CtrlK
BlogDocsLog inGet started
Tessl Logo

square-automation

Automate Square tasks via Rube MCP (Composio): payments, orders, invoices, locations. Always search tools first for current schemas.

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/square-automation/SKILL.md

The canonical home for this skill is square-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

56%Scale 1-5

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

The skill provides a reasonable overview of Square automation via Rube MCP with clear workflow sequences and useful pitfall documentation. However, it suffers from redundancy across sections (pitfalls and patterns repeated multiple times), lacks concrete executable examples showing actual tool invocation syntax, and could benefit from consolidation or splitting into separate reference files. The setup section is well-structured but the body content explains things Claude likely already knows (pagination, RFC 3339 format).

Suggestions

Add concrete tool invocation examples showing actual parameter JSON structures (e.g., the exact query object format for SQUARE_SEARCH_ORDERS) instead of pseudocode steps.

Consolidate pitfalls into a single section rather than repeating them in both per-workflow sections and the 'Known Pitfalls' section — this would significantly reduce token usage.

Remove explanations of concepts Claude already knows (RFC 3339 format, pagination patterns, what rate limits are) and replace with just the specific values/thresholds relevant to Square.

Add explicit error recovery steps for destructive operations like CANCEL_PAYMENT and CANCEL_INVOICE (e.g., verify status before cancelling, confirm result after).

DimensionReasoningScore

Conciseness

The skill is moderately efficient but includes redundant information across sections. The 'Known Pitfalls' section repeats points already covered in per-workflow pitfalls (e.g., versioning, pagination, ID resolution). The 'Common Patterns' section also duplicates guidance from the workflows. The 'When to Use' footer is vacuous. Claude already knows RFC 3339 format and basic pagination patterns.

3 / 5

Actionability

The skill provides tool names, parameter lists, and sequences, but lacks executable code or concrete MCP call examples with actual parameter structures. The 'Common Patterns' section uses pseudocode-like numbered steps rather than showing actual tool invocation syntax. Key details like the exact JSON structure for search queries or update payloads are missing.

3 / 5

Workflow Clarity

Workflows are clearly sequenced with labeled steps (Required/Optional/Prerequisite), and there are implicit validation points (check connection is ACTIVE, check version before update, follow cursor until absent). However, explicit validation checkpoints and error recovery loops are mostly absent — for example, no guidance on what to do if UPDATE_ORDER returns a 409 conflict beyond mentioning it exists.

4 / 5

Progressive Disclosure

The content is a single monolithic file with no bundle files or external references. At ~180 lines with significant repetition between sections (pitfalls repeated in per-workflow and Known Pitfalls), the content would benefit from splitting detailed API reference and pitfalls into separate files. The quick reference table is helpful but the overall structure could be tighter.

3 / 5

Total

13

/

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 a clear domain (Square automation via Composio) and lists key capability areas, but lacks concrete action verbs and an explicit 'Use when...' clause. The trigger terms cover the basics but miss common synonyms and natural user language. Adding explicit trigger guidance and more specific actions would significantly improve skill selection accuracy.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Square payments, processing orders, creating invoices, managing Square locations, or mentions Composio/Square API.'

Replace category nouns with concrete action phrases, e.g., 'Process payments, manage orders, create and send invoices, look up store locations' instead of just 'payments, orders, invoices, locations.'

Include natural synonyms and related terms users might say, such as 'refund', 'charge', 'POS', 'point of sale', 'billing', or 'Square API'.

DimensionReasoningScore

Specificity

Names the domain (Square tasks via Rube MCP/Composio) and lists several capability areas (payments, orders, invoices, locations), but these are nouns/categories rather than concrete actions like 'create invoices' or 'process payments'. The instruction to 'search tools first' is a procedural note, not a capability.

3 / 5

Completeness

The 'what' is present (automate Square tasks for payments, orders, invoices, locations) but there is no explicit 'when' clause. There's no 'Use when...' guidance to help Claude decide when to select this skill over others, which caps this dimension at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes relevant keywords like 'Square', 'payments', 'orders', 'invoices', 'locations', and 'Composio', but misses natural user phrases like 'charge', 'refund', 'billing', 'POS', 'point of sale', or 'Square API'. The term 'Rube MCP' is technical jargon unlikely to be used by end users.

3 / 5

Distinctiveness Conflict Risk

The mention of 'Square' and 'Rube MCP (Composio)' creates a fairly distinct niche. It's unlikely to conflict with generic payment or invoice skills due to the specific platform references. Minor overlap risk exists with other payment-processing or Composio-related skills.

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.