CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

stripe-automation

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

Quality

70%

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

57%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 with concrete tool names, parameters, and genuinely useful pitfalls, and it doesn't waste tokens explaining concepts Claude already knows. Its weaknesses are systematic redundancy, blanket "[Optional]" step markers that obscure real sequencing, and absent verification steps for destructive payment operations like charges and refunds.

Suggestions

Add verification checkpoints to the risky workflows: before issuing a refund, verify the charge ID and confirm the amount with the user; before creating a charge or subscription, confirm the customer has a valid payment method.

Consolidate the amount-unit guidance into one place (e.g., Common Patterns only), remove the filler "When to Use" sentence, and drop the "[Optional]" tags in favor of actual ordering guidance.

Move the Quick Reference table and per-workflow parameter details into a references/ file (e.g., reference.md), keeping SKILL.md as a concise overview with well-signaled one-level-deep links.

DimensionReasoningScore

Conciseness

Amount-unit guidance is repeated in three places ("Amounts are in smallest currency unit (100 = $1.00 for USD)", the "Amount Formatting" section, and "Known Pitfalls / Amount Units"), the 21-row Quick Reference table restates the workflow tool lists, and "When to Use This skill is applicable to execute the workflow or actions described in the overview." is pure filler. Mostly efficient but clearly could be tightened — anchor 3, not 4, because the redundancy is systematic rather than a minor instance.

3 / 5

Actionability

Provides concrete tool slugs, parameter names, and pitfalls with worked values ("'usd' not 'USD'", "Customer IDs start with 'cus_'", "100 = $1.00 for USD"). Not 5: there is no worked example of a complete tool call with values, and marking every step in every "Tool sequence" as "[Optional]" leaves the actual decision of which tool to use unresolved.

4 / 5

Workflow Clarity

The Setup section does have validation checkpoints ("Confirm connection status shows ACTIVE before running any workflows"), but the money-moving workflows — charges and refunds — include no verification steps (e.g., confirm the charge ID and amount before refunding), and every step being "[Optional]" blurs the intended sequence. The destructive/batch-operations guideline caps this at 3; not 4 because validation gaps exist in the risky workflows themselves, not just minor ones.

3 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers, but at ~190 lines it inlines a 21-row quick-reference table and full per-workflow parameter documentation that belong in reference files, and there are no bundle files at all to offload detail to. Anchor 3 (content that should be separate is inline); not 4 because the quick-reference/API-detail bulk is squarely the kind of content the anchor expects in a separate file.

3 / 5

Total

13

/

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.

The description names a distinct, well-scoped niche and lists six concrete Stripe object areas, but it never states when to use the skill. Adding an explicit trigger clause and replacing the generic "Automate Stripe tasks" with specific action verbs would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to create or look up Stripe customers, charge customers, manage subscriptions or invoices, or issue refunds."

Replace the generic verb "Automate Stripe tasks" with concrete actions per area, e.g. "create customers, issue refunds, set up subscriptions, generate invoices".

Consider adding high-frequency synonyms such as "payments" or "billing" to improve trigger term coverage.

DimensionReasoningScore

Specificity

Enumerates six concrete Stripe object areas ("customers, charges, subscriptions, invoices, products, refunds") but the only verb is the generic "Automate Stripe tasks" — no distinct per-area actions. This fits anchor 4 (several specific items, minor gaps) better than 5, which requires multiple concrete action verbs, and better than 3, which covers only 1-2 areas.

4 / 5

Completeness

Has a clear "what" (automating Stripe operations across six object types) but the "when" is entirely missing — "Always search tools first for current schemas" is an instruction, not trigger guidance. Per the guideline, a missing 'Use when...' clause caps completeness at 3; not 4 because no trigger context exists at all, even weakly.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("Stripe", "customers", "charges", "subscriptions", "invoices", "refunds"), giving good keyword coverage. Not 5: misses common variations like "payments", "billing", or verb phrases such as "issue a refund" or "create a subscription".

4 / 5

Distinctiveness Conflict Risk

"Automate Stripe tasks via Rube MCP (Composio)" defines a clear niche pinned to both Stripe and a specific MCP integration, with distinct triggers and minimal conflict risk outside another Stripe skill. Clearly matches the anchor-5 example pattern.

5 / 5

Total

16

/

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

skills/stripe-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.