stripe-automation

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

1.32x

Quality

65%

Does it follow best practices?

Impact

97%

1.32x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/stripe-automation/SKILL.md

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 content is a dense, well-structured operational reference with concrete tool slugs, parameters, and genuinely useful Stripe-specific pitfalls. Its weaknesses are repeated amount-unit content, a quick-reference table that duplicates the workflow sections, and the absence of validation checkpoints for irreversible financial operations like charges and refunds.

Suggestions

Consolidate the smallest-currency-unit rules (stated in the charges pitfalls, 'Amount Formatting', and 'Known Pitfalls') into a single section.

Add pre-flight validation steps to financial workflows, e.g., verify the customer and amount (in smallest currency unit) before creating a charge or issuing a refund.

Trim or move the 21-row Quick Reference table into a separate reference file to reduce duplication with the workflow sections.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's knowledge of Stripe and MCP with no padded explanation, but it could be tightened: smallest-currency-unit rules appear three times (charges pitfalls, "Amount Formatting", "Known Pitfalls"), and the 21-row Quick Reference table largely re-lists the workflow tool sequences.	3 / 5
Actionability	Concrete tool slugs, key parameters with example values ('cus_xxx', 'usd'), ID prefixes, and pagination mechanics make most guidance executable; minor gaps remain (e.g., no example structure for the subscription `items` array, no sample tool-call payloads).	4 / 5
Workflow Clarity	The setup sequence is well-checkpointed (confirm RUBE_SEARCH_TOOLS responds, confirm ACTIVE status before running workflows), but money-moving workflows (charges, refunds, subscriptions) include no validation or verification steps — e.g., confirm amount/customer before creating a charge — which caps workflow clarity at 3 per the rubric's destructive-operation rule.	3 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well-sectioned with clear headers, per-workflow structure, and a navigable quick-reference table; minor organization gaps in that the long tool table and per-tool details could live in a separate reference file.	4 / 5
	Total	14 / 20 Passed

Description

70%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.

A strong, specific description that names the domain, the integration path, and six concrete capability areas. Its main weakness is the complete absence of a 'when to use' trigger clause, which the rubric explicitly penalizes, and slightly generic action phrasing ('Automate Stripe tasks').

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to manage Stripe customers, payments, subscriptions, invoices, products, or refunds."

Replace the generic "Automate Stripe tasks" with concrete verbs per object, e.g. "Create and update customers, charge payments, issue refunds".

Include natural synonyms such as "payments" or "billing" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists six concrete object domains ("customers, charges, subscriptions, invoices, products, refunds") but the action itself is generic ("Automate Stripe tasks"), so coverage is strong with a minor gap rather than comprehensive.	4 / 5
Completeness	The 'what' is clear (automate Stripe operations via Rube MCP/Composio), but there is no 'Use when...' clause or equivalent trigger guidance — "Always search tools first for current schemas" is an instruction, not a usage trigger — which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Natural terms users would say are present ("Stripe", "customers", "subscriptions", "refunds", "invoices"), but common variations like "payments" or "billing" are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Stripe automation via Rube MCP/Composio) with distinct trigger terms (Stripe, refunds, invoices) that would not naturally invoke other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/stripe-automation/SKILL.md
Commit: c9856ea

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.