buy, or track products from online merchants, or to set up and troubleshoot the local UCP profile required for merchant-scoped operations. Covers global catalog search ("find me X under $Y"), named-merchant transactions ("buy this from Z.com"), order tracking, `ucp profile init`, `ucp doctor`, carts, checkout, orders, and UCP setup/help. Falls back to merchant-hosted handoff when direct in-protocol checkout isn't available.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

92%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.

An action-rich, well-sequenced skill body that teaches a complex commerce CLI through executable examples, explicit validation checkpoints, and ordered fallback procedures. Its main weakness is that it is a long monolithic file with no progressive disclosure to bundle reference files for the detailed display/contract material.

Suggestions

Split the detailed display contracts into referenced bundle files — e.g., move the 'Rendering totals (the printer contract)' and 'Display contract for messages' sections into references/totals-rendering.md and references/messages.md, then surface one-line pointers from SKILL.md.

Move the catalog search field-group spec and the get_product/pagination detail into references/catalog-search.md, keeping only the decision table and a concise example in the main body.

Tighten the overlap between the 'How to decide what to do' table, the 'Rule of thumb' note, and the 'Journey heuristics' list, which restate the same business-vs-global guidance in three forms.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with UCP-protocol specifics Claude does not already know (seller.domain vs seller.url, minor currency units, the totals printer contract) and contains no basic-concept padding, so every section earns its place. It is not level 2 because the occasional repetition of the profile-init rule is deliberate enforcement of a safety step rather than unnecessary explanation, though a few heuristic paragraphs could still be tightened.	3 / 3
Actionability	It provides copy-paste-ready commands with real JSON payloads and JMESPath projections — `ucp catalog search --input '{...}' --view '...'`, `ucp cart create`, `ucp checkout complete` — plus specific field rules. It is not level 2 because the examples are fully executable rather than pseudocode and include complete input structures.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced (Cart → Checkout → Complete) with a numbered checkout loop, status interpretation, an ordered error-escalation fallback list, and feedback loops (introspect `--input-schema` on `SCHEMA_VALIDATION_FAILED`, totals-sum verification before completing). It is not level 2 because validation checkpoints and error-recovery loops are explicit, not implicit.	3 / 3
Progressive Disclosure	No bundle files exist in references/, scripts/, or assets/, and the ~255-line body keeps detailed reference material inline — the totals printer contract, the message display obligation table, and the search field-group spec — that could plausibly live in separate reference files. It is not level 3 because there are no one-level-deep external references to offload this detail into, and not level 1 because the document is well organized into clear sections rather than a disorganized wall of text.	2 / 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.

A strong, third-person description that pairs an explicit 'Use when' trigger with a concrete list of supported actions and natural buyer phrasings. It cleanly answers what the skill does and when to invoke it with minimal fluff.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "find, compare, buy, or track products", "global catalog search", "named-merchant transactions", "order tracking", "ucp profile init", "ucp doctor", "carts, checkout, orders" — matching the anchor for multiple specific concrete actions. It is not level 2 because the action list is comprehensive rather than naming only the domain and a few actions.	3 / 3
Completeness	It explicitly answers both halves: "Use when the user wants to use the UCP CLI to find, compare, buy, or track products..." (when) and "Covers global catalog search... carts, checkout, orders, and UCP setup/help" (what). It is not level 2 because the trigger is an explicit 'Use when' clause, not merely implied.	3 / 3
Trigger Term Quality	Natural user phrasings are embedded verbatim — "find me X under $Y", "buy this from Z.com", order tracking, and "set up and troubleshoot" — giving good coverage of terms a buyer would actually say. It is not level 2 because it includes multiple common variations rather than only a single relevant keyword.	3 / 3
Distinctiveness Conflict Risk	The UCP CLI commerce niche with its named-merchant and catalog triggers is a clear, narrow domain unlikely to fire for unrelated skills. It is not level 2 because the triggers ("buy this from Z.com", "find me X under $Y") are specific enough to avoid overlap with general shopping or document skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/shopify/skills/ucp/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.