CtrlK
BlogDocsLog inGet started
Tessl Logo

shopify-automation

Automate Shopify tasks via Rube MCP (Composio): products, orders, customers, inventory, collections. Always search tools first for current schemas.

47

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/shopify-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%Scale 1-5

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

This skill provides a reasonable catalog of Shopify tools available through Rube MCP, but suffers from being a reference listing rather than actionable guidance. It lacks concrete examples with realistic parameters, has no validation steps for destructive operations like bulk product creation, and contains redundant content (workflows duplicated in the quick reference table). The skill would benefit significantly from executable examples and splitting into overview + reference files.

Suggestions

Add concrete, executable examples showing actual tool calls with realistic parameter values (e.g., a complete RUBE_SEARCH_TOOLS call followed by a SHOPIFY_BULK_CREATE_PRODUCTS call with sample product data)

Add explicit validation/verification steps after destructive operations like bulk product creation (e.g., 'After bulk create, call SHOPIFY_GET_PRODUCTS to verify products were created correctly')

Remove the quick reference table or the detailed workflow sections to eliminate redundancy—keep one authoritative source for tool-to-parameter mappings

Split the detailed workflow sections and pitfalls into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with the setup flow and most common patterns

DimensionReasoningScore

Conciseness

The skill is moderately efficient but includes unnecessary padding like the 'When to use' descriptions that restate the obvious, the 'When to Use' section at the bottom that adds nothing, and some pitfalls that explain basic concepts Claude would know (e.g., 'Customer data includes order count and total spent'). The quick reference table largely duplicates the workflow sections above it.

3 / 5

Actionability

The skill lists tool names and key parameters, which is somewhat concrete, but lacks executable examples showing actual tool calls with realistic parameter values. The instruction to 'always call RUBE_SEARCH_TOOLS first to get current tool schemas' undermines the value of the detailed tool listings, and the GraphQL section is pseudocode rather than a real example. No actual input/output examples are provided.

3 / 5

Workflow Clarity

The setup workflow has a clear 4-step sequence with a validation checkpoint (confirm ACTIVE status). However, the core workflows mark most steps as [Optional] without clear decision logic for when to use each, and there are no validation/verification steps after performing operations like bulk product creation or inventory changes—destructive/batch operations without validation caps this at 3.

3 / 5

Progressive Disclosure

The content is a monolithic file with no references to supporting files despite being long enough (~150 lines) to benefit from splitting. The quick reference table, detailed workflow sections, and pitfalls could be organized into separate files. There are no bundle files to reference, and the skill doesn't attempt any progressive structure beyond section headers.

2 / 5

Total

11

/

20

Passed

Description

53%Scale 1-5

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 identifies the platform (Shopify) and lists the resource domains it covers, providing reasonable distinctiveness. However, it lacks concrete action verbs describing what can be done with those resources, and critically missing an explicit 'Use when...' clause that would help Claude select this skill appropriately. The operational instruction about searching tools first takes up space that could be used for better trigger guidance.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about Shopify store management, e-commerce operations, or mentions Shopify products, orders, or inventory.'

Replace the noun list with concrete action phrases: e.g., 'Create and update products, process and fulfill orders, manage customer records, track inventory levels, organize collections.'

Include natural synonyms and related terms users might say, such as 'e-commerce', 'online store', 'shop', 'fulfillment', or 'catalog management'.

DimensionReasoningScore

Specificity

Names the domain (Shopify) and lists resource areas (products, orders, customers, inventory, collections) but doesn't describe concrete actions like 'create products', 'update inventory', or 'process orders'. The listed items are nouns/domains rather than specific actions.

3 / 5

Completeness

Has a reasonable 'what' (automate Shopify tasks across several resource types) but lacks an explicit 'when' clause. There's no 'Use when...' guidance for Claude to know when to select this skill. The instruction to 'search tools first' is operational guidance, not a trigger condition.

3 / 5

Trigger Term Quality

Includes 'Shopify', 'products', 'orders', 'customers', 'inventory', 'collections' which are relevant keywords, but misses natural user phrases like 'e-commerce', 'store', 'shop', 'fulfillment', 'shipping', or action-oriented terms users would say like 'add a product' or 'check order status'.

3 / 5

Distinctiveness Conflict Risk

The combination of 'Shopify' and 'Rube MCP (Composio)' makes this fairly distinct. It's unlikely to conflict with other skills unless there are multiple Shopify-related skills. The specific platform mention reduces overlap risk significantly.

4 / 5

Total

13

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.