Automate Square tasks via Rube MCP (Composio): payments, orders, invoices, locations. Always search tools first for current schemas.
66
51%
Does it follow best practices?
Impact
90%
1.21xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/square-automation/SKILL.mdQuality
Discovery
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 identifies a clear niche (Square automation via Rube MCP/Composio) with good distinctiveness, but falls short on completeness by lacking explicit trigger guidance ('Use when...') and on specificity by listing domain nouns rather than concrete actions. The operational instruction about searching tools first takes up space that could be used for better trigger terms or action descriptions.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Square payments, processing orders, creating invoices, or managing Square locations.'
Replace domain nouns with concrete actions, e.g., 'Process payments, manage orders, create and send invoices, list and update locations' instead of just 'payments, orders, invoices, locations.'
Add common user-facing trigger variations like 'POS', 'point of sale', 'Square API', 'billing', or 'refunds' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists domain areas (payments, orders, invoices, locations) and mentions searching tools first, but doesn't describe specific concrete actions like 'create invoices', 'process payments', or 'list orders'. The actions are implied by the nouns rather than explicitly stated. | 2 / 3 |
Completeness | Describes what it does (automate Square tasks) but has no explicit 'Use when...' clause or equivalent trigger guidance. The instruction to 'always search tools first' is operational guidance, not a when-to-use trigger. Per rubric, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately detailed, so this lands at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Square', 'payments', 'orders', 'invoices', 'locations', and 'Rube MCP (Composio)' which are useful triggers. However, it misses common user variations like 'payment processing', 'POS', 'point of sale', 'billing', or 'Square API'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Square', 'Rube MCP (Composio)', and the specific domain areas (payments, orders, invoices, locations) creates a clear niche that is unlikely to conflict with other skills. The platform-specific naming makes it highly distinguishable. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid workflow structure with clear sequencing and good safety considerations (version checks, status validation, pagination handling). However, it suffers from moderate redundancy across sections and lacks concrete, executable tool invocation examples with actual parameter payloads and response shapes. The content would benefit from deduplication and more actionable examples showing real MCP tool calls.
Suggestions
Add at least one concrete, complete tool invocation example per workflow showing actual parameter values and expected response structure (e.g., a full RUBE_SEARCH_TOOLS call with the Square toolkit and its response).
Consolidate repeated pitfalls (pagination, location_id resolution, versioning) into the 'Common Patterns' or 'Known Pitfalls' section only, and reference them from individual workflows instead of restating them.
Show the exact structure of the `query` filter object for SQUARE_SEARCH_ORDERS, as this is a complex parameter that Claude would need specific guidance on.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some redundancy—pitfalls are repeated across sections (e.g., pagination, location_id requirements, version fields mentioned multiple times), and the 'Known Pitfalls' section largely restates what was already covered in individual workflow pitfalls. The 'Common Patterns' section also partially duplicates workflow steps. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | The skill provides clear tool names, parameter lists, and sequences, but lacks executable code or concrete tool invocation examples with actual parameter payloads. The 'Common Patterns' section uses pseudocode-style numbered lists rather than showing actual MCP tool calls with example arguments and expected response structures. Key details like exact query filter object structure for SEARCH_ORDERS are missing. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit prerequisite steps, labeled as [Required]/[Optional]/[Prerequisite]. The setup section includes a verification flow (check connection → authenticate if needed → confirm ACTIVE). Validation checkpoints are present: version checks before updates, status checks before cancellations, and pagination loops with clear termination conditions. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a quick reference table, but it's a long monolithic file (~180 lines of content) with no bundle files to offload detailed reference material. The pitfalls, common patterns, and per-workflow details could benefit from being split into separate reference files, especially given the repetition between sections. | 2 / 3 |
Total | 9 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
d065ead
Table of Contents
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.