CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

square-automation

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

Quality

69%

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

61%Weight 40%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 body is well-structured and actionable, with concrete tool sequences, parameters, and pitfalls for each Square workflow. The main weaknesses are redundant content (pitfalls duplicated across sections, a vacuous closing line) and missing validation checkpoints before destructive operations like cancelling payments and invoices.

Suggestions

Add explicit validation steps before destructive operations, e.g., "Verify payment status is PENDING before calling SQUARE_CANCEL_PAYMENT" and "Confirm with the user before SQUARE_CANCEL_INVOICE — cancellation is irreversible".

Remove the filler "When to Use" closing line and deduplicate pitfalls between the workflow sections and the "Known Pitfalls" section.

Consider moving the Quick Reference table and Known Pitfalls into a references/ file to keep SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly tight, but pitfalls are duplicated between workflow sections and the "Known Pitfalls" section (versioning and location-ID resolution each appear twice), the Quick Reference table repeats the workflows' tool/param lists, and the closing line "This skill is applicable to execute the workflow or actions described in the overview" is filler. It is not a 2 because most sections are efficient and un-padded, and not a 4 because these redundancies are real trimming opportunities.

3 / 5

Actionability

Concrete tool sequences, required parameters, real example values ("2024-01-01T00:00:00Z", "L1234ABCD"), order states, and pagination mechanics give mostly executable guidance. Minor gaps: no actual tool-call payload examples, though schema discovery is explicitly delegated to RUBE_SEARCH_TOOLS.

4 / 5

Workflow Clarity

Sequences are clearly ordered with per-workflow "When to use" and prerequisites, and setup has a checkpoint (confirm connection ACTIVE). However, destructive operations — cancel payment, cancel invoice (explicitly irreversible), update order (409 on version mismatch) — lack verify-before-act validation steps in their sequences, which caps workflow clarity at 3 per the rubric's destructive-operation rule.

3 / 5

Progressive Disclosure

A single ~180-line file with well-organized, clearly headed sections covering all four workflows plus shared patterns; no bundle files exist so there are no buried or nested references. Minor gap: the Quick Reference table and Known Pitfalls could live in a separate reference file to slim the main skill.

4 / 5

Total

14

/

20

Passed

Description

65%Weight 40%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 names a distinct, well-scoped niche and lists the four Square object domains, but the action verb is generic ("Automate Square tasks") and there is no explicit "Use when..." trigger clause, capping both specificity and completeness. Adding concrete verbs and a trigger clause would move it toward the top anchors.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks about Square payments, orders, invoices, or business locations."

Replace the generic "Automate Square tasks" with concrete actions, e.g., "List and cancel payments, search and update orders, list and cancel invoices, resolve location IDs."

Include natural user synonyms such as "refunds" or "transactions" to broaden trigger coverage.

DimensionReasoningScore

Specificity

"Automate Square tasks" is a generic verb phrase; "payments, orders, invoices, locations" names four specific domains but no concrete actions (e.g., no "list/cancel payments" or "search/update orders"). This sits between anchor 3 and anchor 4 — specific objects but non-specific actions — so 3 is the best fit.

3 / 5

Completeness

The "what" is clear (automate Square payments, orders, invoices, locations via Rube MCP), but there is no "Use when..." clause or equivalent explicit trigger guidance — per the judging guidelines this caps completeness at 3. It is not a 2 because the "what" is concrete, and not a 4 because the "when" is entirely absent rather than weakly implied.

3 / 5

Trigger Term Quality

"Square", "payments", "orders", "invoices" are natural terms users would say, giving good keyword coverage; missing common variations like "refunds", "transactions", or "billing", and "Rube MCP (Composio)" is technical jargon rather than a user phrase.

4 / 5

Distinctiveness Conflict Risk

Square payment processing accessed via a named MCP (Rube/Composio) is a clear niche with distinct triggers ("Square", "payments", "invoices") and minimal overlap risk with other skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

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

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.