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.

72

1.32x
Quality

58%

Does it follow best practices?

Impact

97%

1.32x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/stripe-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 comprehensive catalog of Stripe operations via Rube MCP with good structural organization and useful pitfall warnings. However, it suffers from redundancy (amount formatting and pitfalls repeated multiple times), lacks concrete executable examples of actual MCP tool calls, and marks every workflow step as [Optional] which undermines actionability. Financial operations like charges and refunds would benefit from explicit validation/verification steps.

Suggestions

Add at least one concrete, complete example showing an actual RUBE_SEARCH_TOOLS call followed by a Stripe tool call with real input parameters and expected output structure.

Remove the [Optional] annotations from workflow steps and instead clearly indicate which steps are required vs optional, or show the minimum viable sequence for each workflow.

Add explicit validation steps after destructive/financial operations (e.g., verify charge was created successfully, confirm refund status) to improve workflow safety.

Consolidate the duplicated pitfalls — remove per-section 'amount is in smallest currency unit' warnings and keep only the 'Common Patterns' section for shared knowledge.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but has significant redundancy — the 'Known Pitfalls' section repeats amount unit warnings already stated in multiple workflow sections, and the quick reference table largely duplicates information from the core workflows. The ID prefixes and amount formatting sections appear twice in different forms.

2 / 3

Actionability

The skill provides specific tool names and parameter lists, which is useful, but lacks any executable code or concrete MCP call examples with actual input/output. Every tool step is marked [Optional], making it unclear what the actual recommended sequence is. The instruction to 'Always call RUBE_SEARCH_TOOLS first' is good but no example call is shown.

2 / 3

Workflow Clarity

The setup section has a clear 4-step sequence with a validation checkpoint (confirm ACTIVE status). However, the core workflows lack validation steps — for example, after creating a charge or refund, there's no verification step. For financial operations (charges, refunds), missing validation/feedback loops is a notable gap. Every step being marked [Optional] undermines the sequential clarity.

2 / 3

Progressive Disclosure

The content is well-structured with clear sections and a useful quick reference table, but it's quite long (~180 lines) with no bundle files to offload detail into. The repeated pitfalls and the large reference table could be split into separate files. The single external link to Composio docs is appropriate but the monolithic structure could benefit from splitting workflows into separate references.

2 / 3

Total

8

/

12

Passed

Description

67%

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 is concise and specific about its domain (Stripe automation via Composio) and lists concrete resource types it handles. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding common user-facing trigger terms like 'payment', 'billing', or 'checkout' would also improve discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Stripe operations, payment processing, billing, or managing subscriptions and invoices.'

Include additional natural trigger terms users might say, such as 'payment', 'billing', 'checkout', 'plan', 'pricing', or 'issue a refund'.

DimensionReasoningScore

Specificity

Lists multiple specific concrete entities/actions: customers, charges, subscriptions, invoices, products, refunds. Also includes a concrete procedural instruction ('Always search tools first for current schemas').

3 / 3

Completeness

Clearly answers 'what does this do' (automate Stripe tasks across multiple entities), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Includes good domain-specific terms like 'Stripe', 'customers', 'charges', 'subscriptions', 'invoices', 'products', 'refunds'. However, it lacks common user variations like 'payment', 'billing', 'plan', 'pricing', or action verbs users might say like 'create a subscription' or 'issue a refund'.

2 / 3

Distinctiveness Conflict Risk

Very clearly scoped to Stripe via Rube MCP (Composio), which is a distinct niche. The mention of the specific integration platform and Stripe makes it highly unlikely to conflict with other skills.

3 / 3

Total

10

/

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.

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
davepoon/buildwithclaude
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.