square-automation
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 via Rube MCP/Composio) which makes it distinctive, but it lacks an explicit 'Use when...' clause and lists only broad categories rather than specific actions. Adding trigger guidance and more concrete action verbs would significantly improve skill selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Square payments, orders, invoices, locations, or any Square API task via Composio.'
Replace broad category nouns with specific action phrases, e.g., 'Process payments, create and manage orders, generate invoices, list and update locations' instead of just 'payments, orders, invoices, locations'.
Include additional natural trigger terms users might say, such as 'refunds', 'Square API', 'catalog', 'customers', or 'transaction history'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Square) and lists some action areas (payments, orders, invoices, locations), but these are categories rather than specific concrete actions like 'create invoices' or 'process payments'. The instruction to 'search tools first' is a procedural note rather than a capability. | 2 / 3 |
Completeness | Describes what it does (automate Square tasks) but has no explicit 'Use when...' clause or equivalent trigger guidance. The rubric states a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat thin, 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. However, it misses common user variations like 'payment processing', 'refunds', 'catalog', 'customers', or 'Square API'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Square' and 'Rube MCP (Composio)' creates a very clear niche. It is unlikely to conflict with other skills since it targets a specific platform integration via a specific tool. | 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 a solid structural framework for Square automation via Rube MCP with clear workflow sequences and good labeling of required vs optional steps. Its main weaknesses are redundancy across sections (pitfalls repeated in both per-workflow and summary sections) and lack of executable examples showing actual tool invocation syntax. The content would benefit from consolidating repeated guidance and adding concrete call examples.
Suggestions
Add at least one concrete, executable MCP tool call example showing exact parameter format (e.g., the JSON payload for SQUARE_SEARCH_ORDERS with a date filter and location_ids)
Consolidate repeated pitfalls (pagination, location_id resolution, versioning) into the 'Known Pitfalls' or 'Common Patterns' section only, and reference that section from individual workflows instead of restating
Consider extracting the detailed per-workflow sections into a separate reference file and keeping SKILL.md as a concise overview with the quick reference table and common patterns
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured 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 repeats pagination and date filtering guidance. Could be tightened by ~30%. | 2 / 3 |
Actionability | Tool sequences and parameter names are clearly listed, which is helpful. However, there are no executable code examples or actual MCP call syntax shown — the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual tool invocation examples. Key details like the exact JSON structure for search queries or update payloads are missing. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with labeled steps (Required/Optional/Prerequisite), explicit tool ordering, and validation checkpoints (e.g., confirm connection is ACTIVE before proceeding, check version before updates, verify cursor for pagination). The setup section includes a clear verification flow. Destructive operations (cancel) have clear precondition checks. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a quick reference table, but it's a fairly long monolithic document (~180 lines of content) with significant repetition. The toolkit docs link is provided, but there are no references to separate files for detailed API schemas, examples, or advanced patterns that could reduce the main file's length. | 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 | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.