CtrlK
BlogDocsLog inGet started
Tessl Logo

stripe-automation

Automate Stripe tasks via Rube MCP (Composio): customers, charges, subscriptions, invoices, products, refunds. Always search tools first for current schemas.

49

Quality

54%

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 ./skills/stripe-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 broad reference for Stripe operations via Rube MCP with good structural organization and useful details like ID prefixes and amount formatting. However, it suffers from significant repetition (pitfalls repeated across sections), lacks concrete executable examples or actual tool call syntax, and marks every workflow step as [Optional] which undermines workflow clarity. Financial operations would benefit from explicit validation/verification steps.

Suggestions

Add at least one concrete, end-to-end example showing actual MCP tool call syntax with real parameters and expected response structure (e.g., creating a customer and then a subscription for them).

Remove the [Optional] markers from workflow steps and instead provide distinct workflows for distinct tasks (e.g., 'To create a charge: step 1, step 2, step 3') rather than listing all possible tools as optional.

Consolidate repeated pitfalls (amount formatting, currency units) into the single 'Known Pitfalls' section and remove duplicates from individual workflow sections.

Add validation/verification steps to financial workflows — e.g., after creating a payment intent, verify its status before confirming; after issuing a refund, check the refund status.

DimensionReasoningScore

Conciseness

The skill has significant repetition — amount formatting pitfalls are mentioned three times (in charges, refunds, and the dedicated section). The 'Known Pitfalls' section repeats information already covered in individual workflow sections. The quick reference table is useful but overlaps heavily with the workflow sections. Some content like 'When to Use: This skill is applicable to execute the workflow or actions described in the overview' is pure filler.

3 / 5

Actionability

The skill names specific tools and parameters, which is helpful, but lacks executable examples — no actual MCP tool call syntax or concrete input/output examples are shown. Every tool in the workflows is marked [Optional], making it unclear what the actual recommended sequence is for a given task. The setup steps are concrete, but the core workflows read more like reference documentation than actionable guidance.

3 / 5

Workflow Clarity

Workflows are listed as sequences but every step is marked [Optional], undermining the concept of a workflow. There are no validation checkpoints — for example, after creating a payment intent, there's no step to verify it was created successfully before confirming it. For financial operations (charges, refunds), the absence of verification/confirmation steps is a notable gap. The setup section has a reasonable sequence with a connection verification step.

3 / 5

Progressive Disclosure

The content is reasonably structured with clear section headers and a useful quick reference table. However, at ~180 lines with significant repetition, some content (like the full quick reference table or detailed per-workflow pitfalls) could be split into separate files. There are no bundle files or external references, and the skill is long enough that progressive disclosure would benefit from them.

3 / 5

Total

12

/

20

Passed

Description

58%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 effectively identifies the domain (Stripe) and lists key resource types, making it reasonably specific and distinct. However, it lacks an explicit 'Use when...' clause and misses common user-facing trigger terms like 'payment', 'billing', or 'checkout'. The listed entities are nouns rather than actionable verbs, which reduces clarity about what specific operations are supported.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Stripe payments, billing, managing customers, or processing refunds.'

Include natural user-facing trigger terms such as 'payment', 'billing', 'checkout', 'payment processing' alongside the entity names.

Convert entity nouns into action phrases, e.g., 'create and manage customers, process charges, handle subscriptions and invoices, issue refunds' to clarify supported operations.

DimensionReasoningScore

Specificity

Lists several specific Stripe entities (customers, charges, subscriptions, invoices, products, refunds) and mentions automation, but doesn't describe specific actions on those entities (e.g., 'create customers', 'issue refunds', 'manage subscriptions').

4 / 5

Completeness

The 'what' is reasonably clear (automate Stripe tasks across several domains), but there is no explicit 'when' clause. The description lacks a 'Use when...' statement, which per the rubric should cap completeness at 3.

3 / 5

Trigger Term Quality

Includes 'Stripe', 'customers', 'charges', 'subscriptions', 'invoices', 'products', 'refunds' which are relevant keywords, but misses natural user phrases like 'payment', 'billing', 'checkout', 'create a subscription', and the tool-specific terms 'Rube MCP' and 'Composio' are implementation details rather than user-facing trigger terms.

3 / 5

Distinctiveness Conflict Risk

Specifying 'Stripe' and the specific integration method ('Rube MCP / Composio') makes it fairly distinct. Minor overlap risk exists with other payment or Stripe-related skills, but the Composio/Rube MCP qualifier helps differentiate.

4 / 5

Total

14

/

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.