shopify-polaris-app-home

Build your app's primary user interface embedded in the Shopify admin. If the prompt just mentions `Polaris` and you can't tell based off of the context what API they meant, assume they meant this API.

Quality

58%

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-polaris-app-home/SKILL.md

Quality

Content

77%

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

The body is highly actionable with a clear, validated workflow and real bundled scripts. Its main weakness is verbosity from an oversized inline component catalog that overlaps with the search tool, plus minor duplication of the mandatory-tool workflow.

Suggestions

Move the inline `<s-*>` component catalog into a reference file (or rely on `search_docs.mjs`) and keep only a small representative example plus a pointer in SKILL.md.

Consolidate the two "MANDATORY" sections with the "Required Tool Calls" workflow to remove the restated instructions.

Trim the floating "version: unversioned" line and other non-essential prose to recover token budget.

Dimension	Reasoning	Score
Conciseness	Most sections are efficient, but the ~180-line inline `<s-*>` component catalog duplicates what `scripts/search_docs.mjs` retrieves, and the two "MANDATORY" sections restate the "Required Tool Calls" workflow, so it could be tightened.	2 / 3
Actionability	It gives concrete executable commands with full flags (`scripts/search_docs.mjs`, `scripts/validate.mjs`), copy-paste TSX examples, import statements, and explicit ✅/❌ attribute rules — fully actionable guidance.	3 / 3
Workflow Clarity	The "Required Tool Calls" section lays out a clear 5-step sequence (search → write → validate → retry on failure → return) with an explicit validate→fix→re-validate feedback loop and a 3-retry cap, matching the top anchor.	3 / 3
Progressive Disclosure	Referenced scripts (`search_docs.mjs`, `validate.mjs`) are real and one level deep, but the large inline component API reference (lines 50–232) is content that should live in a separate file, fitting the mid anchor.	2 / 3
	Total	10 / 12 Passed

Description

40%

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 domain-specific and acknowledges a real conflict scenario, but it is written in second person, lists only one action, and lacks an explicit "Use when..." trigger. These issues keep most dimensions at the mid level rather than the top.

Suggestions

Rewrite in third-person imperative (e.g., "Builds the app's primary user interface embedded in the Shopify admin") to avoid the second-person voice penalty.

Add an explicit trigger clause such as "Use when building or modifying a Shopify admin app-home UI, or when the user mentions Polaris app home / Shopify admin app UI."

Enumerate a few concrete actions (e.g., compose Polaris web components, configure App Bridge hooks, validate generated code) to lift specificity above a single action.

Dimension	Reasoning	Score
Specificity	It names the domain and one concrete action ("Build your app's primary user interface embedded in the Shopify admin") but lists no further actions; the second-person phrasing "your app" triggers the rubric's -1 voice penalty, dropping it from a base of 2.	1 / 3
Completeness	It answers "what" (build the app's primary UI in the Shopify admin) but the only "when" guidance is an implied disambiguation clause ("If the prompt just mentions `Polaris`...assume they meant this API"), with no explicit "Use when..." trigger, capping completeness at 2.	2 / 3
Trigger Term Quality	It surfaces relevant keywords like `Polaris` and "Shopify admin", but omits common natural variations a developer would say such as "app home", "app-home", or "Shopify admin UI".	2 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (Shopify admin app-home UI) but explicitly acknowledges overlap with other Polaris APIs and relies on a fallback assumption to resolve conflicts, so it could still trigger for a sibling skill.	2 / 3
	Total	7 / 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-polaris-app-home/SKILL.md
Commit: 11c74d6

Reviewed: 3 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.